Fault Diagnosis of Hydraulic Components Based on Multi-Sensor Information Fusion Using Improved TSO-CNN-BiLSTM

In order to realize the accurate and reliable fault diagnosis of hydraulic systems, a diagnostic model based on improved tuna swarm optimization (ITSO), optimized convolutional neural networks (CNNs), and bi-directional long short-term memory (BiLSTM) networks is proposed. Firstly, sensor selection is implemented using the random forest algorithm to select useful signals from six kinds of physical or virtual sensors including pressure, temperature, flow rate, vibration, motor power, and motor efficiency coefficient. After that, fused features are extracted by CNN, and then, BiLSTM is applied to learn the forward and backward information contained in the data. The ITSO algorithm is adopted to adaptively optimize the learning rate, regularization coefficient, and node number to obtain the optimal CNN-BiLSTM network. Improved Chebyshev chaotic mapping and the nonlinear reduction strategy are adopted to improve population initialization and individual position updating, further promoting the optimization effect of TSO. The experimental results show that the proposed method can automatically extract fusion features and effectively utilize multi-sensor information. The diagnostic accuracies of the plunger pump, cooler, throttle valve, and accumulator are 99.07%, 99.4%, 98.81%, and 98.51%, respectively. The diagnostic results of noisy data with 0 dB, 5 dB, and 10 dB signal-to-noise ratios (SNRs) show that the ITSO-CNN-BiLSTM model has good robustness to noise interference.

Fault Diagnosis for Reducers Based on a Digital Twin

A new method based on a digital twin is proposed for fault diagnosis, in order to compensate for the shortcomings of the existing methods for fault diagnosis modeling, including the single fault type, low similarity, and poor visual effect of state monitoring. First, a fault diagnosis test platform is established to analyze faults under constant and variable speed conditions. Then, the obtained data are integrated into the Unity3D platform to realize online diagnosis and updated with real-time working status data. Finally, an industrial test of the digital twin model is conducted, allowing for its comparison with other advanced methods in order to verify its accuracy and application feasibility. It was found that the accuracy of the proposed method for the entire reducer was 99.5%, higher than that of other methods based on individual components (e.g., 93.5% for bearings, 96.3% for gear shafts, and 92.6% for shells).

A Synchrosqueezed Transform Method Based on Fast Kurtogram and Demodulation and Piecewise Aggregate Approximation for Bearing Fault Diagnosis

Synchrosqueezed transform (SST) is a time-frequency analysis method that can improve energy aggregation and reconstruct signals, which has been applied in the fields of medical treatment, fault diagnosis, and seismic wave processing. However, when dealing with time-varying signals, SST suffers from poor time-frequency resolution and is unable to deal with long signals. In order to accurately extract the characteristic frequency of variable speed rolling bearing faults, this paper proposes a synchrosqueezed transform method based on fast kurtogram and demodulation and piecewise aggregate approximation (PAA). The method firstly filters and demodulates the original signal using fast kurtogram and Hilbert transform to reduce the influence of background noise and improve the time-frequency resolution. Then, it compresses the signal by using piecewise aggregate approximation, so that the SST can deal with long signals and, thus, extract the fault characteristic frequency. The experimental data verification results indicate that the method can effectively identify the fault characteristic frequency of variable-speed rolling bearings.

A New Denoising Method for Belt Conveyor Roller Fault Signals

In the process of the intelligent inspection of belt conveyor systems, due to problems such as its long duration, the large number of rollers, and the complex working environment, fault diagnosis by acoustic signals is easily affected by signal coupling interference, which poses a great challenge to selecting denoising methods of signal preprocessing. This paper proposes a novel wavelet threshold denoising algorithm by integrating a new biparameter and trisegment threshold function. Firstly, we elaborate on the mutual influence and optimization process of two adjustment parameters and three wavelet coefficient processing intervals in the BT-WTD (the biparameter and trisegment of wavelet threshold denoising, BT-WTD) denoising model. Subsequently, the advantages of the proposed threshold function are theoretically demonstrated. Finally, the BT-WTD algorithm is applied to denoise the simulation signals and the vibration and acoustic signals collected from the belt conveyor experimental platform. The experimental results indicate that this method's denoising effectiveness surpasses that of traditional threshold function denoising algorithms, effectively addressing the denoising preprocessing of idler roller fault signals under strong noise backgrounds while preserving useful signal features and avoiding signal distortion problems. This research lays the theoretical foundation for the non-contact intelligent fault diagnosis of future inspection robots based on acoustic signals.

Transmission Line Fault Classification Based on the Combination of Scaled Wavelet Scalograms and CNNs Using a One-Side Sensor for Data Collection

This research focuses on leveraging wavelet transform for fault classification within electrical power transmission networks. This study meticulously examines the influence of various parameters, such as fault resistance, fault inception angle, fault location, and other essential components, on the accuracy of fault classification. We endeavor to explore the interplay between classification accuracy and the input data while assessing the efficacy of combining wavelet analysis with deep learning methodologies. The data, sourced from network recorders, including phase currents and voltages, undergo a scaled continuous wavelet transform (S-CWT) to generate scalogram images. These images are subsequently utilized as inputs for pretrained deep learning models. The experiments encompass various fault scenarios, spanning distinct fault types, locations, times, and resistance values. A remarkable feature of the proposed work is the attainment of 100% classification accuracy, obviating the need for additional algorithmic enhancements. The foundation of this achievement is the deliberate selection of the right input. The decision to employ an identical number of samples as the number of scales for the CWT emerges as a pivotal factor. This approach underpins the high accuracy and renders supplementary algorithms superfluous. Furthermore, this research underscores the versatility of this approach, showcasing its effectiveness across diverse networks and scenarios. Wavelet transform, after rigorous experimentation, emerges as a reliable tool for capturing transient fault characteristics with an optimal balance between time and frequency resolutions.

Unmanned Surface Vehicle Thruster Fault Diagnosis via Vibration Signal Wavelet Transform and Vision Transformer under Varying Rotational Speed Conditions

Among unmanned surface vehicle (USV) components, underwater thrusters are pivotal in their mission execution integrity. Yet, these thrusters directly interact with marine environments, making them perpetually susceptible to malfunctions. To diagnose thruster faults, a non-invasive and cost-effective vibration-based methodology that does not require altering existing systems is employed. However, the vibration data collected within the hull is influenced by propeller-fluid interactions, hull damping, and structural resonant frequencies, resulting in noise and unpredictability. Furthermore, to differentiate faults not only at fixed rotational speeds but also over the entire range of a thruster's rotational speeds, traditional frequency analysis based on the Fourier transform cannot be utilized. Hence, Continuous Wavelet Transform (CWT), known for attributions encapsulating physical characteristics in both time-frequency domain nuances, was applied to address these complications and transform vibration data into a scalogram. CWT results are diagnosed using a Vision Transformer (ViT) classifier known for its global context awareness in image processing. The effectiveness of this diagnosis approach was verified through experiments using a USV designed for field experiments. Seven cases with different fault types and severity were diagnosed and yielded average accuracy of 0.9855 and 0.9908 at different vibration points, respectively.

A Novel Fault Diagnosis Strategy for Diaphragm Pumps Based on Signal Demodulation and PCA-ResNet

The efficient and accurate identification of diaphragm pump faults is crucial for ensuring smooth system operation and reducing energy consumption. The structure of diaphragm pumps is complex and using traditional fault diagnosis strategies to extract typical fault characteristics is difficult, facing the risk of model overfitting and high diagnostic costs. In response to the shortcomings of traditional methods, this study innovatively combines signal demodulation methods with residual networks (ResNet) to propose an efficient fault diagnosis strategy for diaphragm pumps. By using a demodulation method based on principal component analysis (PCA), the vibration signal demodulation spectrum of the fault condition is obtained, the typical fault characteristics of the diaphragm pump are accurately extracted, and the sample features are enhanced, reducing the cost of fault diagnosis. Afterward, the PCA-ResNet model is applied to the fault diagnosis of diaphragm pumps. A reasonable model structure and advanced residual block design can effectively reduce the risk of model overfitting and improve the accuracy of fault diagnosis. Compared with the visual geometry group (VGG) 16, VGG19, ResNet50, and autoencoder models, the proposed model has improved accuracy by 35.89%, 80.27%, 2.72%, and 6.12%. Simultaneously, it has higher operational efficiency and lower loss rate, solving the problem of diagnostic lag in practical engineering. Finally, a model optimization strategy is proposed through model evaluation metrics and testing. The reasonable parameter range of the model is obtained, providing a reference and guarantee for further optimization of the model.

