Fault Diagnosis Techniques Research Articles

Fault Diagnosis of Gearbox Using Machine Learning Approach

Gear box is crucial in industrial processes, enabling adjustments of speed and load conditions to meetoperational needs. As gearboxtechnologyadvances, their capabilities increase, but component failure can result in product losses and maintenance costs. Detecting potential failures before handis essential, and vibration measurementis a proven method for monitoring machine condition and predictinggearboxfaults. This study explores the use of machine learning to develop an automated fault diagnosis system for gear boxes using vibration signals. The performance of the developed model is compared with existing methods to determine the most effective algorithm. This research paper explores the application of machine learning techniques for faultdiagnosis of gear boxes using vibration signals. The study involved collecting vibration data fromgearboxes in both good and defective conditions, under various loading conditions. Statistical features were extracted from the collected data and used to develop a fault identification system. The performance of the developed model was evaluated and compared with existingmethods. The study also aimed to determine the mostsuitablealgorithm for the collected data. Overall, the paper provides insights into the effectiveness of using machine learning approaches for gear box fault diagnosis and identifies the best-performing algorithm for this task. Key Word: Machine Learning, Gearbox, Vibration, Data preprocessing, Algorithms.

Advances in Fault Detection and Diagnosis for Thermal Power Plants: A Review of Intelligent Techniques

Thermal power plants (TPPs) are critical to supplying energy to society, and ensuring their safe and efficient operation is a top priority. To minimize maintenance shutdowns and costs, modern TPPs have adopted advanced fault detection and diagnosis (FDD) techniques. These FDD approaches can be divided into three main categories: model-based, data-driven-based, and statistical-based methods. Despite the practical limitations of model-based methods, a multitude of data-driven and statistical techniques have been developed to monitor key equipment in TPPs. The main contribution of this paper is a systematic review of advanced FDD methods that addresses a literature gap by providing a comprehensive comparison and analysis of these techniques. The review discusses the most relevant FDD strategies, including model-based, data-driven, and statistical-based approaches, and their applications in enhancing the efficiency and reliability of TPPs. Our review highlights the novel and innovative aspects of these techniques and emphasizes their significance in sustainable energy development and the long-term viability of thermal power generation. This review further explores the recent advancements in intelligent FDD techniques for boilers and turbines in TPPs. It also discusses real-world applications, and analyzes the limitations and challenges of current approaches. The paper highlights the need for further research and development in this field, and outlines potential future directions to improve the safety, efficiency, and reliability of intelligent TPPs. Overall, this review provides valuable insights into the current state-of-the-art in FDD techniques for TPPs, and serves as a guide for future research and development.

A Simple and Effective Open-Circuit-Fault Diagnosis Method for Grid-Tied Power Converters—A New Technique Based on Tellegen’s Theorem

Grid-tied power converters are widely adopted in renewable energy integration systems. Reliable operation of such power converters is highly desirable, which relies on effective fault diagnosis and ride-through techniques. In this work, we propose a new open-circuit fault diagnosis method for grid-tied power converters based on Tellegen’s theorem, which is fast in fault detection and accurate in faulty component location. We first developed a “quasi-power” concept to define the relationship between current and voltage magnitudes for the underlying power converter. The value of the afore-developed quasi-power in this proposal depends solely on the connection state (i.e., the switch position and status) of a power converter, resulting in its good features of robustness to parameter variations and immunity to operation changes. Thereafter, we propose a fault diagnosis method based on the quasi-power of a converter, which is able to identify any faulty component among all the semiconductor switches (i.e., the insulated gate bipolar translators (IGBTs) and freewheeling diodes) at a time-scale of only one sampling period. As a case study, the proposed technique is incorporated into a well-known model predictive control (MPC) framework of a grid-tied two-level (2L) power converter and tested at a lab-constructed test bench. Experimental results confirm its effectiveness.

Extreme-Low-Speed Heavy Load Bearing Fault Diagnosis by Using Improved RepVGG and Acoustic Emission Signals.

