Machine learning techniques applied to mechanical fault diagnosis and fault prognosis in the context of real industrial manufacturing use-cases: a systematic literature review

ResNet diagnosis of rotor faults in oil transfer pumps

To address rotor imbalance and misalignment in oil transfer pumps, an innovative diagnostic framework using Residual Network (ResNet) is proposed. The model incorporates advanced signal processing algorithms and strategic sensor placement to enhance diagnostic efficacy. A fault simulation test rig captured vibration signals from eight key measurement points on the pump. One-dimensional and multi-dimensional signal processing techniques generated comprehensive datasets for training and validating the model. Sensor placement optimization, focusing on the bearing seat's axial direction, inlet flange's vertical direction, and outlet flange's axial direction, increased rotor fault sensitivity. Time-frequency data processed via Short-Time Fourier Transform (STFT) achieved the highest diagnostic accuracy, surpassing 98 %. This study highlights the importance of optimal signal processing and precise sensor placement in improving the accuracy of diagnosing rotor faults in oil transfer pumps, thus enhancing the operational reliability and efficiency of energy transportation systems.

Condition Monitoring and Predictive Maintenance of Assets in Manufacturing Using LSTM-Autoencoders and Transformer Encoders

The production of multivariate time-series data facilitates the continuous monitoring of production assets. The modelling approach of multivariate time series can reveal the ways in which parameters evolve as well as the influences amongst themselves. These data can be used in tandem with artificial intelligence methods to create insight on the condition of production equipment, hence potentially increasing the sustainability of existing manufacturing and production systems, by optimizing resource utilization, waste, and production downtime. In this context, a predictive maintenance method is proposed based on the combination of LSTM-Autoencoders and a Transformer encoder in order to enable the forecasting of asset failures through spatial and temporal time series. These neural networks are implemented into a software prototype. The dataset used for training and testing the models is derived from a metal processing industry case study. Ultimately, the goal is to train a remaining useful life (RUL) estimation model.

Strategies for overcoming data scarcity, imbalance, and feature selection challenges in machine learning models for predictive maintenance

Predictive maintenance harnesses statistical analysis to preemptively identify equipment and system faults, facilitating cost- effective preventive measures. Machine learning algorithms enable comprehensive analysis of historical data, revealing emerging patterns and accurate predictions of impending system failures. Common hurdles in applying ML algorithms to PdM include data scarcity, data imbalance due to few failure instances, and the temporal dependence nature of PdM data. This study proposes an ML-based approach that adapts to these hurdles through the generation of synthetic data, temporal feature extraction, and the creation of failure horizons. The approach employs Generative Adversarial Networks to generate synthetic data and LSTM layers to extract temporal features. ML algorithms trained on the generated data achieved high accuracies: ANN (88.98%), Random Forest (74.15%), Decision Tree (73.82%), KNN (74.02%), and XGBoost (73.93%).

Systematic review of predictive maintenance and digital twin technologies challenges, opportunities, and best practices

Background

Maintaining machines effectively continues to be a challenge for industrial organisations, which frequently employ reactive or premeditated methods. Recent research has begun to shift its attention towards the application of Predictive Maintenance (PdM) and Digital Twins (DT) principles in order to improve maintenance processes. PdM technologies have the capacity to significantly improve profitability, safety, and sustainability in various industries. Significantly, precise equipment estimation, enabled by robust supervised learning techniques, is critical to the efficacy of PdM in conjunction with DT development. This study underscores the application of PdM and DT, exploring its transformative potential across domains demanding real-time monitoring. Specifically, it delves into emerging fields in healthcare, utilities (smart water management), and agriculture (smart farm), aligning with the latest research frontiers in these areas.

Methodology

Employing the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) criteria, this study highlights diverse modeling techniques shaping asset lifetime evaluation within the PdM context from 34 scholarly articles.

Results

The study revealed four important findings: various PdM and DT modelling techniques, their diverse approaches, predictive outcomes, and implementation of maintenance management. These findings align with the ongoing exploration of emerging applications in healthcare, utilities (smart water management), and agriculture (smart farm). In addition, it sheds light on the critical functions of PdM and DT, emphasising their extraordinary ability to drive revolutionary change in dynamic industrial challenges. The results highlight these methodologies' flexibility and application across many industries, providing vital insights into their potential to revolutionise asset management and maintenance practice for real-time monitoring.

Conclusions

Therefore, this systematic review provides a current and essential resource for academics, practitioners, and policymakers to refine PdM strategies and expand the applicability of DT in diverse industrial sectors.