Remote Fault Diagnosis for the Powertrain System of Fuel Cell Vehicles Based on Random Forest Optimized with a Genetic Algorithm

To enhance the safety and reliability of fuel cell vehicles, a remote monitoring system based on 5th generation (5G) mobile networks and controller area networks (CANs) was designed, and a random forest (RF) algorithm for the fault diagnosis for eight typical malfunctions of its powertrain system was incorporated. Firstly, the information on the powertrain system was obtained through a 5G-based monitoring terminal, and the Alibaba Cloud IoT platform was utilized for data storage and remote monitoring. Secondly, a fault diagnosis model based on the RF algorithm was constructed for fault classification; its parameters were optimized with a genetic algorithm (GA), and it was applied on the Alibaba Cloud PAI platform. Finally, the performance of the proposed RF fault diagnosis model was evaluated by comparing it with three other classification models: random search conditioning, grid search conditioning, and Bayesian optimization. Results show that the model accuracy, F1 score, and kappa value of the optimized RF fault classification model are higher than the other three. The model achieves an F1 value of 97.77% in identifying multiple typical faults of the powertrain system, as validated by vehicle malfunction data. The method demonstrates the feasibility of remote monitoring and fault diagnosis for the powertrain system of fuel cell vehicles.

Open-Circuit Fault Diagnosis of T-Type Three-Level Inverter Based on Knowledge Reduction

Compared with traditional two-level inverters, multilevel inverters have many solid-state switches and complex composition methods. Therefore, diagnosing and treating inverter faults is a prerequisite for the reliable and efficient operation of the inverter. Based on the idea of intelligent complementary fusion, this paper combines the genetic algorithm-binary granulation matrix knowledge-reduction method with the extreme learning machine network to propose a fault-diagnosis method for multi-tube open-circuit faults in T-type three-level inverters. First, the fault characteristics of power devices at different locations of T-type three-level inverters are analyzed, and the inverter output power and its harmonic components are extracted as the basis for power device fault diagnosis. Second, the genetic algorithm-binary granularity matrix knowledge-reduction method is used for optimization to obtain the minimum attribute set required to distinguish the state transitions in various fault cases. Finally, the kernel attribute set is utilized to construct extreme learning machine subclassifiers with corresponding granularity. The experimental results show that the classification accuracy after attribute reduction is higher than that of all subclassifiers under different attribute sets, reflecting the advantages of attribute reduction and the complementarity of different intelligent diagnosis methods, which have stronger fault-diagnosis accuracy and generalization ability compared with the existing methods and provides a new way for hybrid intelligent diagnosis.

An Adaptive Deconvolution Method with Improve Enhanced Envelope Spectrum and Its Application for Bearing Fault Feature Extraction

To address the problem that complex bearing faults are coupled to each other, and the difficulty of diagnosis increases, an improved envelope spectrum-maximum second-order cyclostationary blind deconvolution (IES-CYCBD) method is proposed to realize the separation of vibration signal fault features. The improved envelope spectrum (IES) is obtained by integrating the part of the frequency axis containing resonance bands in the cyclic spectral coherence function. The resonant bands corresponding to different fault types are accurately located, and the IES with more prominent target characteristic frequency components are separated. Then, a simulation is carried out to prove the ability of this method, which can accurately separate and diagnose fault types under high noise and compound fault conditions. Finally, a compound bearing fault experiment with inner and outer ring faults is designed, and the inner and outer ring fault characteristics are successfully separated by the proposed IES-CYCBD method. Therefore, simulation and experiments demonstrate the strong capability of the proposed method for complex fault separation and diagnosis.

Residual Shrinkage ViT with Discriminative Rebalancing Strategy for Small and Imbalanced Fault Diagnosis

In response to the challenge of small and imbalanced Datasets, where the total Sample size is limited and healthy Samples significantly outweigh faulty ones, we propose a diagnostic framework designed to tackle Class imbalance, denoted as the Dual-Stream Adaptive Deep Residual Shrinkage Vision Transformer with Interclass-Intraclass Rebalancing Loss (DSADRSViT-IIRL). Firstly, to address the issue of limited Sample quantity, we incorporated the Dual-Stream Adaptive Deep Residual Shrinkage Block (DSA-DRSB) into the Vision Transformer (ViT) architecture, creating a DSA-DRSB that adaptively removes redundant signal information based on the input data characteristics. This enhancement enables the model to focus on the Global receptive field while capturing crucial local fault discrimination features from the extremely limited Samples. Furthermore, to tackle the problem of a significant Class imbalance in long-tailed Datasets, we designed an Interclass-Intraclass Rebalancing Loss (IIRL), which decouples the contributions of the Intraclass and Interclass Samples during training, thus promoting the stable convergence of the model. Finally, we conducted experiments on the Laboratory and CWRU bearing Datasets, validating the superiority of the DSADRSViT-IIRL algorithm in handling Class imbalance within mixed-load Datasets.

Fault Diagnosis in Centrifugal Pumps: A Dual-Scalogram Approach with Convolution Autoencoder and Artificial Neural Network

This paper proposes a new fault diagnosis method for centrifugal pumps by combining signal processing with deep learning techniques. Centrifugal pumps facilitate fluid transport through the energy generated by the impeller. Throughout the operation, variations in the fluid pressure at the pump's inlet may impact the generalization of traditional machine learning models trained on raw statistical features. To address this concern, first, vibration signals are collected from centrifugal pumps, followed by the application of a lowpass filter to isolate frequencies indicative of faults. These signals are then subjected to a continuous wavelet transform and Stockwell transform, generating two distinct time-frequency scalograms. The Sobel filter is employed to further highlight essential features within these scalograms. For feature extraction, this approach employs two parallel convolutional autoencoders, each tailored for a specific scalogram type. Subsequently, extracted features are merged into a unified feature pool, which forms the basis for training a two-layer artificial neural network, with the aim of achieving accurate fault classification. The proposed method is validated using three distinct datasets obtained from the centrifugal pump under varying inlet fluid pressures. The results demonstrate classification accuracies of 100%, 99.2%, and 98.8% for each dataset, surpassing the accuracies achieved by the reference comparison methods.

Fault Diagnosis Methods for an Artillery Loading System Driving Motor in Complex Noisy Environments

With the development of modern military technology, electrical drive technology has become a power source for modern artillery. In fault monitoring of a driving motor mounted on a piece of artillery, various sensors are susceptible to interference from the complex environment, both inside and outside the artillery itself. In this study, we creatively propose a fault diagnosis model based on an attention mechanism, the AdaBoost method and a wavelet noise reduction network to address the difficulty in obtaining high-quality motor signals in complex noisy interference environments. First, multiple fusion wavelet basis, soft thresholding, and index soft filter optimization were used to train multiple wavelet noise reduction networks that could recover sample signals under different noise conditions. Second, a convolutional neural network (CNN) classification module was added to construct end-to-end classification models that could correctly identify faults. The above basis classification models were then integrated into the AdaBoost method with an improved attention mechanism to develop a fault diagnosis model suitable for complex noisy environments. Finally, two experiments were conducted to validate the proposed method. Under motor signals with varying signal-to-noise ratios (SNRs) noises, the proposed method achieved an average accuracy of 92%, surpassing the conventional method by over 8.5%.

