Supervised and Unsupervised Approaches for the Real-Time Detection of Undesired Insulin Suspension Caused by Malfunctions

BACKGROUND

Automated insulin delivery (AID) systems, permit improved treatment of type 1 diabetes (T1D). Unfortunately, malfunctioning in the insulin pump or in the infusion set can prevent insulin from being administered, reducing the AID efficacy and posing the patient at risk. Different data-driven methods available in the literature can be used to deal with the problem of automatically detecting complete insulin suspension in real-time. This article investigates both supervised and unsupervised strategies and proposes a fair comparison under either population or personalized settings.

METHODS

Several algorithms are compared using data generated through the UVA/Padova T1D simulator, a computer simulator widely used to test control strategies in silico and accepted by the Food and Drugs Administration (FDA) as a substitute to animal pre-clinical trials. Two synthetic data sets, each consisting of 100 virtual subjects monitored for 1 month, were generated. Occasional faults of the insulin pump are simulated as complete occlusions by suspending the therapy administration. Personalized algorithms are investigated with unsupervised approaches only, since personalized labels are hardly available.

RESULTS

In the population scenario, the supervised approach outperforms the unsupervised strategy. In particular, logistic regression and random forest achieves a recall of 72% and 82%, with 0.12 and 0.21 false positives (FP) per day, respectively. In the personalized setting scenario, the unsupervised algorithms are tailored on each patient and outperform the population ones, in particular isolation forest achieves a recall 80% and 0.06 FPs per day.

CONCLUSIONS

This article suggests that unsupervised personalized approach, by addressing the large variability in glucose response among individuals with T1D, is superior to other one-fits-all approaches in detecting insulin suspensions caused by malfunctioning. Population methodologies can be effectively used while waiting to collect sufficient patient data, when the system is installed on a new patient.

Resilient Event-Based Fuzzy Fault Detection for DC Microgrids in Finite-Frequency Domain against DoS Attacks

This paper addresses the problem of fault detection in DC microgrids in the presence of denial-of-service (DoS) attacks. To deal with the nonlinear term in DC microgrids, a Takagi-Sugeno (T-S) model is employed. In contrast to the conventional approach of utilizing current sampling data in the traditional event-triggered mechanism (ETM), a novel integrated ETM employs historical information from measured data. This innovative strategy mitigates the generation of additional triggering packets resulting from random perturbations, thus reducing redundant transmission data. Under the assumption of faults occurring within a finite-frequency domain, a resilient event-based H-/H∞ fault detection filter (FDF) is designed to withstand DoS attacks. The exponential stability conditions are derived in the form of linear matrix inequalities to ensure the performance of fault detected systems. Finally, the simulation results are presented, demonstrating that the designed FDF effectively detects finite-frequency faults in time even under DoS attacks. Furthermore, the FDF exhibits superior fault detection sensitivity compared to the conventional H∞ method, thus confirming the efficacy of the proposed approach. Additionally, it is observed that a trade-off exists between fault detection performance and the data releasing rate (DRR).

Industrial Fault Detection Employing Meta Ensemble Model Based on Contact Sensor Ultrasonic Signal

Ultrasonic diagnostics is the earliest way to predict industrial faults. Usually, a contact microphone is employed for detection, but the recording will be contaminated with noise. In this paper, a dataset that contains 10 main faults of pipelines and motors is analyzed from which 30 different features in the time and frequency domains are extracted. Afterward, for dimensionality reduction, principal component analysis (PCA), linear discriminant analysis (LDA), and t-distributed stochastic neighbor embedding (t-SNE) are performed. In the subsequent phase, recursive feature elimination (RFE) is employed as a strategic method to analyze and select the most relevant features for the classifiers. Next, predictive models consisting of k-Nearest Neighbor (KNN), Logistic Regression (LR), Decision Tree (DT), Gaussian Naive Bayes (GNB), and Support Vector Machine (SVM) are employed. Then, in order to solve the classification problem, a stacking classifier based on a meta-classifier which combines multiple classification models is introduced. Furthermore, the k-fold cross-validation technique is employed to assess the effectiveness of the model in handling new data for the evaluation of experimental results in ultrasonic fault detection. With the proposed method, the accuracy is around 5% higher over five cross folds with the least amount of variation. The timing evaluation of the meta model on the 64 MHz Cortex M4 microcontroller unit (MCU) revealed an execution time of 11 ms, indicating it could be a promising solution for real-time monitoring.

Research on Fault Detection by Flow Sequence for Industrial Internet of Things in Sewage Treatment Plant Case

Classifying the flow subsequences of sensor networks is an effective way for fault detection in the Industrial Internet of Things (IIoT). Traditional fault detection algorithms identify exceptions by a single abnormal dataset and do not pay attention to the factors such as electromagnetic interference, network delay, sensor sample delay, and so on. This paper focuses on fault detection by continuous abnormal points. We proposed a fault detection algorithm within the module of sequence state generated by unsupervised learning (SSGBUL) and the module of integrated encoding sequence classification (IESC). Firstly, we built a network module based on unsupervised learning to encode the flow sequence of the different network cards in the IIoT gateway, and then combined the multiple code sequences into one integrated sequence. Next, we classified the integrated sequence by comparing the integrated sequence with the encoding fault type. The results obtained from the three IIoT datasets of a sewage treatment plant show that the accuracy of the SSGBUL-IESC algorithm exceeds 90% with subsequence length 10, which is significantly higher than the accuracies of the dynamic time warping (DTW) algorithm and the time series forest (TSF) algorithm. The proposed algorithm reaches the classification requirements for fault detection for the IIoT.

Lightweight Transmission Line Fault Detection Method Based on Leaner YOLOv7-Tiny

Aiming to address the issues of parameter complexity and high computational load in existing fault detection algorithms for transmission lines, which hinder their deployment on devices like drones, this study proposes a novel lightweight model called Leaner YOLOv7-Tiny. The primary goal is to swiftly and accurately detect typical faults in transmission lines from aerial images. This algorithm inherits the ELAN structure from YOLOv7-Tiny network and replaces its backbone with depthwise separable convolutions to reduce model parameters. By integrating the SP attention mechanism, it fuses multi-scale information, capturing features across various scales to enhance small target recognition. Finally, an improved FCIoU Loss function is introduced to balance the contribution of high-quality and low-quality samples to the loss function, expediting model convergence and boosting detection accuracy. Experimental results demonstrate a 20% reduction in model size compared to the original YOLOv7-Tiny algorithm. Detection accuracy for small targets surpasses that of current mainstream lightweight object detection algorithms. This approach holds practical significance for transmission line fault detection.