Data-driven fault detection of heterogeneous multi-agent systems using combined hardware and temporal redundant information

This study addresses the fault detection (FD) problem in heterogeneous multi-agent systems (HMASs) with unknown system models. A novel data-driven FD scheme is proposed by properly combining hardware and temporal redundant information to accelerate the generation of fault detectors while ensuring detection accuracy. The computational burden associated with the FD scheme is alleviated by applying a two-step order reduction algorithm. Additionally, an optimization problem is formulated, simplified and solved to achieve a compromise between sensitivity to faults and robustness to disturbances, further enhancing the detection performance of agents. Through a series of examples and comparative experiments, the effectiveness and improvements of the proposed approach are demonstrated.

Prognostic and Health Management of Critical Aircraft Systems and Components: An Overview

Prognostic and health management (PHM) plays a vital role in ensuring the safety and reliability of aircraft systems. The process entails the proactive surveillance and evaluation of the state and functional effectiveness of crucial subsystems. The principal aim of PHM is to predict the remaining useful life (RUL) of subsystems and proactively mitigate future breakdowns in order to minimize consequences. The achievement of this objective is helped by employing predictive modeling techniques and doing real-time data analysis. The incorporation of prognostic methodologies is of utmost importance in the execution of condition-based maintenance (CBM), a strategic approach that emphasizes the prioritization of repairing components that have experienced quantifiable damage. Multiple methodologies are employed to support the advancement of prognostics for aviation systems, encompassing physics-based modeling, data-driven techniques, and hybrid prognosis. These methodologies enable the prediction and mitigation of failures by identifying relevant health indicators. Despite the promising outcomes in the aviation sector pertaining to the implementation of PHM, there exists a deficiency in the research concerning the efficient integration of hybrid PHM applications. The primary aim of this paper is to provide a thorough analysis of the current state of research advancements in prognostics for aircraft systems, with a specific focus on prominent algorithms and their practical applications and challenges. The paper concludes by providing a detailed analysis of prospective directions for future research within the field.

Rolling Bearing Fault Diagnosis Based on Support Vector Machine Optimized by Improved Grey Wolf Algorithm

This study targets the low accuracy and efficiency of the support vector machine (SVM) algorithm in rolling bearing fault diagnosis. An improved grey wolf optimizer (IGWO) algorithm was proposed based on deep learning and a swarm intelligence optimization algorithm to optimize the structural parameters of SVM and improve the rolling bearing fault diagnosis. A nonlinear contraction factor update strategy was also proposed. The variable coefficient changes with the shrinkage factor α. Thus, the search ability was balanced at different early and late stages by controlling the dynamic changes of the variable coefficient. In the early stages of optimization, its speed is low to avoid falling into local optimization. In the later stages of optimization, the speed is higher, and finding the optimal solution is easier, balancing the two different global and local optimization capabilities to complete efficient convergence. The dynamic weight update strategy was adopted to perform position updates based on adaptive dynamic weights. First, the dataset of Case Western Reserve University was used for simulation, and the results showed that the diagnosis accuracy of IGWO-SVM was 98.75%. Then, the IGWO-SVM model was trained and tested using data obtained from the full-life-cycle test platform of mechanical transmission bearings independently researched and developed by Nanjing Agricultural University. The fault diagnosis accuracy and convergence value of the adaptation curve were compared with those of PSO-SVM (particle swarm optimization) and GWO-SVM diagnosis models. Results showed that the IGWO-SVM model had the highest rolling bearing fault diagnosis accuracy and the best diagnosis convergence.

GRU-Based Denoising Autoencoder for Detection and Clustering of Unknown Single and Concurrent Faults during System Integration Testing of Automotive Software Systems

Recently, remarkable successes have been achieved in the quality assurance of automotive software systems (ASSs) through the utilization of real-time hardware-in-the-loop (HIL) simulation. Based on the HIL platform, safe, flexible and reliable realistic simulation during the system development process can be enabled. However, notwithstanding the test automation capability, large amounts of recordings data are generated as a result of HIL test executions. Expert knowledge-based approaches to analyze the generated recordings, with the aim of detecting and identifying the faults, are costly in terms of time, effort and difficulty. Therefore, in this study, a novel deep learning-based methodology is proposed so that the faults of automotive sensor signals can be efficiently and automatically detected and identified without human intervention. Concretely, a hybrid GRU-based denoising autoencoder (GRU-based DAE) model with the k-means algorithm is developed for the fault-detection and clustering problem in sequential data. By doing so, based on the real-time historical data, not only individual faults but also unknown simultaneous faults under noisy conditions can be accurately detected and clustered. The applicability and advantages of the proposed method for the HIL testing process are demonstrated by two automotive case studies. To be specific, a high-fidelity gasoline engine and vehicle dynamic system along with an entire vehicle model are considered to verify the performance of the proposed model. The superiority of the proposed architecture compared to other autoencoder variants is presented in the results in terms of reconstruction error under several noise levels. The validation results indicate that the proposed model can perform high detection and clustering accuracy of unknown faults compared to stand-alone techniques.