Aircraft Engine Fault Diagnosis Model Based on 1DCNN-BiLSTM with CBAM

As the operational status of aircraft engines evolves, their fault modes also undergo changes. In response to the operational degradation trend of aircraft engines, this paper proposes an aircraft engine fault diagnosis model based on 1DCNN-BiLSTM with CBAM. The model can be directly applied to raw monitoring data without the need for additional algorithms to extract fault degradation features. It fully leverages the advantages of 1DCNN in extracting local features along the spatial dimension and incorporates CBAM, a channel and spatial attention mechanism. CBAM could assign higher weights to features relevant to fault categories and make the model pay more attention to them. Subsequently, it utilizes BiLSTM to handle nonlinear time feature sequences and bidirectional contextual feature information. Finally, experimental validation is conducted on the publicly available CMAPSS dataset from NASA, categorizing fault modes into three types: faultless, HPC fault (the single fault), and HPC&Fan fault (the mixed fault). Comparative analysis with other models reveals that the proposed model has a higher classification accuracy, which is of practical significance in improving the reliability of aircraft engine operations and for Remaining Useful Life (RUL) prediction.

Voiceprint Fault Diagnosis of Converter Transformer under Load Influence Based on Multi-Strategy Improved Mel-Frequency Spectrum Coefficient and Temporal Convolutional Network

In order to address the challenges of low recognition accuracy and the difficulty in effective diagnosis in traditional converter transformer voiceprint fault diagnosis, a novel method is proposed in this article. This approach takes account of the impact of load factors, utilizes a multi-strategy improved Mel-Frequency Spectrum Coefficient (MFCC) for voiceprint signal feature extraction, and combines it with a temporal convolutional network for fault diagnosis. Firstly, it improves the hunter-prey optimizer (HPO) as a parameter optimization algorithm and adopts IHPO combined with variational mode decomposition (VMD) to achieve denoising of voiceprint signals. Secondly, the preprocessed voiceprint signal is combined with Mel filters through the Stockwell transform. To adapt to the stationary characteristics of the voiceprint signal, the processed features undergo further mid-temporal processing, ultimately resulting in the implementation of a multi-strategy improved MFCC for voiceprint signal feature extraction. Simultaneously, load signal segmentation is introduced for the diagnostic intervals, forming a joint feature vector. Finally, by using the Mish activation function to improve the temporal convolutional network, the IHPO-ITCN is proposed to adaptively optimize the size of convolutional kernels and the number of hidden layers and construct a transformer fault diagnosis model. By constructing multiple sets of comparison tests through specific examples and comparing them with the traditional voiceprint diagnostic model, our results show that the model proposed in this paper has a fault recognition accuracy as high as 99%. The recognition accuracy was significantly improved and the training speed also shows superior performance, which can be effectively used in the field of multiple fault diagnosis of converter transformers.

Research on a Fault Diagnosis Method for Crankshafts Based on Improved Multi-Scale Permutation Entropy

As the crucial part of a transmission assembly, the monitoring of the status of the crankshaft is essential for the normal working of a reciprocating machinery system. In consideration of the interaction between crankshaft system components, the fault vibration feature is typically non-stationary and nonlinear, and the single-scale feature extraction method cannot adequately assess the fault features, therefore a novel impact feature extraction method based on genetic algorithms to optimize multi-scale permutation entropy is proposed. Compared with other traditional feature extraction methods, the proposed method illustrates good robustness and high adaptability in the signal processing of crankshaft vibrations. Firstly, the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) method is developed on the signal to obtain several intrinsic mode function (IMF) components, and the IMF components with a large kurtosis are selected for array reorganization. Then, the parameters of multi-scale permutation entropy (MPE) are optimized based on genetic algorithm (GA), the multi-scale permutation entropy is calculated and the feature vector set is constructed. The feature vector set is input into the support vector machine (SVM) and optimized by a particle swarm optimization (PSO) model for training and final pattern recognition, where the Variational Mode Decomposition(VMD)-GA-MPE with a PSO-SVM recognition model and the ICEEMDAN-MPE with PSO-SVM recognition model without GA optimization are constructed for a comparison with the proposed method. The research result illustrates that the proposed method, which inputs the genetic algorithm optimized multi-scale permutation entropy extracted from the ICEEMDAN decomposition into the PSO-SVM, performs well in impact feature extraction and the pattern recognition of crankshaft vibrations.

Analysis of Local Track Discontinuities and Defects in Railway Switches Based on Track-Side Accelerations

Switches are an essential, safety-critical part of the railway infrastructure. Compared to open tracks, their complex geometry leads to increased dynamic loading on the track superstructure from passing trains, resulting in high maintenance costs. To increase efficiency, condition monitoring methods specific to railway switches are required. A common approach to track superstructure monitoring is to measure the acceleration caused by vehicle track interaction. Local interruptions in the wheel-rail contact, caused for example by local defects or track discontinuities, appear in the data as transient impact events. In this paper, such transient events are investigated in an experimental setup of a railway switch with track-side acceleration sensors, using frequency and waveform analysis. The aim is to understand if and how the origins of these impact events can be distinguished in the data of this experiment, and what the implications for condition monitoring of local track discontinuities and defects with wayside acceleration sensors are in practice. For the same experimental configuration, individual impact events are shown to be reproducible in waveform and frequency content. Nevertheless, with this track-side sensor setup, the different types of track discontinuities and defects (squats, joints, crossing) could not be clearly distinguished using characteristic frequencies or waveforms. Other factors, such as the location of impact event origin relative to the sensor, are shown to have a much stronger influence. The experimental data suggest that filtering the data to narrow frequency bands around certain natural track frequencies could be beneficial for impact event detection in practice, but differentiating between individual impact event origins requires broadband signals. A multi-sensor setup with time-synchronized acceleration sensors distributed over the switch is recommended.

Anomaly Detection Method for Rocket Engines Based on Convex Optimized Information Fusion

The power system, as a core component of a launch vehicle, has a crucial impact on the reliability and safety of a rocket launch. Due to the limited measurement information inside the engine, it is often challenging to realize fast and accurate anomaly detection. For this reason, this paper introduces the rocket flight state data to expand the information source for anomaly detection. However, engine measurement and rocket flight state information have different data distribution characteristics. To find the optimal data fusion scheme for anomaly detection, a data set information fusion algorithm based on convex optimization is proposed, which solves the optimal fusion parameter using the convex quadratic programming problem and then adopts the adaptive CUSUM algorithm to realize the fast and accurate anomaly detection of engine faults. Numerical simulation tests show that the algorithm proposed in this paper has a higher detection accuracy and lower detection time than the traditional algorithm.

An Exploration into the Fault Diagnosis of Analog Circuits Using Enhanced Golden Eagle Optimized 1D-Convolutional Neural Network (CNN) with a Time-Frequency Domain Input and Attention Mechanism

With the continuous operation of analog circuits, the component degradation problem gradually comes to the forefront, which may lead to problems, such as circuit performance degradation, system stability reductions, and signal quality degradation, which could be particularly evident in increasingly complex electronic systems. At the same time, due to factors, such as continuous signal transformation, the fluctuation of component parameters, and the nonlinear characteristics of components, traditional fault localization methods are still facing significant challenges when dealing with large-scale complex circuit faults. Based on this, this paper proposes a fault-diagnosis method for analog circuits using the ECWGEO algorithm, an enhanced version of the GEO algorithm, to de-optimize the 1D-CNN with an attention mechanism to handle time-frequency fusion inputs. Firstly, a typical circuit-quad op-amp dual second-order filter circuit is selected to construct a fault-simulation model, and Monte Carlo analysis is used to obtain a large number of samples as the dataset of this study. Secondly, the 1D-CNN network structure is improved for the characteristics of the analog circuits themselves, and the time-frequency domain fusion input is implemented before inputting it into the network, while the attention mechanism is introduced into the network. Thirdly, instead of relying on traditional experience for network structure determination, this paper adopts a parameter-optimization algorithm for network structure optimization and improves the GEO algorithm according to the problem characteristics, which enhances the diversity of populations in the late stage of its search and accelerates the convergence speed. Finally, experiments are designed to compare the results in different dimensions, and the final proposed structure achieved a 98.93% classification accuracy, which is better than other methods.