Interacting Multiple Model Estimators for Fault Detection in a Magnetorheological Damper

This paper proposes a novel estimator for the purpose of fault detection and diagnosis. The interacting multiple model (IMM) strategy is effective for estimating the behaviour of systems with multiple operating modes. Each mode corresponds to a distinct mathematical model and is subject to a filtering process. This paper applies various model-based filters in combination with the IMM strategy. One such estimator employs the recently introduced extended sliding innovation filter (ESIF) known as the IMM-ESIF. The ESIF is an extension of the sliding innovation filter for nonlinear systems based on the sliding mode concept. In the presence of modeling uncertainties, the ESIF has been proven to be more robust compared to methods such as the extended Kalman filter (EKF). The novel IMM-ESIF strategy is also compared with the IMM strategy, which incorporates the unscented Kalman filter (UKF), referred to herein as IMM-UKF. While EKF uses Taylor series approximation to linearize the system model, the UKF uses sigma point to calculate the system's mean and covariance. The methods were applied to an experimental magnetorheological (MR) damper setup, which was designed for testing control and estimation theory. Magnetorheological dampers exhibit a diverse array of applications in the automotive and aerospace sectors, with particular relevance to attenuating vibrations through adaptive suspension systems. Applied to a magnetorheological (MR) damper with distinct operating modes determined by the damper's current, the results showcase the effectiveness of IMM-ESIF. In mixed operational conditions, IMM-ESIF demonstrates a notable 80% to 90% reduction in estimation error compared to its counterparts. Furthermore, it exhibits a 4% to 5% enhancement in correctly classifying operational modes, establishing IMM-ESIF as a promising and efficient alternative for adaptive estimation in electromechanical systems. The improved accuracy in estimating the system's behaviour, even amidst uncertainties and mixed operational scenarios, signifies the potential of IMM-ESIF to significantly enhance the overall robustness and efficiency of estimations.

Viability Under Degraded Control Authority

In this letter, we solve the problem of quantifying and mitigating control authority degradation in real time. Here, our target systems are controlled nonlinear affine-in-control evolution equations with finite control input and finite- or infinite-dimensional state. We consider two cases of control input degradation: finitely many affine maps acting on unknown disjoint subsets of the inputs and general Lipschitz continuous maps. These degradation modes are encountered in practice due to actuator wear and tear, hard locks on actuator ranges due to over-excitation, as well as more general changes in the control allocation dynamics. We derive sufficient conditions for identifiability of control authority degradation, and propose a novel real-time algorithm for identifying or approximating control degradation modes. We demonstrate our method on a nonlinear distributed parameter system, namely a one-dimensional heat equation with a velocity-controlled moveable heat source, motivated by autonomous energy-based surgery.

A Fault Detection Approach Based on One-Sided Domain Adaptation and Generative Adversarial Networks for Railway Door Systems

Fault detection using the domain adaptation technique is one of the more promising methods of solving the domain shift problem, and has therefore been intensively investigated in recent years. However, the domain adaptation method still has elements of impracticality: firstly, domain-specific decision boundaries are not taken into consideration, which often results in poor performance near the class boundary; and secondly, information on the source domain needs to be exploited with priority over information on the target domain, as the source domain can provide a rich dataset. Thus, the real-world implementations of this approach are still scarce. In order to address these issues, a novel fault detection approach based on one-sided domain adaptation for real-world railway door systems is proposed. An anomaly detector created using label-rich source domain data is used to generate distinctive source latent features, and the target domain features are then aligned toward the source latent features in a one-sided way. The performance and sensitivity analyses show that the proposed method is more accurate than alternative methods, with an F1 score of 97.9%, and is the most robust against variation in the input features. The proposed method also bridges the gap between theoretical domain adaptation research and tangible industrial applications. Furthermore, the proposed approach can be applied to conventional railway components and various electro-mechanical actuators. This is because the motor current signals used in this study are primarily obtained from the controller or motor drive, which eliminates the need for extra sensors.

Application of 1D ResNet for Multivariate Fault Detection on Semiconductor Manufacturing Equipment

Amid the ongoing emphasis on reducing manufacturing costs and enhancing productivity, one of the crucial objectives when manufacturing is to maintain process tools in optimal operating conditions. With advancements in sensing technologies, large amounts of data are collected during manufacturing processes, and the challenge today is to utilize these massive data efficiently. Some of these data are used for fault detection and classification (FDC) to evaluate the general condition of production machinery. The distinctive characteristics of semiconductor manufacturing, such as interdependent parameters, fluctuating behaviors over time, and frequently changing operating conditions, pose a major challenge in identifying defective wafers during the manufacturing process. To address this challenge, a multivariate fault detection method based on a 1D ResNet algorithm is introduced in this study. The aim is to identify anomalous wafers by analyzing the raw time-series data collected from multiple sensors throughout the semiconductor manufacturing process. To achieve this objective, a set of features is chosen from specified tools in the process chain to characterize the status of the wafers. Tests on the available data confirm that the gradient vanishing problem faced by very deep networks starts to occur with the plain 1D Convolutional Neural Network (CNN)-based method when the size of the network is deeper than 11 layers. To address this, a 1D Residual Network (ResNet)-based method is used. The experimental results show that the proposed method works more effectively and accurately compared to techniques using a plain 1D CNN and can thus be used for detecting abnormal wafers in the semiconductor manufacturing industry.

Induction Motor Stator Winding Inter-Tern Short Circuit Fault Detection Based on Start-Up Current Envelope Energy

Inter-turn short circuit (ITSC) is a common fault in induction motors. However, it is challenging to detect the early stage of ITSC fault. To address this issue, this paper proposes an ITSC fault detection method for three-phase induction motors based on start-up current envelope energy. This approach uses Akima interpolation to calculate the envelope of the measured start-up current of the induction motor. A Gaussian window weighting is applied to eliminate endpoint effects caused by the initial phase angle, and the enveloping energy is obtained using the energy formula as the fault feature. Finally, by combining this with the support vector machine (SVM) classification learner, fault detection of ITSC in induction motors is achieved. The experimental results show that the average accuracy of this method reaches 96.9%, which can quickly and accurately detect ITSC faults in asynchronous motors and determine the severity of the faults. Furthermore, the average accuracy of SVM in detecting early ITSC faults under no-load conditions is 98.8%, which is higher than other classification learners, including LR, KNN, and NN. This study provides a new idea for induction motor fault detection and can contribute to induction motor maintenance.

Incipient Fault Detection in a Hydraulic System Using Canonical Variable Analysis Combined with Adaptive Kernel Density Estimation

Incipient fault detection in a hydraulic system is a challenge in the condition monitoring community. Existing research mainly monitors abnormal working conditions in hydraulic systems by separately detecting the key working parameter, which often causes a high miss warning rate for incipient faults due to the oversight of parameter dependence. A principal component analysis provides an effective method for incipient fault detection by taking the correlation of multiple parameters into consideration, but this technique assumes the systems are Gaussian-distributed, making it invalid for a dynamic non-Gaussian system. In this paper, we combine a canonical variable analysis (CVA) and adaptive kernel density estimation (AKDE) for the early fault detection of nonlinear dynamic hydraulic systems. The collected hydraulic system data set was used to construct the typical variable space, and the state space and residual space are divided to represent the characteristics of different correlations between the two variables, which are quantitatively described using Hotelling's T2 and Q. In order to investigate the proper upper control limits, AKDE was utilised to estimate the underlying probability density functions of T2 and Q by taking the nonlinearity of the hydraulic system variables into consideration. The advantages of the proposed approach for incipient fault detection are illustrated via a marine power plant lubrication system.

Optimization of Gearbox Fault Detection Method Based on Deep Residual Neural Network Algorithm

Because of its long running time, complex working environment, and for other reasons, a gear is prone to failure, and early failure is difficult to detect by direct observation; therefore, fault diagnosis of gears is very necessary. Neural network algorithms have been widely used to realize gear fault diagnosis, but the structure of the neural network model is complicated, the training time is long and the model is not easy to converge. To solve the above problems and combine the advantages of the ResNeXt50 model in the extraction of image features, this paper proposes a gearbox fault detection method that integrates the convolutional block attention module (CBAM). Firstly, the CBAM is embedded in the ResNeXt50 network to enhance the extraction of image channels and spatial features. Secondly, the different time-frequency analysis method was compared and analyzed, and the method with the better effect was selected to convert the one-dimensional vibration signal in the open data set of the gearbox into a two-dimensional image, eliminating the influence of the redundant background noise, and took it as the input of the model for training. Finally, the accuracy and the average training time of the model were obtained by entering the test set into the model, and the results were compared with four other classical convolutional neural network models. The results show that the proposed method performs well both in fault identification accuracy and average training time under two working conditions, and it also provides some references for existing gear failure diagnosis research.