With the worldwide carbon neutralization boom, low-speed heavy load bearings have been widely used in the field of wind power. Bearing failure generates impulses when the rolling element passes the cracked surface of the bearing. Over the past decade, acoustic emission (AE) techniques have been used to detect failure signals. However, the high sampling rates of AE signals make it difficult to design and extract fault features; thus, deep neural network-based approaches have been proposed. In this paper, we proposed an improved RepVGG bearing fault diagnosis technique. The normalized and noise-reduced bearing signals were first converted into Mel frequency cepstrum coefficients (MFCCs) and then inputted into the model. In addition, the exponential moving average method was used to optimize the model and improve its accuracy. Data were extracted from the test bench and wind turbine main shaft bearing. Four damage classes were studied experimentally. The experimental results demonstrated that the improved RepVGG model could be employed for classifying low-speed heavy load bearing states by using MFCCs. Furthermore, the effectiveness of the proposed model was assessed by performing comparisons with existing models.

Editorial for Special Issue: Machine Health Monitoring and Fault Diagnosis Techniques

Machine health monitoring and fault diagnosis have played crucial roles in automatic and intelligent industrial plants [...].

Motor On-Line Fault Diagnosis Method Research Based on 1D-CNN and Multi-Sensor Information

The motor is the primary impetus source of most mechanical equipment, and its failure will cause substantial economic losses and safety problems. Therefore, it is necessary to study online fault diagnosis techniques for motors, given the problems caused by shallow learning models or single-sensor fault analysis in previous motor fault diagnosis techniques, such as blurred fault features, inaccurate identification, and time and manpower consumption. In this paper, we proposed a model for motor fault diagnosis based on deep learning and multi-sensor information fusion. Firstly, a correlation adaptive weighting method is proposed in this paper, and it is used to integrate the collected multi-source homogeneous sensor information into multi-source heterogeneous sensor information through the data layer fusion. Secondly, the 1D-CNN is used to carry out feature extraction, feature layer fusion, and fault classification of multi-source heterogeneous information of the motor. Finally, the data of seven states (one healthy and six faulty) of the motor are collected by the motor drive test bench to realize the model’s training, testing, and verification. The experimental results show that the fault diagnosis accuracy of the model is 99.3%. Thus, this method has important practical implications for improving the accuracy of motor fault diagnosis further.

Comparative study of machine learning and deep learning techniques for fault diagnosis in suspension system

Comparative study of machine learning and deep learning techniques for fault diagnosis in suspension system

Condition-based maintenance with reinforcement learning for refrigeration systems with selected monitored features

Worldwide, buildings are responsible for almost 30% of energy consumption, and those buildings that intensively use refrigeration systems, such as supermarkets and grocery stores, are also among the most energy-intensive consumers. Refrigeration devices, either commercial or residential, are responsible for a significant part of net emissions. Based on careful measurements, it is possible to reduce energy consumption in these devices by up to 15% only by improving the fault detection and diagnosis techniques. Thus, improving maintenance programs has become a crucial area in energy management in recent years. Nowadays, the market has experienced a hike after smart systems and new network interfaces applied to smart buildings that have allowed previously isolated devices to become smart devices, interacting with control algorithms smartly and, to some extent, autonomously. Here, we propose a reinforcement learning framework to develop a maintenance policy for mechanical compression refrigeration devices. Firstly, a test bench is built in which each component is assigned to be individually repairable and individually degradable in parallel and interconnected processes. Then, the degradation of the components is combined to formulate the system degradation, and the optimal maintenance policy is modeled via Markov decision processes and solved by a reinforcement learning algorithm. The agent-proposed maintenance program if compared to corrective maintenance, managed to reduce energy use and emissions by around 6% while avoiding shortfalls, as well as about the preventive program, where the agent managed to accomplish the same level of energy efficiency while reducing the maintenance costs by 31% and the time under maintenance in 10%. It was found that the reinforcement learning frameworks applied to maintenance have a series of challenges but are innovative and can show promising results compared to traditional maintenance techniques, such as preventive and corrective ones.