A Fault Diagnosis Method for 5G Cellular Networks Based on Knowledge and Data Fusion

As 5G networks become more complex and heterogeneous, the difficulty of network operation and maintenance forces mobile operators to find new strategies to stay competitive. However, most existing network fault diagnosis methods rely on manual testing and time stacking, which suffer from long optimization cycles and high resource consumption. Therefore, we herein propose a knowledge- and data-fusion-based fault diagnosis algorithm for 5G cellular networks from the perspective of big data and artificial intelligence. The algorithm uses a generative adversarial network (GAN) to expand the data set collected from real network scenarios to balance the number of samples under different network fault categories. In the process of fault diagnosis, a naive Bayesian model (NBM) combined with domain expert knowledge is firstly used to pre-diagnose the expanded data set and generate a topological association graph between the data with solid engineering significance and interpretability. Then, as the pre-diagnostic prior knowledge, the topological association graph is fed into the graph convolutional neural network (GCN) model simultaneously with the training data set for model training. We use a data set collected by Minimization of Drive Tests under real network scenarios in Lu'an City, Anhui Province, in August 2019. The simulation results demonstrate that the algorithm outperforms other traditional models in fault detection and diagnosis tasks, achieving an accuracy of 90.56% and a macro F1 score of 88.41%.

Interpretable fusion methodology of health indices with an application to industrial turbine cavitation condition monitoring

Using health indices (HIs) to characterize machine conditions is greatly helpful to prevent machine failures and their subsequent catastrophe. Fusion and interpretation of the main contributions of HIs to machine condition monitoring are still challenging. In this paper, an interpretable fusion methodology of HIs is proposed for machine condition monitoring. The proposed methodology begins with elements of statistical learning for classification, following by an essence of how HIs are fused with their associated linear weights to realize machine condition monitoring. One main contribution of this paper gives a theoretical justification for positive and negative weights of the proposed fusion methodology for understanding their importance for machine condition monitoring and making the proposed methodology physically interpretable. In order to be suitable for two practical situations, in which whether faulty data are available or not, two solutions including an offline solution with healthy and faulty datasets and an online solution with only available healthy datasets are suggested to estimate interpretable weights of the proposed methodology. Finally, industrial turbine cavitation status data collected from our group are used to verify the proposed methodology and show its superiority to two existing popular machine fault diagnosis methods. This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 2)'.

Real-Time Fault Diagnosis for Hydraulic System Based on Multi-Sensor Convolutional Neural Network

This paper proposed a real-time fault diagnostic method for hydraulic systems using data collected from multiple sensors. The method is based on a proposed multi-sensor convolutional neural network (MS-CNN) that incorporates feature extraction, sensor selection, and fault diagnosis into an end-to-end model. Both the sensor selection process and fault diagnosis process are based on abstract fault-related features learned by a CNN deep learning model. Therefore, compared with the traditional sensor-and-feature selection method, the proposed MS-CNN can find the sensor channels containing higher-level fault-related features, which provides two advantages for diagnosis. First, the sensor selection can reduce the redundant information and improve the diagnostic performance of the model. Secondly, the reduced number of sensors simplifies the model, reducing communication burden and computational complexity. These two advantages make the MS-CNN suitable for real-time hydraulic system fault diagnosis, in which the multi-sensor feature extraction and the computation speed are both significant. The proposed MS-CNN approach is evaluated experimentally on an electric-hydraulic subsea control system test rig and an open-source dataset. The proposed method shows obvious superiority in terms of both diagnosis accuracy and computational speed when compared with traditional CNN models and other state-of-the-art multi-sensor diagnostic methods.

Conditional Enhanced Variational Autoencoder-Heterogeneous Graph Attention Neural Network: A Novel Fault Diagnosis Method for Electric Rudders Based on Heterogeneous Information

In machine fault diagnosis, despite the wealth of information multi-sensor data provide for constructing high-quality graphs, existing graph data-driven diagnostic methods face challenges posed by handling these heterogeneous multi-sensor data. To address this issue, we propose CEVAE-HGANN, an innovative model for fault diagnosis based on the electric rudder, which can process heterogeneous data efficiently. Initially, we facilitate interaction between conditional information and the original features, followed by dimensional reduction via a conditional enhanced variational autoencoder, thereby achieving a more robust state representation. Subsequently, we define two meta-paths and employ both the Euclidean distance and Pearson coefficient in crafting an effective adjacency matrix to delineate the relationships among edges within the graph, thereby effectively representing the complex interrelations among these subsystems. Ultimately, we incorporate heterogeneous graph attention neural networks for classification, which emphasizes the connections among different subsystems, moving beyond the reliance on node-level fault identification and effectively capturing the complex interactions between subsystems. The experimental outcomes substantiate the superiority of the electric rudder-based CEVAE-HGANN model fault diagnosis.

Fault Diagnosis of Rotating Machinery Using an Optimal Blind Deconvolution Method and Hybrid Invertible Neural Network

This paper proposes a novel approach to predicting the useful life of rotating machinery and making fault diagnoses using an optimal blind deconvolution and hybrid invertible neural network. First, a new optimal adaptive maximum second-order cyclostationarity blind deconvolution (OACYCBD) is developed for denoising vibration signals obtained from rotating machinery. This technique is obtained from the optimization of traditional adaptive maximum second-order cyclostationarity blind deconvolution (ACYCBD). To optimize the weights of conventional ACYCBD, the proposed method utilizes a probability density function (PDF) of Monte Carlo to assess fault-related incipient changes in the vibration signal. Cross-entropy is used as a convergence criterion for denoising. Because the denoised signal carries information related to the health of the rotating machinery, a novel health index is calculated in the second step using the peak value and square of the arithmetic mean of the signal. The novel health index can change according to the degradation of the health state of the rotating bearing. To predict the remaining useful life of the bearing in the final step, the health index is used as input for a newly developed hybrid invertible neural network (HINN), which combines an invertible neural network and long short-term memory (LSTM) to forecast trends in bearing degradation. The proposed approach outperforms SVM, CNN, and LSTM methods in predicting the remaining useful life of bearings, showcasing RMSE values of 0.799, 0.593, 0.53, and 0.485, respectively, when applied to a real-world industrial bearing dataset.

Adaptive Convolution Sparse Filtering Method for the Fault Diagnosis of an Engine Timing Gearbox

Due to the superior robustness of outlier signals and the unique advantage of not relying on a priori knowledge, Convolution Sparse Filtering (CSF) is drawing more and more attention. However, the excellent properties of CSF is limited by its inappropriate selection of the number and length of its filters. Therefore, the Adaptive Convolution Sparse Filtering (ACSF) method is proposed in this paper to implement an end-to-end health monitoring and fault diagnostic model. Firstly, a novel metric entropy-time function (He-T) is proposed to measure the accuracy and efficiency of signals filtered by the CSF. Then, the filtered signal with the minimum He-T is detected with particle swarm optimization. Finally, the failure mode is diagnosed according to the envelope spectrum of the signal with minimum He-T. The effectiveness and efficiency of the ACSF is demonstrated through the experiment. The results indicate the ACSF can extract the failure characteristic of the gearbox.