Fault Detection in 3D Printing: A Study on Sensor Positioning and Vibrational Patterns

This work examines the use of accelerometers to identify vibrational patterns that can effectively predict the state of a 3D printer, which could be useful for predictive maintenance. Prototypes using both a simple rectangular shape and a more complex Octopus shape were fabricated and evaluated. Fast Fourier Transform, Spectrogram, and machine learning models, such as Principal Component Analysis and Support Vector Machine, were employed for data analysis. The results indicate that vibrational signals can be used to predict the state of a 3D printer. However, the position of the accelerometers is crucial for vibration-based fault detection. Specifically, the sensor closest to the nozzle could predict the state of the 3D printer faster at a 71% greater sensitivity compared to sensors mounted on the frame and print bed. Therefore, the model presented in this study is appropriate for vibrational fault detection in 3D printers.

Discovering anomalies in big data: a review focused on the application of metaheuristics and machine learning techniques

With the increase in available data from computer systems and their security threats, interest in anomaly detection has increased as well in recent years. The need to diagnose faults and cyberattacks has also focused scientific research on the automated classification of outliers in big data, as manual labeling is difficult in practice due to their huge volumes. The results obtained from data analysis can be used to generate alarms that anticipate anomalies and thus prevent system failures and attacks. Therefore, anomaly detection has the purpose of reducing maintenance costs as well as making decisions based on reports. During the last decade, the approaches proposed in the literature to classify unknown anomalies in log analysis, process analysis, and time series have been mainly based on machine learning and deep learning techniques. In this study, we provide an overview of current state-of-the-art methodologies, highlighting their advantages and disadvantages and the new challenges. In particular, we will see that there is no absolute best method, i.e., for any given dataset a different method may achieve the best result. Finally, we describe how the use of metaheuristics within machine learning algorithms makes it possible to have more robust and efficient tools.

Sensor Fusion for Power Line Sensitive Monitoring and Load State Estimation

This paper deals with a specific approach to fault detection in transformer systems using the extended Kalman filter (EKF). Specific faults are investigated in power lines where a transformer is connected and only the primary electrical quantities, input voltage, and current are measured. Faults can occur in either the primary or secondary winding of the transformer. Two EKFs are proposed for fault detection. The first EKF estimates the voltage, current, and electrical load resistance of the secondary winding using measurements of the primary winding. The model of the transformer used is known as mutual inductance. For a short circuit in the secondary winding, the observer generates a signal indicating a fault. The second EKF is designed for harmonic detection and estimates the amplitude and frequency of the primary winding voltage. This contribution focuses on mathematical methods useful for galvanic decoupled soft sensing and fault detection. Moreover, the contribution emphasizes how EKF observers play a key role in the context of sensor fusion, which is characterized by merging multiple lines of information in an accurate conceptualization of data and their reconciliation with the measurements. Simulations demonstrate the efficiency of the fault detection using EKF observers.

Design and Implementation of a Fuzzy Classifier for FDI Applied to Industrial Machinery

In the present work, the design and the implementation of a Fault Detection and Isolation (FDI) system for an industrial machinery is proposed. The case study is represented by a multishaft centrifugal compressor used for the syngas manufacturing. The system has been conceived for the monitoring of the faults which may damage the multishaft centrifugal compressor: instrument single and multiple faults have been considered as well as process faults like fouling of the compressor stages and break of the thrust bearing. A new approach that combines Principal Component Analysis (PCA), Cluster Analysis and Pattern Recognition is developed. A novel procedure based on the statistical test ANOVA (ANalysis Of VAriance) is applied to determine the most suitable number of Principal Components (PCs). A key design issue of the proposed fault isolation scheme is the data Cluster Analysis performed to solve the practical issue of the complexity growth experienced when analyzing process faults, which typically involve many variables. In addition, an automatic online Pattern Recognition procedure for finding the most probable faults is proposed. Clustering procedure and Pattern Recognition are implemented within a Fuzzy Faults Classifier module. Experimental results on real plant data illustrate the validity of the approach. The main benefits produced by the FDI system concern the improvement of the maintenance operations, the enhancement of the reliability and availability of the compressor, the increase in the plant safety while achieving reduction in plant functioning costs.

Investigating Machine Learning and Control Theory Approaches for Process Fault Detection: A Comparative Study of KPCA and the Observer-Based Method

The paper focuses on the importance of prompt and efficient process fault detection in contemporary manufacturing industries, where product quality and safety protocols are critical. The study compares the efficiencies of two techniques for process fault detection: Kernel Principal Component Analysis (KPCA) and the observer method. Both techniques are applied to observe water volume variation within a hydraulic system comprising three tanks. PCA is an unsupervised learning technique used for dimensionality reduction and pattern recognition. It is an extension of Principal Component Analysis (PCA) that utilizes kernel functions to transform data into higher-dimensional spaces, where it becomes easier to separate classes or identify patterns. In this paper, KPCA is applied to detect faults in the hydraulic system by analyzing the variation in water volume. The observer method originates from control theory and is utilized to estimate the internal states of a system based on its output measurements. It is commonly used in control systems to estimate the unmeasurable or hidden states of a system, which is crucial for ensuring proper control and fault detection. In this study, the observer method is applied to the hydraulic system to estimate the water volume variations within the three tanks. The paper presents a comparative study of these two techniques applied to the hydraulic system. The results show that both KPCA and the observer method perform similarly in detecting faults within the system. This similarity in performance highlights the efficacy of these techniques and their potential adaptability in various fault diagnosis scenarios within modern manufacturing processes.

The implication of oversampling on the effectiveness of force signals in the fault detection of endodontic instruments during RCT

This work provides an innovative endodontic instrument fault detection methodology during root canal treatment (RCT). Sometimes, an endodontic instrument is prone to fracture from the tip, for causes uncertain the dentist's control. A comprehensive assessment and decision support system for an endodontist may avoid several breakages. This research proposes a machine learning and artificial intelligence-based approach that can help to diagnose instrument health. During the RCT, force signals are recorded using a dynamometer. From the acquired signals, statistical features are extracted. Because there are fewer instances of the minority class (i.e. faulty/moderate class), oversampling of datasets is required to avoid bias and overfitting. Therefore, the synthetic minority oversampling technique (SMOTE) is employed to increase the minority class. Further, evaluating the performance using the machine learning techniques, namely Gaussian Naïve Bayes (GNB), quadratic support vector machine (QSVM), fine k-nearest neighbor (FKNN), and ensemble bagged tree (EBT). The EBT model provides excellent performance relative to the GNB, QSVM, and FKNN. Machine learning (ML) algorithms can accurately detect endodontic instruments' faults by monitoring the force signals. The EBT and FKNN classifier is trained exceptionally well with an area under curve values of 1.0 and 0.99 and prediction accuracy of 98.95 and 97.56%, respectively. ML can potentially enhance clinical outcomes, boost learning, decrease process malfunctions, increase treatment efficacy, and enhance instrument performance, contributing to superior RCT processes. This work uses ML methodologies for fault detection of endodontic instruments, providing practitioners with an adequate decision support system.