Thermographic fault diagnosis of electrical faults of commutator and induction motors

In this paper, the author proposes a fault diagnosis technique for the analysis of thermal images of commutator motors (CMs) and single-phase induction motors (SIMs). The aim of scientific research is to confirm the effectiveness of the proposed technique for the analysis of thermal images of electric motors. Original feature extraction methods: DAMOM (Differences of Arithmetic Mean with Otsu’s Method), DAM20HP (Differences of Arithmetic Mean with 20 Highest Peaks), DAMMH (Differences of Arithmetic Mean with Mean of the histogram), IB (Ignore Binarization). The Nearest Neighbor classifier and Long short-term memory (LSTM) classified feature vectors. The thermal imaging camera was moved 0–1 [m/s2] vertically, during the measurements. Thermal imaging measurements with shivering and analysis are a novelty for fault diagnosis methods. The following conditions of motors were analyzed: healthy commutator motor (HCM), broken rotor coil of the commutator motor (BRCoCM), shorted stator coils of the commutator motor (SSCoCM), healthy single-phase induction motor (HSIM), single-phase induction motor with shorted coils of auxiliary winding (SIMwSCoAW), single-phase induction motor with shorted coils of auxiliary winding, and main winding (SIMwSCoAWaMW). The proposed analysis was successful. The value of AMECM (Arithmetic mean of the efficiency of recognition) was equal to 100% for the analyzed states of the CM. The value of AMESIM was in the range of 95.33%–100% for the analyzed states of the SIM. The original perspective of the presented study is to develop techniques of thermal imaging diagnostics. Readers can learn about the subject of thermographic diagnostics of electrical motors. Readers also gain knowledge about the processing of thermal images. A literature review on the diagnostics of electric motors was also presented.

Novel Discriminant Locality Preserving Projection Integrated With Monte Carlo Sampling for Fault Diagnosis

In complex industrial processes, the technique of fault diagnosis has been playing an increasingly considerable role in ensuring the safety of life and property. Unfortunately, the process data of complex industrial processes have the features of high dimension. Feature extraction from high-dimensional data is promising to coping with the fault data with high dimension. Recently, one of manifold learning methods named discriminant locality preserving projection achieves excellent performance in feature extraction. However, the performance of discriminant locality preserving projection (DLPP) is subject to the problem of matrix decomposition in the denominator of the objection function caused by the small sample size (SSS) issue. To overcome this limitation, novel DLPP integrated with Monte Carlo sampling is proposed to enhance the performance of feature extraction through dimensionality reduction. In the proposed MC-DLPP, Monte Carlo sampling is first utilized to generate fault samples for each fault type. With the aid of the virtually generated fault samples, the rank of the matrix in the denominator of the objection function of DLPP increases, thus well addressing the SSS problem. The Softmax classifier is used for fault diagnosis. To test the performance of the improved DLPP-based fault diagnosis, case studies using the Tennessee Eastman process are carried out. Simulation results confirm the presented MC-DLPP achieves superior accuracy in fault diagnosis.

Improved Locality Preserving Projections Based on Heat-Kernel and Cosine Weights for Fault Classification in Complex Industrial Processes

Data-driven fault diagnosis techniques have been widely used in industrial processes. However, facing a large amount of high-dimensional, nonlinear, and strongly coupled process data, traditional data-driven methods achieve low diagnostic accuracy due to ignoring the structural features inside data. To overcome this problem, this article proposes an improved locality preserving projections based on the heat-kernel and cosine weight matrix named Heat-Kernel and Cosine Weights Locality Preserving Projections (HC-LPP). In HC-LPP, a novel weight matrix construction strategy is employed, where a heat-kernel function is combined with a cosine function to optimize the weight matrix between data in terms of shortening distance and angle correlation, respectively. With the new weight matrix, the proposed HC-LPP considers both the distance and the correlation of samples (the shorter the distance is, the closer the neighbors are; the smaller the angle is, the more similar the neighbors are). The dimensionality reduction process of HC-LPP can well maintain the spatial geometric structure of data. Finally, the proposed HC-LPP integrated with the AdaBoost. M2 classifier is applied to the Tennessee Eastman process and the PROcess NeTwork Optimization process for fault diagnosis performance verification. Simulation results show, the proposed HC-LPP achieves better performance in diagnostic accuracy compared with other related methods.