Few-Shot Fault Diagnosis Based on an Attention-Weighted Relation Network

As energy conversion systems continue to grow in complexity, pneumatic control valves may exhibit unexpected anomalies or trigger system shutdowns, leading to a decrease in system reliability. Consequently, the analysis of time-domain signals and the utilization of artificial intelligence, including deep learning methods, have emerged as pivotal approaches for addressing these challenges. Although deep learning is widely used for pneumatic valve fault diagnosis, the success of most deep learning methods depends on a large amount of labeled training data, which is often difficult to obtain. To address this problem, a novel fault diagnosis method based on the attention-weighted relation network (AWRN) is proposed to achieve fault detection and classification with small sample data. In the proposed method, fault diagnosis is performed through the relation network in few-shot learning, and in order to enhance the representativeness of feature extraction, the attention-weighted mechanism is introduced into the relation network. Finally, in order to verify the effectiveness of the method, a DA valve fault dataset is constructed, and experimental validation is performed on this dataset and another benchmark PU rolling bearing fault dataset. The results show that the accuracy of the network on DA is 99.15%, and the average accuracy on PU is 98.37%. Compared with the state-of-the-art diagnosis methods, the proposed method achieves higher accuracy while significantly reducing the amount of training data.

Real-Time Monitoring of Air Discharge in a Switchgear by an Intelligent NO2 Sensor Module

An air-insulated power equipment adopts air as the insulating medium and is widely implemented in power systems. When discharge faults occur, the air produces decomposition products represented by NO2. The efficient NO2 sensor enables the identification of electrical equipment faults. However, single-sensor-dependent NO2 detection is vulnerable to interfering gases. Implementing the sensor array could reduce the interference and improve detection efficiency. In the field of NO2 detection, In2O3 sensors have exhibited tremendous advantages. In our work, four composites based on In2O3 are integrated into sensor arrays, which could detect 250 ppb of NO2 and exhibit excellent selectivity when simultaneously exposed to CO. To further reduce the impact of humidity on gas-sensing performance, a convolutional neural network and a long short-term memory model equipped with an attention mechanism are proposed to evaluate NO2 concentration within 1 ppm, and the detection error is 63.69 ppb. In addition, the NO2 concentration estimation platform based on a microgas sensor is established to detect air discharge faults. The average concentration of NO2 generated by 10 consecutive discharge faults at 15 kV is 726.58 ppb, which indicates severe discharge in the switchgear. Our NO2 estimation method has great potential for large-scale deployment in low- and medium-voltage switchgears.

Graph Multi-Scale Permutation Entropy for Bearing Fault Diagnosis

Bearing faults are one kind of primary failure in rotatory machines. To avoid economic loss and casualties, it is important to diagnose bearing faults accurately. Vibration-based monitoring technology is widely used to detect bearing faults. Graph signal processing methods promising for the extraction of the fault features of bearings. In this work, graph multi-scale permutation entropy (MPEG) is proposed for bearing fault diagnosis. In the proposed method, the vibration signal is first transformed into a visibility graph. Secondly, a graph coarsening method is used to generate coarse graphs with different reduced sizes. Thirdly, the graph's permutation entropy is calculated to obtain bearing fault features. Finally, a support vector machine (SVM) is applied for fault feature classification. To verify the effectiveness of the proposed method, open-source and laboratory data are used to compare conventional entropies and other graph entropies. Experimental results show that the proposed method has higher accuracy and better robustness and de-noising ability.

Bio-Inspired Fault Diagnosis for Aircraft Fuel Pumps Using a Cloud-Edge System

The fuel pump serves as the central component of the aircraft fuel system, necessitating real-time data acquisition for monitoring purposes. As the number of sensors increases, there is a substantial rise in data volume, leading to a simultaneous increase in computational processing for traditional Prognostics and Health Management methods while computational efficiency decreases. In response to this challenge, a novel health monitoring approach for aircraft fuel pumps is proposed based on the collaborative utilization of cloud-edge resources. This approach enables efficient cooperation among the sensor side, edge side, and cloud side to achieve timely fault warnings and accurate fault classification for fuel pumps. Within this method, anomaly judgment tasks are allocated to the edge side, and an anomaly judgment method that integrates the 3σ threshold and "3/5 strategy" is devised. Additionally, a fault diagnosis algorithm, founded on a convolutional auto-encoder, is formulated in the cloud to discern various fault types and severities. Comparative results demonstrate that, in contrast to long short-term memory networks, convolutional neural networks, extreme learning machines, and support vector machines, the proposed method yields improvements in accuracy of 4.35%, 6.40%, 17.65%, and 19.35%, respectively. Consequently, it is evident that the proposed method exhibits notable efficacy in the condition monitoring of aircraft fuel pumps.

Fault Diagnosis Method for Human Coexistence Robots Based on Convolutional Neural Networks Using Time-Series Data Generation and Image Encoding

This paper proposes fault diagnosis methods aimed at proactively preventing potential safety issues in robot systems, particularly human coexistence robots (HCRs) used in industrial environments. The data were collected from durability tests of the driving module for HCRs, gathering time-series vibration data until the module failed. In this study, to apply classification methods in the absence of post-failure data, the initial 50% of the collected data were designated as the normal section, and the data from the 10 h immediately preceding the failure were selected as the fault section. To generate additional data for the limited fault dataset, the Wasserstein generative adversarial networks with gradient penalty (WGAN-GP) model was utilized and residual connections were added to the generator to maintain the basic structure while preventing the loss of key features of the data. Considering that the performance of image encoding techniques varies depending on the dataset type, this study applied and compared five image encoding methods and four CNN models to facilitate the selection of the most suitable algorithm. The time-series data were converted into image data using image encoding techniques including recurrence plot, Gramian angular field, Markov transition field, spectrogram, and scalogram. These images were then applied to CNN models, including VGGNet, GoogleNet, ResNet, and DenseNet, to calculate the accuracy of fault diagnosis and compare the performance of each model. The experimental results demonstrated significant improvements in diagnostic accuracy when employing the WGAN-GP model to generate fault data, and among the image encoding techniques and convolutional neural network models, spectrogram and DenseNet exhibited superior performance, respectively.

Research on Rotating Machinery Fault Diagnosis Based on an Improved Eulerian Video Motion Magnification

Rotating machinery condition monitoring and fault diagnosis are important bases for maintenance decisions, as the vibrations generated during operation are usually imperceptible to the naked eye. Eulerian video motion magnification (EVMM) can reveal subtle changes and has been widely used in various fields such as medicine, structural analysis, and fault diagnosis, etc. However, the method has a bound relationship among three parameters: spatial wavelength, amplification factor, and displacement function, so it is necessary to adjust the parameters manually in practical applications. In this paper, on the basis of the original method, an automatic solution of spatial cutoff wavelength based on brightness is proposed. First, an input video is decomposed into image sequences, their RGB color spaces are transformed into HSV color spaces, and the Value channel image representing brightness is selected to automatically calculate the spatial cutoff frequency, and then the spatial cutoff wavelength is determined, and the motion magnification video in the specified frequency band is obtained by substituting it into the original method. Then, a publicly available video is taken as an example for simulation analysis. By comparing the time-brightness curves of the three videos (original video, motion magnification video obtained by the original method and the improved method), it is apparent that the proposed method exhibits the most significant brightness variation. Finally, taking an overhung rotor-bearing test device as the object, five conditions are set, respectively: normal, rotor unbalance, loosened anchor bolt of the bearing seat, compound fault, rotor misalignment. The proposed method is adopted to magnify the motion of the characteristic frequency bands including 1X frequency and 2X frequency. The results show that no obvious displacement is found in normal working conditions, and that the rotor unbalance fault has an overall axial shaking, the bearing seat at the loose place has an obvious vertical displacement, while the compound fault combines the both fault characteristics, and the rotor misalignment fault has an obvious axial displacement of the free-end bearing seat. The method proposed in this paper can automatically obtain the space cutoff wavelength, which solves the problem of defects arising from manually adjusting the parameters in the original method, and provides a new method for rotating machinery fault diagnosis and other fields of application.