Research on Wind Turbine Fault Detection Based on the Fusion of ASL-CatBoost and TtRSA

The internal structure of wind turbines is intricate and precise, although the challenging working conditions often give rise to various operational faults. This study aims to address the limitations of traditional machine learning algorithms in wind turbine fault detection and the imbalance of positive and negative samples in the fault detection dataset. To achieve the real-time detection of wind turbine group faults and to capture wind turbine fault state information, an enhanced ASL-CatBoost algorithm is proposed. Additionally, a crawling animal search algorithm that incorporates the Tent chaotic mapping and t-distribution mutation strategy is introduced to assess the sensitivity of the ASL-CatBoost algorithm toward hyperparameters and the difficulty of manual hyperparameter setting. The effectiveness of the proposed hyperparameter optimization strategy, termed the TtRSA algorithm, is demonstrated through a comparison of traditional intelligent optimization algorithms using 11 benchmark test functions. When applied to the hyperparameter optimization of the ASL-CatBoost algorithm, the TtRSA-ASL-CatBoost algorithm exhibits notable enhancements in accuracy, recall, and other performance measures compared with the ASL-CatBoost algorithm and other ensemble learning algorithms. The experimental results affirm that the proposed algorithm model improvement strategy effectively enhances the wind turbine fault detection classification recognition rate.

Improving the Efficiency of Fan Coil Units in Hotel Buildings through Deep-Learning-Based Fault Detection

Optimizing the performance of heating, ventilation, and air-conditioning (HVAC) systems is critical in today's energy-conscious world. Fan coil units (FCUs) play a critical role in providing comfort in various environments as an important component of HVAC systems. However, FCUs often experience failures that affect their efficiency and increase their energy consumption. In this context, deep learning (DL)-based fault detection offers a promising solution. By detecting faults early and preventing system failures, the efficiency of FCUs can be improved. This paper explores DL models as fault detectors for FCUs to enable smarter and more energy-efficient hotel buildings. We tested three contemporary DL modeling approaches: convolutional neural network (CNN), long short-term memory network (LSTM), and a combination of CNN and gated recurrent unit (GRU). The random forest model (RF) was additionally developed as a baseline benchmark. The fault detectors were tested on a real-world dataset obtained from the sensory measurement system installed in a hotel and additionally supplemented with simulated data via a physical model developed in TRNSYS. Three representative FCU faults, namely, a stuck valve, a reduction in airflow, and an FCU outage, were simulated with a much larger dataset than is typically utilized in similar studies. The results showed that the hybrid model, integrating CNN and GRU, performed best for all three observed faults. DL-based fault detectors outperformed the baseline RF model, confirming these solutions as viable components for energy-efficient hotels.

Quality-Related Process Monitoring and Diagnosis of Hot-Rolled Strip Based on Weighted Statistical Feature KPLS

Rolling is the main process in steel production. There are some problems in the rolling process, such as insufficient ability of abnormal detection and evaluation, low accuracy of process monitoring, and fault diagnosis. To improve the accuracy of quality-related fault diagnosis, this paper proposes a quality-related process monitoring and diagnosis method for hot-rolled strip based on weighted statistical feature KPLS. Firstly, the process-monitoring and diagnosis model of strip thickness and quality based on the KPLS method is introduced. Then, considering that the KPLS diagnosis method ignores the contribution of process variables to quality, it is easy to misjudge the root cause of quality in the diagnosis process. Based on the rolling mechanism model, the influence weight of strip thickness is constructed. By weighing the statistical data features, a quality diagnosis framework of series structure data fusion is constructed. Finally, the method is applied to the 1580 mm hot-rolling process for industrial verification. The verification results show that the proposed method has higher diagnostic accuracy than PLS, KPLS, and other methods. The results show that the diagnostic model based on weighted statistical feature KPLS has a diagnostic accuracy of more than 96% for strip thickness and quality-related faults.

Research on Rolling Bearing Fault Diagnosis Based on Digital Twin Data and Improved ConvNext

This article introduces a novel framework for diagnosing faults in rolling bearings. The framework combines digital twin data, transfer learning theory, and an enhanced ConvNext deep learning network model. Its purpose is to address the challenges posed by the limited actual fault data density and inadequate result accuracy in existing research on the detection of rolling bearing faults in rotating mechanical equipment. To begin with, the operational rolling bearing is represented in the digital realm through the utilization of a digital twin model. The simulation data produced by this twin model replace traditional experimental data, effectively creating a substantial volume of well-balanced simulated datasets. Next, improvements are made to the ConvNext network by incorporating an unparameterized attention module called the Similarity Attention Module (SimAM) and an efficient channel attention feature referred to as the Efficient Channel Attention Network (ECA). These enhancements serve to augment the network's capability for extracting features. Subsequently, the enhanced network model is trained using the source domain dataset. Simultaneously, the trained model is transferred to the target domain bearing using transfer learning techniques. This transfer learning process enables the accurate fault diagnosis of the main bearing to be achieved. Finally, the proposed method's feasibility is validated, and a comparative analysis is conducted in comparison with similar approaches. The comparative study demonstrates that the proposed method effectively addresses the issue of low mechanical equipment fault data density, leading to improved accuracy in fault detection and classification, along with a certain level of robustness.

High-Speed Hardware Architecture Based on Error Detection for KECCAK

The hash function KECCAK integrity algorithm is implemented in cryptographic systems to provide high security for any circuit requiring integrity and protect the transmitted data. Fault attacks, which can extricate confidential data, are one of the most effective physical attacks against KECCAK hardware. Several KECCAK fault detection systems have been proposed to counteract fault attacks. The present research proposes a modified KECCAK architecture and scrambling algorithm to protect against fault injection attacks. Thus, the KECCAK round is modified so that it consists of two parts with input and pipeline registers. The scheme is independent of the KECCAK design. Iterative and pipeline designs are both protected by it. To test the resilience of the suggested detection system approach fault attacks, we conduct permanent as well as transient fault attacks, and we evaluate the fault detection capabilities (99.9999% for transient faults and 99.999905% for permanent faults). The KECCAK fault detection scheme is modeled using VHDL language and implemented on an FPGA hardware board. The experimental results show that our technique effectively secures the KECCAK design. It can be carried out with little difficulty. In addition, the experimental FPGA results demonstrate the proposed KECCAK detection scheme's low area burden, high efficiency and working frequency.

RAIM and Failure Mode Slope: Effects of Increased Number of Measurements and Number of Faults

This article provides a comprehensive analysis of the impact of the increasing number of measurements and the possible increase in the number of faults in multi-constellation Global Navigation Satellite System (GNSS) Receiver Autonomous Integrity Monitoring (RAIM). Residual-based fault detection and integrity monitoring techniques are ubiquitous in linear over-determined sensing systems. An important application is RAIM, as used in multi-constellation GNSS-based positioning. This is a field in which the number of measurements, m, available per epoch is rapidly increasing due to new satellite systems and modernization. Spoofing, multipath, and non-line of sight signals could potentially affect a large number of these signals. This article fully characterizes the impact of measurement faults on the estimation (i.e., position) error, the residual, and their ratio (i.e., the failure mode slope) by analyzing the range space of the measurement matrix and its orthogonal complement. For any fault scenario affecting h measurements, the eigenvalue problem that defines the worst-case fault is expressed and analyzed in terms of these orthogonal subspaces, which enables further analysis. For h>(m-n), where n is the number of estimated variables, it is known that there always exist faults that are undetectable from the residual vector, yielding an infinite value for the failure mode slope. This article uses the range space and its complement to explain: (1) why, for fixed h and n, the failure mode slope decreases with m; (2) why, for a fixed n and m, the failure mode slope increases toward infinity as h increases; (3) why a failure mode slope can become infinite for h≤(m-n). A set of examples demonstrate the results of the paper.