Passive Thermography Based Bearing Fault Diagnosis Using Transfer Learning With Varying Working Conditions

Bearing is one of the core components of any rotating machine, and its failure is widespread. This reason drives continuous monitoring and detecting bearing faults during machine operation to warn operators and prevent unforeseen damage. This paper proposes an intelligent Passive Thermography (PTG) based fault diagnosis technique for detection of bearing faults using Convolutional Neural Network (CNN) with Transfer Learning (TL) under varying working conditions. The validation of the proposed method has been done on three different datasets; bearing test rig dataset has been taken as a source domain data while Induction Motor (IM), and Machine Fault Simulator (MFS) datasets have been taken as target domain data. The proposed method enables and speeds up the training process of CNN towards accurate adaptation for fault diagnosis approach in the escalated time frame. The experimental results demonstrated that the suggested approach could successfully learn transferable characteristics from the source domain model, which can cope with the issue of limited availability of training data required for the target domain. The classification accuracy on the target domain dataset were varied in the range of 89 -95.4 % in the case of the IM dataset and 96.5-97.5% in the case of the MFS dataset. Moreover, it shows the benefits of the suggested method, which may be utilized as an effective non-invasive diagnostic tool for rotating machines to avoid unexpected system shutdowns.

Investigation of Fault Diagnosis and Prognostics Techniques for Predictive Maintenance in Industrial Machinery

This research looks into fault detection and prognostic methods for industrial machinery predictive maintenance to maximize equipment dependability, reduce downtime, and improve operational effectiveness. The project aims to investigate integrated fault diagnosis and prognostics methodologies, analyze their applications in different industrial sectors, and determine policy implications to encourage implementation. Peer-reviewed articles, industry reports, case studies, and other current material are thoroughly reviewed as part of the technique. Major conclusions demonstrating the value of integrated fault diagnosis and prognostics in early fault identification, proactive decision-making, and optimal maintenance scheduling have been drawn from case studies in the power generating, petrochemical refining, and automotive manufacturing industries. The policy ramifications encompass the requirement for staff training, data standardization, investment in R&D, and regulatory frameworks to surmount constraints and stimulate innovation in industrial maintenance procedures. Organizations must adopt predictive maintenance technology to maintain competitiveness, cut expenses, and guarantee the dependable operation of vital mechanical assets in changing circumstances.

Induction Motor Fault Diagnosis Using Support Vector Machine, Neural Networks, and Boosting Methods

Induction motors are robust and cost effective; thus, they are commonly used as power sources in various industrial applications. However, due to the characteristics of induction motors, industrial processes can stop when motor failures occur. Thus, research is required to realize the quick and accurate diagnosis of faults in induction motors. In this study, we constructed an induction motor simulator with normal, rotor failure, and bearing failure states. Using this simulator, 1240 vibration datasets comprising 1024 data samples were obtained for each state. Then, failure diagnosis was performed on the acquired data using support vector machine, multilayer neural network, convolutional neural network, gradient boosting machine, and XGBoost machine learning models. The diagnostic accuracies and calculation speeds of these models were verified via stratified K-fold cross validation. In addition, a graphical user interface was designed and implemented for the proposed fault diagnosis technique. The experimental results demonstrate that the proposed fault diagnosis technique is suitable for diagnosing faults in induction motors.

Current Status and Prospects of Research on Sensor Fault Diagnosis of Agricultural Internet of Things

Sensors have been used in various agricultural production scenarios due to significant advances in the Agricultural Internet of Things (Ag-IoT), leading to smart agriculture. Intelligent control or monitoring systems rely heavily on trustworthy sensor systems. Nonetheless, sensor failures are likely due to various factors, including key equipment malfunction or human error. A faulty sensor can produce corrupted measurements, resulting in incorrect decisions. Early detection of potential faults is crucial, and fault diagnosis techniques have been proposed. The purpose of sensor fault diagnosis is to detect faulty data in the sensor and recover or isolate the faulty sensors so that the sensor can finally provide correct data to the user. Current fault diagnosis technologies are based mainly on statistical models, artificial intelligence, deep learning, etc. The further development of fault diagnosis technology is also conducive to reducing the loss caused by sensor failures.