Fault Diagnosis of Rotating Machinery Using Kernel Neighborhood Preserving Embedding and a Modified Sparse Bayesian Classification Model

Fault diagnosis of rotating machinery plays an important role in modern industrial machines. In this paper, a modified sparse Bayesian classification model (i.e., Standard_SBC) is utilized to construct the fault diagnosis system of rotating machinery. The features are extracted and adopted as the input of the SBC-based fault diagnosis system, and the kernel neighborhood preserving embedding (KNPE) is proposed to fuse the features. The effectiveness of the fault diagnosis system of rotating machinery based on KNPE and Standard_SBC is validated by utilizing two case studies: rolling bearing fault diagnosis and rotating shaft fault diagnosis. Experimental results show that base on the proposed KNPE, the feature fusion method shows superior performance. The accuracy of case1 and case2 is improved from 93.96% to 99.92% and 98.67% to 99.64%, respectively. To further prove the superiority of the KNPE feature fusion method, the kernel principal component analysis (KPCA) and relevance vector machine (RVM) are utilized, respectively. This study lays the foundation for the feature fusion and fault diagnosis of rotating machinery.

On Model-Based Transfer Learning Method for the Detection of Inter-Turn Short Circuit Faults in PMSM

The early detection of an inter-turn short circuit (ITSC) fault is extremely critical for permanent magnet synchronous motors (PMSMs) because it can lead to catastrophic consequences. In this study, a model-based transfer learning method is developed for ITSC fault detection. The contribution can be summarized as two points. First of all, a Bayesian-optimized residual dilated CNN model was proposed for the pre-training of the method. The dilated convolution is utilized to extend the receptive domain of the model, the residual architecture is employed to surmount the degradation problems, and the Bayesian optimization method is launched to address the hyperparameters tuning issues. Secondly, a transfer learning framework and strategy are presented to settle the new target domain datasets after the pre-training of the proposed model. Furthermore, motor fault experiments are carried out to validate the effectiveness of the proposed method. Comparison with seven other methods indicates the performance and advantage of the proposed method.

A Fault Diagnosis Strategy for Analog Circuits with Limited Samples Based on the Combination of the Transformer and Generative Models

As a pivotal integral component within electronic systems, analog circuits are of paramount importance for the timely detection and precise diagnosis of their faults. However, the objective reality of limited fault samples in operational devices with analog circuitry poses challenges to the direct applicability of existing diagnostic methods. This study proposes an innovative approach for fault diagnosis in analog circuits by integrating deep convolutional generative adversarial networks (DCGANs) with the Transformer architecture, addressing the problem of insufficient fault samples affecting diagnostic performance. Firstly, the employment of the continuous wavelet transform in combination with Morlet wavelet basis functions serves as a means to derive time-frequency images, enhancing fault feature recognition while converting time-domain signals into time-frequency representations. Furthermore, the augmentation of datasets utilizing deep convolutional GANs is employed to generate synthetic time-frequency signals from existing fault data. The Transformer-based fault diagnosis model was trained using a mixture of original signals and generated signals, and the model was subsequently tested. Through experiments involving single and multiple fault scenarios in three simulated circuits, a comparative analysis of the proposed approach was conducted with a number of established benchmark methods, and its effectiveness in various scenarios was evaluated. In addition, the ability of the proposed fault diagnosis technique was investigated in the presence of limited fault data samples. The outcome reveals that the proposed diagnostic method exhibits a consistently high overall accuracy of over 96% in diverse test scenarios. Moreover, it delivers satisfactory performance even when real sample sizes are as small as 150 instances in various fault categories.

Digital Twin-Based Fault Diagnosis Platform for Final Rolling Temperature in Hot Strip Production

The final rolling temperature in hot rolling is an important process parameter for hot-rolled strips and greatly influences their mechanical properties and rolling stability. The diagnosis of final rolling temperature anomalies in hot rolling has always been difficult in industry. A data-driven risk assessment method for detecting final rolling temperature anomalies is proposed. In view of the abnormal setting value for the strip head, a random forest model is established to screen the process parameters with high feature importance, and the isolation forest algorithm is used to evaluate the risk associated with the remaining parameters. In view of the abnormal process curve of the full length of the strip, the Hausdorff distance algorithm is used to eliminate samples with large deviations, and a risk assessment of the curve is carried out using the LCSS algorithm. Aiming to understand the complex coupling relationship between the influencing factors, a method for identifying the causes of anomalies, combining a knowledge graph and a Bayesian network, is established. According to the results of the strip head and the full-length risk assessment model, the occurrence of the corresponding nodes in the Bayesian network is determined, and the root cause of the abnormality is finally output. By combining mechanistic modeling and data modeling techniques, it becomes possible to rapidly, automatically, and accurately detect and analyze final rolling temperature anomalies during the rolling process. When applying the system in the field, when compared to manual analysis by onsite personnel, the accuracy of deducing the causes of anomalies was found to reach 92%.

An Intelligent Framework for Fault Diagnosis of Centrifugal Pump Leveraging Wavelet Coherence Analysis and Deep Learning

This paper proposes an intelligent framework for the fault diagnosis of centrifugal pumps (CPs) based on wavelet coherence analysis (WCA) and deep learning (DL). The fault-related impulses in the CP vibration signal are often attenuated due to the background interference noises, thus affecting the sensitivity of the traditional statistical features towards faults. Furthermore, extracting health-sensitive information from the vibration signal needs human expertise and background knowledge. To extract CP health-sensitive features autonomously from the vibration signals, the proposed approach initially selects a healthy baseline signal. The wavelet coherence analysis is then computed between the healthy baseline signal and the signal obtained from a CP under different operating conditions, yielding coherograms. WCA is a signal processing technique that is used to measure the degree of linear correlation between two signals as a function of frequency. The coherograms carry information about the CP vulnerability towards the faults as the color intensity in the coherograms changes according to the change in CP health conditions. To utilize the changes in the coherograms due to the health conditions of the CP, they are provided to a Convolution Neural Network (CNN) and a Convolution Autoencoder (CAE) for the extraction of discriminant CP health-sensitive information autonomously. The CAE extracts global variations from the coherograms, and the CNN extracts local variations related to CP health. This information is combined into a single latent space vector. To identify the health conditions of the CP, the latent space vector is classified using an Artificial Neural Network (ANN). The proposed method identifies faults in the CP with higher accuracy as compared to already existing methods when it is tested on the vibration signals acquired from real-world industrial CPs.

A Novel Intelligent Fault Diagnosis Method for Self-Priming Centrifugal Pumps

The real-time diagnostic monitoring of self-priming centrifugal pumps is essential to ensure their safe operation. Nevertheless, owing to the intricate structure and complex operational conditions inherent in such pumps, existing fault diagnosis methods encounter challenges in effectively extracting crucial fault feature information and accurately identifying fault types. Consequently, this paper introduces an intelligent fault diagnosis method tailored for self-priming centrifugal pumps. The approach amalgamates refined time-shift multiscale fluctuation dispersion entropy, cosine pairwise-constrained supervised manifold mapping, and adaptive chaotic Aquila optimization support vector machine techniques. To begin with, refined time-shift multiscale fluctuation dispersion entropy is employed to extract fault-related features, adeptly mitigating concerns related to entropy domain deviations and instability. Subsequently, the application of cosine pairwise-constrained supervised manifold mapping serves to reduce the dimensionality of the extracted fault features, thereby bolstering the efficiency and precision of the ensuing identification process. Ultimately, the utilization of an adaptive chaotic Aquila optimization support vector machine facilitates intelligent fault classification, leading to enhanced accuracy in fault identification. The experimental findings unequivocally affirm the efficacy of the proposed method in accurately discerning among various fault types in self-priming centrifugal pumps, achieving an exceptional recognition rate of 100%. Moreover, it is noteworthy that the average correct recognition rate achieved by the proposed method surpasses that of five existing intelligent fault diagnosis techniques by a significant margin, registering a notable increase of 15.97%.