Machine Fault Detection Using a Hybrid CNN-LSTM Attention-Based Model

The predictive maintenance of electrical machines is a critical issue for companies, as it can greatly reduce maintenance costs, increase efficiency, and minimize downtime. In this paper, the issue of predicting electrical machine failures by predicting possible anomalies in the data is addressed through time series analysis. The time series data are from a sensor attached to an electrical machine (motor) measuring vibration variations in three axes: X (axial), Y (radial), and Z (radial X). The dataset is used to train a hybrid convolutional neural network with long short-term memory (CNN-LSTM) architecture. By employing quantile regression at the network output, the proposed approach aims to manage the uncertainties present in the data. The application of the hybrid CNN-LSTM attention-based model, combined with the use of quantile regression to capture uncertainties, yielded superior results compared to traditional reference models. These results can benefit companies by optimizing their maintenance schedules and improving the overall performance of their electric machines.

Fault Detection for Vaccine Refrigeration via Convolutional Neural Networks Trained on Simulated Datasets

In low-and middle-income countries, the cold chain that supports vaccine storage and distribution is vulnerable due to insufficient infrastructure and interoperable data. To bolster these networks, we developed a convolutional neural network-based fault detection method for vaccine refrigerators using datasets synthetically generated by thermodynamic modelling. We demonstrate that these thermodynamic models can be calibrated to real cooling systems in order to identify system-specific faults under a diverse range of operating conditions. If implemented on a large scale, this portable, flexible approach has the potential to increase the fidelity and lower the cost of vaccine distribution in remote communities.

The Performance Investigation of Smart Diagnosis for Bearings Using Mixed Chaotic Features with Fractional Order

This article presents a performance investigation of a fault detection approach for bearings using different chaotic features with fractional order, where the five different chaotic features and three combinations are clearly described, and the detection achievement is organized. In the architecture of the method, a fractional order chaotic system is first applied to produce a chaotic map of the original vibration signal in the chaotic domain, where small changes in the signal with different bearing statuses might be present; then, a 3D feature map can be obtained. Second, five different features, combination methods, and corresponding extraction functions are introduced. In the third action, the correlation functions of extension theory used to construct the classical domain and joint fields are applied to further define the ranges belonging to different bearing statuses. Finally, testing data are fed into the detection system to verify the performance. The experimental results show that the proposed different chaotic features perform well in the detection of bearings with 7 and 21 mil diameters, and an average accuracy rate of 94.4% was achieved in all cases.

Squat Detection of Railway Switches and Crossings Using Point Machine Vibration Measurements

Railway switches and crossings (S&C) are among the most important high-value components in a railway network and a failure of such an asset could result in severe network disturbance. Therefore, potential defects need to be detected at an early stage to prevent traffic-disturbing downtime or even severe accidents. A squat is a common defect of S&Cs that has to be monitored and repaired to reduce such risks. In this study, a testbed including a full-scale S&C and a bogie wagon was developed. Vibrations were measured for different squat sizes by an accelerometer mounted at the point machine. A method of processing the vibration data and the speed data is proposed to investigate the possibility of detecting and quantifying the severity of a squat. One key technology used is wavelet denoising. The study shows that it is possible to monitor the development of the squat size on the rail up to around 13 m from the point machine. The relationships between the normalised peak-to-peak amplitude of the vibration signal and the squat depth were also estimated.

A Fault-Detection System Approach for the Optimization of Warship Equipment Replacement Parts Based on Operation Parameters

Systems engineering plays a key role in the naval sector, focusing on how to design, integrate, and manage complex systems throughout their life cycle; it is therefore difficult to conceive functional warships without it. To this end, specialized information systems for logistical support and the sustainability of material solutions are essential to ensure proper provisioning and to know the operational status of the frigate. However, based on an architecture composed of a set of logistics applications, this information system may require highly qualified operators with a deep knowledge of the behavior of onboard systems to manage it properly. In this regard, failure detection systems have been postulated as one of the main cutting-edge methods to address the challenge, employing intelligent techniques for observing anomalies in the normal behavior of systems without the need for expert knowledge. In this paper, the study is concerned to the scope of the Spanish navy, where a complex information system structure is responsible for ensuring the correct maintenance and provisioning of the vessels. In such context, we hereby suggest a comparison between different one-class techniques, such as statistical models, geometric boundaries, or dimensional reduction to face anomaly detection in specific subsystems of a warship, with the prospect of applying it to the whole ship.

Anomaly Detection and Concept Drift Adaptation for Dynamic Systems: A General Method with Practical Implementation Using an Industrial Collaborative Robot

Industrial collaborative robots (cobots) are known for their ability to operate in dynamic environments to perform many different tasks (since they can be easily reprogrammed). Due to their features, they are largely used in flexible manufacturing processes. Since fault diagnosis methods are generally applied to systems where the working conditions are bounded, problems arise when defining condition monitoring architecture, in terms of setting absolute criteria for fault analysis and interpreting the meanings of detected values since working conditions may vary. The same cobot can be easily programmed to accomplish more than three or four tasks in a single working day. The extreme versatility of their use complicates the definition of strategies for detecting abnormal behavior. This is because any variation in working conditions can result in a different distribution of the acquired data stream. This phenomenon can be viewed as concept drift (CD). CD is defined as the change in data distribution that occurs in dynamically changing and nonstationary systems. Therefore, in this work, we propose an unsupervised anomaly detection (UAD) method that is capable of operating under CD. This solution aims to identify data changes coming from different working conditions (the concept drift) or a system degradation (failure) and, at the same time, can distinguish between the two cases. Additionally, once a concept drift is detected, the model can be adapted to the new conditions, thereby avoiding misinterpretation of the data. This paper concludes with a proof of concept (POC) that tests the proposed method on an industrial collaborative robot.

Controller Cyber-Attack Detection and Isolation

This article deals with the cyber security of industrial control systems. Methods for detecting and isolating process faults and cyber-attacks, consisting of elementary actions named "cybernetic faults" that penetrate the control system and destructively affect its operation, are analysed. FDI fault detection and isolation methods and the assessment of control loop performance methods developed in the automation community are used to diagnose these anomalies. An integration of both approaches is proposed, which consists of checking the correct functioning of the control algorithm based on its model and tracking changes in the values of selected control loop performance indicators to supervise the control circuit. A binary diagnostic matrix was used to isolate anomalies. The presented approach requires only standard operating data (process variable (PV), setpoint (SP), and control signal (CV). The proposed concept was tested using the example of a control system for superheaters in a steam line of a power unit boiler. Cyber-attacks targeting other parts of the process were also included in the study to test the proposed approach's applicability, effectiveness, and limitations and identify further research directions.