A Support Vector Machine-Based Approach for Bolt Loosening Monitoring in Industrial Customized Vehicles

Machine learning techniques have progressively emerged as important and reliable tools that, when combined with machine condition monitoring, can diagnose faults with even superior performance than other condition-based monitoring approaches. Furthermore, statistical or model-based approaches are often not applicable in industrial environments with a high degree of customization of equipment and machines. Structures such as bolted joints are a key part of the industry; therefore, monitoring their health is critical to maintaining structural integrity. Despite this, there has been little research on the detection of bolt loosening in rotating joints. In this study, vibration-based detection of bolt loosening in a rotating joint of a custom sewer cleaning vehicle transmission was performed using support vector machines (SVM). Different failures were analyzed for various vehicle operating conditions. Several classifiers were trained to evaluate the influence of the number and location of accelerometers used and to determine the best approach between specific models for each operating condition or a single model for all cases. The results showed that using a single SVM model with data from four accelerometers mounted both upstream and downstream of the bolted joint resulted in more reliable fault detection, with an overall accuracy of 92.4%.

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.

A novel approach for estimating and predicting uncertainty in water quality index model using machine learning approaches

With the significant increase in WQI applications worldwide and lack of specific application guidelines, accuracy and reliability of WQI models is a major issue. It has been reported that WQI models produce significant uncertainties during the various stages of their application including: (i) water quality indicator selection, (ii) sub-index (SI) calculation, (iii) water quality indicator weighting and (iv) aggregation of sub-indices to calculate the overall index. This research provides a robust statistically sound methodology for assessment of WQI model uncertainties. Eight WQI models are considered. The Monte Carlo simulation (MCS) technique was applied to estimate model uncertainty, while the Gaussian Process Regression (GPR) algorithm was utilised to predict uncertainties in the WQI models at each sampling site. The sub-index functions were found to contribute to considerable uncertainty and hence affect the model reliability - they contributed 12.86% and 10.27% of uncertainty for summer and winter applications, respectively. Therefore, the selection of sub-index function needs to be made with care. A low uncertainty of less than 1% was produced by the water quality indicator selection and weighting processes. Significant statistical differences were found between various aggregation functions. The weighted quadratic mean (WQM) function was found to provide a plausible assessment of water quality of coastal waters at reduced uncertainty levels. The findings of this study also suggest that the unweighted root means squared (RMS) aggregation function could be potentially also used for assessment of coastal water quality. Findings from this research could inform a range of stakeholders including decision-makers, researchers, and agencies responsible for water quality monitoring, assessment and management.

Deep Learning Techniques in Intelligent Fault Diagnosis and Prognosis for Industrial Systems: A Review

Fault diagnosis and prognosis (FDP) tries to recognize and locate the faults from the captured sensory data, and also predict their failures in advance, which can greatly help to take appropriate actions for maintenance and avoid serious consequences in industrial systems. In recent years, deep learning methods are being widely introduced into FDP due to the powerful feature representation ability, and its rapid development is bringing new opportunities to the promotion of FDP. In order to facilitate the related research, we give a summary of recent advances in deep learning techniques for industrial FDP in this paper. Related concepts and formulations of FDP are firstly given. Seven commonly used deep learning architectures, especially the emerging generative adversarial network, transformer, and graph neural network, are reviewed. Finally, we give insights into the challenges in current applications of deep learning-based methods from four different aspects of imbalanced data, compound fault types, multimodal data fusion, and edge device implementation, and provide possible solutions, respectively. This paper tries to give a comprehensive guideline for further research into the problem of intelligent industrial FDP for the community.

An Industrial Fault Diagnostic System Based on a Cubic Dynamic Uncertain Causality Graph

This study presents an industrial fault diagnosis system based on the cubic dynamic uncertain causality graph (cubic DUCG) used to model and diagnose industrial systems without sufficient data for model training. The system is developed based on cloud native technology. It contains two main parts, the diagnostic knowledge base and the inference method. The knowledge base was built by domain experts modularly based on professional knowledge. It represented the causality between events in the target industrial system in a visual and graphical form. During the inference, the cubic DUCG algorithm could dynamically generate the cubic causal graph according to the real-time data and perform the logic and probability calculations based on the generated cubic DUCG models, visually displaying the dynamic causal evolution of faults. To verify the system’s feasibility, we rebuild a fault-diagnosis model of the secondary circuit system of No. 1 at the Ningde nuclear power plant based on the new system. Twenty-four fault cases were used to test the diagnostic accuracy of the system, and all faults were correctly diagnosed. The results showed that it was feasible to use the cubic DUCG platform for fault diagnosis.