Enhanced Feature Extraction Network Based on Acoustic Signal Feature Learning for Bearing Fault Diagnosis

The method of acoustic radiation signal detection not only enables contactless measurement but also provides comprehensive state information during equipment operation. This paper proposes an enhanced feature extraction network (EFEN) for fault diagnosis of rolling bearings based on acoustic signal feature learning. The EFEN network comprises four main components: the data preprocessing module, the information feature selection module (IFSM), the channel attention mechanism module (CAMM), and the convolutional neural network module (CNNM). Firstly, the one-dimensional acoustic signal is transformed into a two-dimensional grayscale image. Then, IFSM utilizes three different-sized convolution filters to process input image data and fuse and assign weights to feature information that can attenuate noise while highlighting effective fault information. Next, a channel attention mechanism module is introduced to assign weights to each channel. Finally, the convolutional neural network (CNN) fault diagnosis module is employed for accurate classification of rolling bearing faults. Experimental results demonstrate that the EFEN network achieves high accuracy in fault diagnosis and effectively detects rolling bearing faults based on acoustic signals. The proposed method achieves an accuracy of 98.52%, surpassing other methods in terms of performance. In comparative analysis of antinoise experiments, the average accuracy remains remarkably high at 96.62%, accompanied by a significantly reduced average iteration time of only 0.25 s. Furthermore, comparative analysis confirms that the proposed algorithm exhibits excellent accuracy and resistance against noise.

Dynamic Semi-Supervised Federated Learning Fault Diagnosis Method Based on an Attention Mechanism

In cases where a client suffers from completely unlabeled data, unsupervised learning has difficulty achieving an accurate fault diagnosis. Semi-supervised federated learning with the ability for interaction between a labeled client and an unlabeled client has been developed to overcome this difficulty. However, the existing semi-supervised federated learning methods may lead to a negative transfer problem since they fail to filter out unreliable model information from the unlabeled client. Therefore, in this study, a dynamic semi-supervised federated learning fault diagnosis method with an attention mechanism (SSFL-ATT) is proposed to prevent the federation model from experiencing negative transfer. A federation strategy driven by an attention mechanism was designed to filter out the unreliable information hidden in the local model. SSFL-ATT can ensure the federation model's performance as well as render the unlabeled client capable of fault classification. In cases where there is an unlabeled client, compared to the existing semi-supervised federated learning methods, SSFL-ATT can achieve increments of 9.06% and 12.53% in fault diagnosis accuracy when datasets provided by Case Western Reserve University and Shanghai Maritime University, respectively, are used for verification.

Fault Diagnosis of PMSMs Based on Image Features of Multi-Sensor Fusion

Permanent magnet synchronous motors (PMSMs) are extensively utilized in production and manufacturing fields due to their wide speed range, high output torque, fast speed response, small size and light weight. PMSMs are susceptible to inter-turn short circuit faults, demagnetization faults, bearing faults, and other faults arising from irregular vibrations and frequent start-brake cycles. While fault diagnosis for PMSMs offers an effective means to enhance operational efficiency, the multi-sensor information fusion is often overlooked. In industrial production processes, the collected data inevitably suffers from noise contamination, which can adversely impact diagnostic outcomes. To enhance the robustness of diagnostic methods in noisy environments and mitigate the risk of overfitting, a PMSM fault diagnosis method based on image features of multi-sensor fusion is proposed. Firstly, the vibration acceleration signals of the PMSM at different positions were acquired. Then, the newly designed multi-signal Gramian Angular Difference Fields (MGADF) method combines sensor signals from three different installation locations into a single image. Next, the multi-texture features are fused to extract the features of the image. Various machine models are compared in the fault feature learning and classification, and the results show that the proposed diagnostic method has good diagnostic accuracy and robustness, with an average diagnostic accuracy of 99.54% and a standard deviation of accuracy of 0.19. It has excellent performance even in noisy environments. The method is non-invasive and can be extended and applied to the condition monitoring and diagnosis of industrial motors.

Spatial Domain Image Fusion with Particle Swarm Optimization and Lightweight AlexNet for Robotic Fish Sensor Fault Diagnosis

Safety and reliability are vital for robotic fish, which can be improved through fault diagnosis. In this study, a method for diagnosing sensor faults is proposed, which involves using Gramian angular field fusion with particle swarm optimization and lightweight AlexNet. Initially, one-dimensional time series sensor signals are converted into two-dimensional images using the Gramian angular field method with sliding window augmentation. Next, weighted fusion methods are employed to combine Gramian angular summation field images and Gramian angular difference field images, allowing for the full utilization of image information. Subsequently, a lightweight AlexNet is developed to extract features and classify fused images for fault diagnosis with fewer parameters and a shorter running time. To improve diagnosis accuracy, the particle swarm optimization algorithm is used to optimize the weighted fusion coefficient. The results indicate that the proposed method achieves a fault diagnosis accuracy of 99.72% when the weighted fusion coefficient is 0.276. These findings demonstrate the effectiveness of the proposed method for diagnosing depth sensor faults in robotic fish.

Early Fault Detection of Rolling Bearings Based on Time-Varying Filtering Empirical Mode Decomposition and Adaptive Multipoint Optimal Minimum Entropy Deconvolution Adjusted

Due to the early formation of rolling bearing fault characteristics in an environment with strong background noise, the single use of the time-varying filtering empirical mode decomposition (TVFEMD) method is not effective for the extraction of fault characteristics. To solve this problem, a new method for early fault detection of rolling bearings is proposed, which combines multipoint optimal minimum entropy deconvolution adjusted (MOMEDA) with parameter optimization and TVFEMD. Firstly, a new weighted envelope spectrum kurtosis index is constructed using the correlation coefficient and envelope spectrum kurtosis, which is used to identify the effective component and noise component of the bearing fault signal decomposed by TVFEMD, and the intrinsic mode function (IMF) containing rich fault information is selected for reconstruction. Then, a new synthetic impact index (SII) is constructed by combining the maximum value of the autocorrelation function and the kurtosis of the envelope spectrum. The SII index is used as the fitness function of the gray wolf optimization algorithm to optimize the fault period, T, and the filter length, L, of MOMDEA. The signal reconstructed by TVF-EMD undergoes adaptive filtering using the MOMEDA method after parameter optimization. Finally, an envelope spectrum analysis is performed on the signal filtered by the adaptive MOMEDA method to extract fault feature information. The experimental results of the simulated and measured signals indicate that this method can effectively extract early fault features of rolling bearings and has good reliability. Compared to the classical FSK, MCKD, and TVFEMD-MOMEDA methods, the first-order correlated kurtosis (FCK) and fault feature coefficient (FFC) of the filtered signal obtained using the proposed method are the largest, while the sample entropy (SE) and envelope spectrum entropy (ESE) are the smallest.

Research on Three-Phase Asynchronous Motor Fault Diagnosis Based on Multiscale Weibull Dispersion Entropy

Three-phase asynchronous motors have a wide range of applications in the machinery industry and fault diagnosis aids in the healthy operation of a motor. In order to improve the accuracy and generalization of fault diagnosis in three-phase asynchronous motors, this paper proposes a three-phase asynchronous motor fault diagnosis method based on the combination of multiscale Weibull dispersive entropy (WB-MDE) and particle swarm optimization-support vector machine (PSO-SVM). Firstly, the Weibull distribution (WB) is used to linearize and smooth the vibration signals to obtain sharper information about the motor state. Secondly, the quantitative features of the regularity and orderliness of a given sequence are extracted using multiscale dispersion entropy (MDE). Then, a support vector machine (SVM) is used to construct a classifier, the parameters are optimized via the particle swarm optimization (PSO) algorithm, and the extracted feature vectors are fed into the optimized SVM model for classification and recognition. Finally, the accuracy and generalization of the model proposed in this paper are tested by adding raw data with Gaussian white noise with different signal-to-noise ratios and the CHIST-ERA SOON public dataset. This paper builds a three-phase asynchronous motor vibration signal experimental platform, through a piezoelectric acceleration sensor to discern the four states of the motor data, to verify the effectiveness of the proposed method. The accuracy of the collected data using the WB-MDE method proposed in this paper for feature extraction and the extracted features using the optimization of the PSO-SVM method for fault classification and identification is 100%. Additionally, the proposed model is tested for noise resistance and generalization. Finally, the superiority of the present method is verified through experiments as well as noise immunity and generalization tests.