Decision Fault Tree Learning and Differential Lyapunov Optimal Control for Path Tracking

This paper considers the main challenges for all components engaged in the driving task suggested by the automation of road vehicles or autonomous cars. Numerous autonomous vehicle developers often invest an important amount of time and effort in fine-tuning and measuring the route tracking to obtain reliable tracking performance over a wide range of autonomous vehicle speed and road curvature diversities. However, a number of automated vehicles were not considered for fault-tolerant trajectory tracking methods. Motivated by this, the current research study of the Differential Lyapunov Stochastic and Decision Defect Tree Learning (DLS-DFTL) method is proposed to handle fault detection and course tracking for autonomous vehicle problems. Initially, Differential Lyapunov Stochastic Optimal Control (SOC) with customizable Z-matrices is to precisely design the path tracking for a particular target vehicle while successfully managing the noise and fault issues that arise from the localization and path planning. With the autonomous vehicle's low ceilings, a recommendation trajectory generation model is created to support such a safety justification. Then, to detect an unexpected deviation caused by a fault, a fault detection technique known as Decision Fault Tree Learning (DFTL) is built. The DLS-DFTL method can be used to find and locate problems in expansive, intricate communication networks. We conducted various tests and showed the applicability of DFTL. By offering some analysis of the experimental outcomes, the suggested method produces significant accuracy. In addition to a thorough study that compares the results to state-of-the-art techniques, simulation was also used to quantify the rate and time of defect detection. The experimental result shows that the proposed DLS-DFTL enhances the fault detection rate (38%), reduces the loss rate (14%), and has a faster fault detection time (24%) than the state of art methods.

Condition Monitoring of Additively Manufactured Injection Mould Tooling: A Review of Demands, Opportunities and Potential Strategies

Injection moulding (IM) is an important industrial process, known to be the most used plastic formation technique. Demand for faster cycle times and higher product customisation is driving interest in additive manufacturing (AM) as a new method for mould tool manufacturing. The use of AM offers advantages such as greater design flexibility and conformal cooling of components to reduce cycle times and increase product precision. However, shortcomings of metal additive manufacturing, such as porosity and residual stresses, introduce uncertainties about the reliability and longevity of AM tooling. The injection moulding process relies on high volumes of produced parts and a minimal amount of tool failures. This paper reviews the demands for tool condition monitoring systems for AM-manufactured mould tools; although tool failures in conventionally manufactured tooling are rare, they do occur, usually due to cracking, deflection, and channel blockages. However, due to the limitations of the AM process, metal 3D-printed mould tools are susceptible to failures due to cracking, delamination and deformation. Due to their success in other fields, acoustic emission, accelerometers and ultrasound sensors offer the greatest potential in mould tool condition monitoring. Due to the noisy machine environment, sophisticated signal processing and decision-making algorithms are required to prevent false alarms or the missing of warning signals. This review outlines the state of the art in signal decomposition and both data- and model-based approaches to determination of the current state of the tool, and how these can be employed for IM tool condition monitoring. The development of such a system would help to ensure greater industrial uptake of additive manufacturing of injection mould tooling, by increasing confidence in the technology, further improving the efficiency and productivity of the sector.

Automated Battery Making Fault Classification Using Over-Sampled Image Data CNN Features

Due to the tremendous expectations placed on batteries to produce a reliable and secure product, fault detection has become a critical part of the manufacturing process. Manually, it takes much labor and effort to test each battery individually for manufacturing faults including burning, welding that is too high, missing welds, shifting, welding holes, and so forth. Additionally, manual battery fault detection takes too much time and is extremely expensive. We solved this issue by using image processing and machine learning techniques to automatically detect faults in the battery manufacturing process. Our approach will reduce the need for human intervention, save time, and be easy to implement. A CMOS camera was used to collect a large number of images belonging to eight common battery manufacturing faults. The welding area of the batteries' positive and negative terminals was captured from different distances, between 40 and 50 cm. Before deploying the learning models, first, we used the CNN for feature extraction from the image data. To over-sample the dataset, we used the Synthetic Minority Over-sampling Technique (SMOTE) since the dataset was highly imbalanced, resulting in over-fitting of the learning model. Several machine learning and deep learning models were deployed on the CNN-extracted features and over-sampled data. Random forest achieved a significant 84% accuracy with our proposed approach. Additionally, we applied K-fold cross-validation with the proposed approach to validate the significance of the approach, and the logistic regression achieved an 81.897% mean accuracy score and a +/- 0.0255 standard deviation.

A Brief Review of Acoustic and Vibration Signal-Based Fault Detection for Belt Conveyor Idlers Using Machine Learning Models

Due to increasing demands for ensuring the safety and reliability of a system, fault detection (FD) has received considerable attention in modern industries to monitor their machines. Bulk materials are transported worldwide using belt conveyors as an essential transport system. The majority of conveyor components are monitored continuously to ensure their reliability, but idlers remain a challenge to monitor due to the large number of idlers (rollers) distributed throughout the working environment. These idlers are prone to external noises or disturbances that cause a failure in the underlying system operations. The research community has begun using machine learning (ML) to detect idler's defects to assist industries in responding to failures on time. Vibration and acoustic measurements are commonly employed to monitor the condition of idlers. However, there has been no comprehensive review of FD for belt conveyor idlers. This paper presents a recent review of acoustic and vibration signal-based fault detection for belt conveyor idlers using ML models. It also discusses major steps in the approaches, such as data collection, signal processing, feature extraction and selection, and ML model construction. Additionally, the paper provides an overview of the main components of belt conveyor systems, sources of defects in idlers, and a brief introduction to ML models. Finally, it highlights critical open challenges and provides future research directions.

Generative Adversarial Network-Based Fault Detection in Semiconductor Equipment with Class-Imbalanced Data

This research proposes an application of generative adversarial networks (GANs) to solve the class imbalance problem in the fault detection and classification study of a plasma etching process. Small changes in the equipment part condition of the plasma equipment may cause an equipment fault, resulting in a process anomaly. Thus, fault detection in the semiconductor process is essential for success in advanced process control. Two datasets that assume faults of the mass flow controller (MFC) in equipment components were acquired using optical emission spectroscopy (OES) in the plasma etching process of a silicon trench: The abnormal process changed by the MFC is assumed to be faults, and the minority class of Case 1 is the normal class, and that of Case 2 is the abnormal class. In each case, additional minority class data were generated using GANs to compensate for the degradation of model training due to class-imbalanced data. Comparisons of five existing fault detection algorithms with the augmented datasets showed improved modeling performances. Generating a dataset for the minority group using GANs is beneficial for class imbalance problems of OES datasets in fault detection for the semiconductor plasma equipment.

Single-Sensor Engine Multi-Type Fault Detection

Engine fault detection is conducive to improving equipment reliability and reducing maintenance costs. In practical scenarios, high-quality data is difficult to obtain. Usually, only single-sensor data is available. This paper proposes a fault detection method combining Variational Mode Decomposition (VMD) and Random Forest (RF). At first, the spectral energy distribution is obtained by decomposing and statistic the engine data of multiple working conditions. Based on the spectral energy distribution, the overall optimal mode number was identified, and the quadratic penalty term was optimized using SNR. The improved VMD (IVMD) improves mode aliasing and iterative efficiency and unifies feature dimensions. Decomposition of real signals demonstrates the effectiveness. The paper designs a feature vector composed of seven types of attributes, including unit bandwidth energy, center frequency, maximum singular value and so on. The feature vector is then fed to RF for classification. Features are selected in order of importance to classification to improve the training efficiency. By comparing with various algorithms, the proposed method has higher accuracy and faster training efficiency in single-speed, multi-speed and cross-speed single-sensor data diagnosis. The results show that the method has application prospects with little training data and low hardware requirements.

A Review on Immune-Inspired Node Fault Detection in Wireless Sensor Networks with a Focus on the Danger Theory

The use of fault detection and tolerance measures in wireless sensor networks is inevitable to ensure the reliability of the data sources. In this context, immune-inspired concepts offer suitable characteristics for developing lightweight fault detection systems, and previous works have shown promising results. In this article, we provide a literature review of immune-inspired fault detection approaches in sensor networks proposed in the last two decades. We discuss the unique properties of the human immune system and how the found approaches exploit them. With the information from the literature review extended with the findings of our previous works, we discuss the limitations of current approaches and consequent future research directions. We have found that immune-inspired techniques are well suited for lightweight fault detection, but there are still open questions concerning the effective and efficient use of those in sensor networks.

A THD-Based Fault Protection Method Using MSOGI-FLL Grid Voltage Estimator

The rapid growth of the distributed generators (DGs) integration into the distribution systems (DSs) creates new technical issues; conventional relay settings need to be updated depending on the network topology and operational mode as fault protection a major challenge. This emphasizes the need for new fault protection methods to ensure secure protection and prevent undesirable tripping. Total harmonic distortion (THD) is an important indicator for assessing the quality of the grid. Here, a new protection system based on the THD of the grid voltages is proposed to address fault events in the electrical distribution network. The proposed protection system combines the THD with the estimates of the amplitude voltages and the zero-sequence component for defining an algorithm based on a finite state machine (FSM) for the detection, identification, and isolation of faults in the grid. The algorithm employs communication lines between all the protective devices (PDs) of the system to transmit tripping signals, allowing PDs to be coordinated. A second order generalized integrator (SOGI) and multiple SOGI (MSOGI) are used to obtain the THDs, estimated amplitude voltages, and zero-sequence component, which allows for fast detection with a low computational burden. The protection algorithm performance is evaluated through simulations in MATLAB/Simulink and a comparative study is developed between the proposed protection method and a differential relay (DR) protection system. The proposed method shows its capability to detect and isolate faults during different fault types with different fault resistances in different locations in the proposed network. In all the tested scenarios, the detection time of the faults has been between 7-10 ms. Moreover, this method gave the best solution as it has a higher accuracy and faster response than the conventional DR protection system.

On-Device Intelligence for Malfunction Detection of Water Pump Equipment in Agricultural Premises: Feasibility and Experimentation

The digital transformation of agriculture is a promising necessity for tackling the increasing nutritional needs on Earth and the degradation of natural resources. Toward this direction, the availability of innovative electronic components and of the accompanying software programs can be exploited to detect malfunctions in typical agricultural equipment, such as water pumps, thereby preventing potential failures and water and economic losses. In this context, this article highlights the steps for adding intelligence to sensors installed on pumps in order to intercept and deliver malfunction alerts, based on cheap in situ microcontrollers, sensors, and radios and easy-to-use software tools. This involves efficient data gathering, neural network model training, generation, optimization, and execution procedures, which are further facilitated by the deployment of an experimental platform for generating diverse disturbances of the water pump operation. The best-performing variant of the malfunction detection model can achieve an accuracy rate of about 93% based on the vibration data. The system being implemented follows the on-device intelligence approach that decentralizes processing and networking tasks, thereby aiming to simplify the installation process and reduce the overall costs. In addition to highlighting the necessary implementation variants and details, a characteristic set of evaluation results is also presented, as well as directions for future exploitation.

Broken Bar Fault Detection Using Taylor-Fourier Filters and Statistical Analysis

Broken rotor bars in induction motors make up one of the typical fault types that are challenging to detect. This type of damage can provoke adverse effects on the motors, such as mechanical and electrical stresses, together with an increase in electricity consumption, causing higher operative costs and losses related to the maintenance times or even the motor replacement if the damage has led to a complete failure. To prevent such situations, diverse signal processing algorithms have been applied to incipient fault detection, using different variables to analyze, such as vibrations, current, or flux. To counteract the broken rotor bar damage, this paper focuses on a motor current signal analysis for early broken bar detection and classification by using the digital Taylor-Fourier transform (DTFT), whose implementation allows fine filtering and amplitude estimation with the final purpose of achieving an incipient fault detection. The detection is based on an analysis of variance followed by a Tukey test of the estimated amplitude. The proposed methodology is implemented in Matlab using the O-splines of the DTFT to reduce the computational load compared with other methods. The analysis is focused on groups of 50-test of current signals corresponding to different damage levels for a motor operating at 50% and 75% of its full load.

Data-Driven Low-Frequency Oscillation Event Detection Strategy for Railway Electrification Networks

Low-frequency oscillations (LFO) occur in railway electrification systems due to the incorporation of new trains with switching converters. As a result, the increased harmonic content can cause catenary stability problems under certain conditions. Most of the research published on this topic to date is focused on modelling the event and analysing it using frequency spectrums. However, in recent years, due to the new technologies linked to Big Data (BD) and data mining (DM), a new opportunity to study and detect LFO events by means of machine-learning (ML) methods has emerged. Trains continuously collect data from the most important catenary variables, which offers new resources for analysing this type of event. Therefore, this article presents the design and implementation of a data-driven LFO event detection strategy for AC railway network scenarios. Compared to previous investigations, a new approach to analyse and detect LFO events, based on field data and ML, is presented. To obtain the most appropriate detection approach for the context of this application, on the one hand, this investigation includes a comparison of machine-learning algorithms (support vector machine, logistic regression, random forest, k-nearest neighbours, naïve Bayes) which have been trained with real field data. On the other hand, an analysis of key parameters and features to optimize event detection is also included. Thus, the most significant result of this work is the high metric values of the solution, reaching values above 97% in accuracy and 93% in F-1 score with the random forest algorithm. In addition, the applicability and training of data-driven methods with real field data are demonstrated. This automatic detection strategy can help with speeding up and improving LFO detection tasks that used to be performed manually. Finally, it is worth mentioning that this research has been structured based on the CRISP-DM methodology, established as the de facto approach for industrial DM projects.

Comparative Study between Physics-Informed CNN and PCA in Induction Motor Broken Bars MCSA Detection

In this article, two methods for broken bar detection in induction motors are considered and tested using data collected from the LIAS laboratory at the University of Poitiers. The first approach is Motor Current Signature Analysis (MCSA) with Convolutional Neural Networks (CNN), in which measurements have to be processed in the frequency domain before training the CNN to ensure that the resulting model is physically informed. A double input CNN has been introduced to perform a 100% detection regardless of the speed and load torque value. A second approach is the Principal Components Analysis (PCA), in which the processing is undertaken in the time domain. The PCA is applied on the induction motor currents to eventually calculate the Q statistic that serves as a threshold for detecting anomalies/faults. Even if obtained results show that both approaches work very well, there are major differences that need to be pointed out, and this is the aim of the current paper.

Piston Wear Detection and Feature Selection Based on Vibration Signals Using the Improved Spare Support Vector Machine for Axial Piston Pumps

A piston wear fault is a major failure mode of axial piston pumps, which may decrease their volumetric efficiency and service life. Although fault detection based on machine learning theory can achieve high accuracy, the performance mainly depends on the detection model and feature selection. Feature selection in learning has recently emerged as a crucial issue. Therefore, piston wear detection and feature selection are essential and urgent. In this paper, we propose a vibration signal-based methodology using the improved spare support vector machine, which can integrate the feature selection into the piston wear detection learning process. Forty features are defined to capture the piston wear signature in the time domain, frequency domain, and time-frequency domain. The relevance and impact of sparsity in 40 features are illustrated through the single and multiple statistical feature analysis. Model performance is assessed and the sparse features are discovered. The maximum model testing and training accuracy are 97.50% and 96.60%, respectively. Spare features s₁₀, s₁₂, E_w(8), x₇, E_e(5), and E_e(4) are selected and validated. Results show that the proposed methodology is applicable for piston wear detection and feature selection, with high model accuracy and good feature sparsity.