Enhanced Fault Type Detection in Covered Conductors Using a Stacked Ensemble and Novel Algorithm Combination

This study introduces an innovative approach to enhance fault detection in XLPE-covered conductors used for power distribution systems. These covered conductors are widely utilized in forested areas (natural parks) to decrease the buffer zone and increase the reliability of the distribution network. Recognizing the imperative need for precise fault detection in this context, this research employs an antenna-based method to detect a particular type of fault. The present research contains the classification of fault type detection, which was previously accomplished using a very expensive and challenging-to-install galvanic contact method, and only to a limited extent, which did not provide information about the fault type. Additionally, differentiating between types of faults in the contact method is much easier because information for each phase is available. The proposed method uses antennas and a classifier to effectively differentiate between fault types, ranging from single-phase to three-phase faults, as well as among different types of faults. This has never been done before. To bolster the accuracy, a stacking ensemble method involving the logistic regression is implemented. This approach not only advances precise fault detection but also encourages the broader adoption of covered conductors. This promises benefits such as a reduced buffer zone, improved distribution network reliability, and positive environmental outcomes through accident prevention and safe covered conductor utilization. Additionally, it is suggested that the fault type detection could lead to a decrease in false positives.

Fault Diagnosis of Medium Voltage Circuit Breakers Based on Vibration Signal Envelope Analysis

In modern power systems or new energy power stations, the medium voltage circuit breakers (MVCBs) are becoming more crucial and the operation reliability of the MVCBs could be greatly improved by online monitoring technology. The purpose of this research is to put forward a fault diagnosis approach based on vibration signal envelope analysis, including offline fault feature training and online fault diagnosis. During offline fault feature training, the envelope of the vibration signal is extracted from the historic operation data of the MVCB, and then the typical fault feature vector M is built by using the wavelet packet-energy spectrum. In the online fault diagnosis process, the fault feature vector T is built based on the extracted envelope of the real-time vibration signal, and the MVCB states are assessed by using the distance between the feature vectors T and M. The proposed method only needs to handle the envelope of the vibration signal, which dramatically reduces the signal bandwidth, and then the cost of the processing hardware and software could be cut down.

Improved RAkEL's Fault Diagnosis Method for High-Speed Train Traction Transformer

The traction system is very important to ensure the safe operation of high-speed trains, and the failure of the traction transformer is the most likely fault in the traction system. Fault diagnosis in actual work relies largely on manual experience. This paper proposes an improved RAkEL (Random k-Labelsets) algorithm for the fault diagnosis of high-speed train traction transformers. Firstly, this article starts from the large amount of "sleeping" fault maintenance data accumulated by the railway department, takes a single maintenance record as an instance, uses specific monitoring values to construct an instance vector, and uses the fault phenomena corresponding to the monitoring indicators as labels. Then, this paper improves the step of selecting k-labelsets in RAkEL, and extracts associated faults using the Relief algorithm. Finally, this paper excavates and uses the association rules between data and faults to identify traction transformer faults. The results showed that the improved RAkEL diagnostic method had a significant improvement in the evaluation indicators. Compared with other multi-label classification algorithms, including BR (Binary Relevance) and CLR (Calibrated Label Ranking), this method performs well on multiple evaluation indicators. It can further help engineers perform timely maintenance work in the future.

A Novel Deep Convolutional Neural Network Combining Global Feature Extraction and Detailed Feature Extraction for Bearing Compound Fault Diagnosis

This study researched the application of a convolutional neural network (CNN) to a bearing compound fault diagnosis. The proposed idea lies in the ability of CNN to automatically extract fault features from complex raw signals. In our approach, to extract more effective features from a raw signal, a novel deep convolutional neural network combining global feature extraction with detailed feature extraction (GDDCNN) is proposed. First, wide and small kernel sizes are separately adopted in shallow and deep convolutional layers to extract global and detailed features. Then, the modified activation layer with a concatenated rectified linear unit (CReLU) is added following the shallow convolution layer to improve the utilization of shallow global features of the network. Finally, to acquire more robust features, another strategy involving the GMP layer is utilized, which replaces the traditional fully connected layer. The performance of the obtained diagnosis was validated on two bearing datasets. The results show that the accuracy of the compound fault diagnosis is over 98%. Compared with three other CNN-based methods, the proposed model demonstrates better stability.

Gas Sensor Array Fault Diagnosis Based on Multi-Dimensional Fusion, an Attention Mechanism, and Multi-Task Learning

With the development of gas sensor arrays and computational technology, machine olfactory systems have been widely used in environmental monitoring, medical diagnosis, and other fields. The reliable and stable operation of gas sensing systems depends heavily on the accuracy of the sensors outputs. Therefore, the realization of accurate gas sensor array fault diagnosis is essential to monitor the working status of sensor arrays and ensure the normal operation of the whole system. The existing methods extract features from a single dimension and require the separate training of models for multiple diagnosis tasks, which limits diagnostic accuracy and efficiency. To address these limitations, for this study, a novel fault diagnosis network based on multi-dimensional feature fusion, an attention mechanism, and multi-task learning, MAM-Net, was developed and applied to gas sensor arrays. First, feature fusion models were applied to extract deep and comprehensive features from the original data in multiple dimensions. A residual network equipped with convolutional block attention modules and a Bi-LSTM network were designed for two-dimensional and one-dimensional signals to capture spatial and temporal features simultaneously. Subsequently, a concatenation layer was constructed using feature stitching to integrate the fault details of different dimensions and avoid ignoring useful information. Finally, a multi-task learning module was designed for the parallel learning of the sensor fault diagnosis to effectively improve the diagnosis capability. The experimental results derived from using the proposed framework on gas sensor datasets across different amounts of data, balanced and unbalanced datasets, and different experimental settings show that the proposed framework outperforms the other available methods and demonstrates good recognition accuracy and robustness.

A Sensor-Fault-Estimation Method for Lithium-Ion Batteries in Electric Vehicles

In recent years, electric vehicles powered by lithium-ion batteries have developed rapidly, and the safety and reliability of lithium-ion batteries have been a paramount issue. Battery management systems are highly dependent on sensor measurements to ensure the proper functioning of lithium-ion batteries. Therefore, it is imperative to develop a suitable fault diagnosis scheme for battery sensors, to realize a diagnosis at an early stage. The main objective of this paper is to establish validated electrical and thermal models for batteries, and address a model-based fault diagnosis scheme for battery sensors. Descriptor proportional and derivate observer systems are applied for sensor diagnosis, based on electrical and thermal models of lithium-ion batteries, which can realize the real-time estimation of voltage sensor fault, current sensor fault, and temperature sensor fault. To verify the estimation effect of the proposed scheme, various types of faults are utilized for simulation experiments. Battery experimental data are used for battery modeling and observer-based fault diagnosis in battery sensors.

Corn Harvester Bearing Fault Diagnosis Based on ABC-VMD and Optimized EfficientNet

The extraction of the optimal mode of the bearing signal in the drive system of a corn harvester is a challenging task. In addition, the accuracy and robustness of the fault diagnosis model are low. Therefore, this paper proposes a fault diagnosis method that uses the optimal mode component as the input feature. The vibration signal is first decomposed by variational mode decomposition (VMD) based on the optimal parameters searched by the artificial bee colony (ABC). Moreover, the key components are screened using an evaluation function that is a fusion of the arrangement entropy, the signal-to-noise ratio, and the power spectral density weighting. The Stockwell transform is then used to convert the filtered modal components into time-frequency images. Finally, the MBConv quantity and activation function of the EfficientNet network are optimized, and the time-frequency pictures are imported into the optimized network model for fault diagnosis. The comparative experiments show that the proposed method accurately extracts the optimal modal component and has a fault classification accuracy greater than 98%.