Applied Machine Learning for IIoT and Smart Production-Methods to Improve Production Quality, Safety and Sustainability

Industrial IoT (IIoT) has revolutionized production by making data available to stakeholders at many levels much faster, with much greater granularity than ever before. When it comes to smart production, the aim of analyzing the collected data is usually to achieve greater efficiency in general, which includes increasing production but decreasing waste and using less energy. Furthermore, the boost in communication provided by IIoT requires special attention to increased levels of safety and security. The growth in machine learning (ML) capabilities in the last few years has affected smart production in many ways. The current paper provides an overview of applying various machine learning techniques for IIoT, smart production, and maintenance, especially in terms of safety, security, asset localization, quality assurance and sustainability aspects. The approach of the paper is to provide a comprehensive overview on the ML methods from an application point of view, hence each domain-namely security and safety, asset localization, quality control, maintenance-has a dedicated chapter, with a concluding table on the typical ML techniques and the related references. The paper summarizes lessons learned, and identifies research gaps and directions for future work.

Explainable AI Algorithms for Vibration Data-Based Fault Detection: Use Case-Adadpted Methods and Critical Evaluation

Analyzing vibration data using deep neural networks is an effective way to detect damages in rotating machinery at an early stage. However, the black-box approach of these methods often does not provide a satisfactory solution because the cause of classifications is not comprehensible to humans. Therefore, this work investigates the application of the explainable AI (XAI) algorithms to convolutional neural networks for vibration-based condition monitoring. Thus, the three XAI algorithms GradCAM, LRP and LIME with a modified perturbation strategy are applied to classifications based on the Fourier transform as well as the order analysis of the vibration signal. The following visualization as frequency-RPM maps and order-RPM maps allows for an effective assessment of saliency values for variable periodicity of the data, which translates to a varying rotation speed of a real-world machine. To compare the explanatory power of the XAI methods, investigations are first carried out with a synthetic data set with known class-specific characteristics. Both a visual and a quantitative analysis of the resulting saliency maps are presented. Then, a real-world data set for vibration-based imbalance classification on an electric motor, which runs at a broad range of rotation speeds, is used. The results indicate that the investigated algorithms are each partially successful in providing sample-specific saliency maps which highlight class-specific features and omit features which are not relevant for classification.

A Machine-Learning-Based Robust Classification Method for PV Panel Faults

Renewable energy resources have gained considerable attention in recent years due to their efficiency and economic benefits. Their proportion of total energy use continues to grow over time. Photovoltaic (PV) cell and wind energy generation are the least-expensive new energy sources in most countries. Renewable energy technologies significantly contribute to climate mitigation and provide economic benefits. Apart from these advantages, renewable energy sources, particularly solar energy, have drawbacks, for instance restricted energy supply, reliance on weather conditions, and being affected by several kinds of faults, which cause a high power loss. Usually, the local PV plants are small in size, and it is easy to trace any fault and defect; however, there are many PV cells in the grid-connected PV system where it is difficult to find a fault. Keeping in view the aforedescribed facts, this paper presents an intelligent model to detect faults in the PV panels. The proposed model utilizes the Convolutional Neural Network (CNN), which is trained on historic data. The dataset was preprocessed before being fed to the CNN. The dataset contained different parameters, such as current, voltage, temperature, and irradiance, for five different classes. The simulation results showed that the proposed CNN model achieved a training accuracy of 97.64% and a testing accuracy of 95.20%, which are much better than the previous research performed on this dataset.

A Review on Rolling Bearing Fault Signal Detection Methods Based on Different Sensors

As a precision mechanical component to reduce friction between components, the rolling bearing is widely used in many fields because of its slight friction loss, strong bearing capacity, high precision, low power consumption, and high mechanical efficiency. This paper reviews several excellent kinds of study and their relevance to the fault detection of rolling bearings. We summarize the fault location, sensor types, bearing fault types, and fault signal analysis of rolling bearings. The fault signal types are divided into one-dimensional and two-dimensional images, which account for 40.14% and 31.69%, respectively, and their classification is clarified and discussed. We counted the proportions of various methods in the references cited in this paper. Among them, the method of one-dimensional signal detection with external sensors accounted for 3.52%, the method of one-dimensional signal detection with internal sensors accounted for 36.62%, and the method of two-dimensional signal detection with external sensors accounted for 19.72%. The method of two-dimensional signal detection with internal sensors accounted for 11.97%. Among these methods, the highest detection rate is 100%, and the lowest detection rate is more than 70%. The similarities between the different methods are compared. The research results summarized in this paper show that with the progress of the times, a variety of new and better research methods have emerged, which have sped up the detection and diagnosis of rolling bearing faults. For example, the technology using artificial intelligence is still developing rapidly, such as artificial neural networks, convolutional neural networks, and machine learning. Although there are still defects, such methods can quickly discover a fault and its cause, enrich the database, and accumulate experience. More and more advanced techniques are applied in this field, and the detection method has better robustness and superiority.

Multiple Sensor Fault Detection Using Index-Based Method

The research on sensor fault detection has drawn much interest in recent years. Abrupt, incipient, and intermittent sensor faults can cause the complete blackout of the system if left undetected. In this research, we examined the observer-based residual analysis via index-based approaches for fault detection of multiple sensors in a healthy drive. Seven main indices including the moving mean, average, root mean square, energy, variance, first-order derivative, second-order derivative, and auto-correlation-based index were employed and analyzed for sensor fault diagnosis. In addition, an auxiliary index was computed to differentiate a faulty sensor from a non-faulty one. These index-based methods were utilized for further analysis of sensor fault detection operating under a range of various loads, varying speeds, and fault severity levels. The simulation results on a permanent magnet synchronous motor (PMSM) are provided to demonstrate the pros and cons of various index-based methods for various fault detection scenarios.

A Fault Detection Method Based on an Oil Temperature Forecasting Model Using an Improved Deep Deterministic Policy Gradient Algorithm in the Helicopter Gearbox

The main gearbox is very important for the operation safety of helicopters, and the oil temperature reflects the health degree of the gearbox; therefore establishing an accurate oil temperature forecasting model is an important step for reliable fault detection. Firstly, in order to achieve accurate gearbox oil temperature forecasting, an improved deep deterministic policy gradient algorithm with a CNN-LSTM basic learner is proposed, which can excavate the complex relationship between oil temperature and working condition. Secondly, a reward incentive function is designed to accelerate the training time costs and to stabilize the model. Further, a variable variance exploration strategy is proposed to enable the agents of the model to fully explore the state space in the early training stage and to gradually converge in the training later stage. Thirdly, a multi-critics network structure is adopted to solve the problem of inaccurate Q-value estimation, which is the key to improving the prediction accuracy of the model. Finally, KDE is introduced to determine the fault threshold to judge whether the residual error is abnormal after EWMA processing. The experimental results show that the proposed model achieves higher prediction accuracy and shorter fault detection time costs.