Advanced fault detection and diagnosis in spacecraft attitude control systems: Current state and challenges

A review of advanced fault detection and diagnosis (FDD) techniques in attitude control systems (ACSs) of spacecraft is presented. In the first part of the paper, several types of ACS failure scenarios with their practical solutions are presented. Next, the existing approaches to FDD are considered and classified based on different criteria, including applications and design techniques. The literature of this part showed that to enhance ACS operational safety, predictability of failure of an ACS and/or of its components as well as reducing the possibility of failure occurrence is imperative. In addition, fast FDD of various kinds of failures is necessary to guarantee the required reliability of an ACS. The second part of this study highlights challenges involved with different FDD approaches, emphasizing their practical applicability. Current research gaps in FDD techniques such as insensitive residual signal, process monitoring methods, accurate plant model design, easy-to-use software development, FDD tuning process, dealing with noisy sensor measurements, time taken for fault management, the sensitivity of FDD system to faults, and FDD robustness are further elaborated on. Subsequently, the state-of-the-art FDD and its future needs are reflected on. The results of this study could direct spacecraft manufacturers and ACS providers to focus on future needs and improve ground testing for enhanced operational reliability and redundancy.

Deep Transfer Learning Models for Industrial Fault Diagnosis Using Vibration and Acoustic Sensors Data: A Review

In order to evaluate final quality, nondestructive testing techniques for finding bearing flaws have grown in favor. The precision of image processing-based vision-based technology has greatly improved for defect identification, inspection, and classification. Deep Transfer Learning (DTL), a kind of machine learning, combines the superiority of Transfer Learning (TL) for knowledge transfer with the benefits of Deep Learning (DL) for feature representation. As a result, the discipline of Intelligent Fault Diagnosis has extensively developed and researched DTL approaches. They can improve the robustness, reliability, and usefulness of DL-based fault diagnosis techniques (IFD). IFD has been the subject of several thorough and excellent studies, although most of them have appraised important research from an algorithmic standpoint, neglecting real-world applications. DTL-based IFD strategies have also not yet undergone a full evaluation. It is necessary and imperative to go through the relevant DTL-based IFD publications in light of this. Readers will be able to grasp the most cutting-edge concepts and develop practical solutions to any IFD challenges they may encounter by doing this. The theory behind DTL is briefly discussed before describing how transfer learning algorithms may be included into deep learning models. This research study looks at a number of vision-based methods for defect detection and identification utilizing vibration acoustic sensor data. The goal of this review is to assess where vision inspection system research is right now. In this respect, image processing as well as deep learning, machine learning, transfer learning, few-shot learning, and light-weight approach and its selection were explored. This review addresses the creation of defect classifiers and vision-based fault detection systems.

Fault Detection for Photovoltaic Panels in Solar Power Plants by Using Linear Iterative Fault Diagnosis (LIFD) Technique Based on Thermal Imaging System

Fault Detection for Photovoltaic Panels in Solar Power Plants by Using Linear Iterative Fault Diagnosis (LIFD) Technique Based on Thermal Imaging System

Application of Transient Analysis Techniques to Fault Diagnosis in Low- and Medium-Power Synchronous Machines

Fault diagnosis techniques applied to synchronous motors such as Permanent Magnet Synchronous Machines (PMSMs) and Synchronous Reluctance Machines (SynRMs) are scarcely addressed in the literature, in strong contrast to the attention paid to asynchronous motors. In addition, the most widespread techniques are those based on steady-state condition analysis, and little attention is paid to detection during transient operation. The present paper aims to identify research gaps on the topic and to demonstrate the potential of transient analysis. First, the different diagnostic methodologies in literature are thoroughly analyzed. Then, two laboratory case studies are presented to demonstrate the potential of fault detection under non-stationary conditions for a PMSM and a SynRM. Stator current analysis is performed by building time–frequency maps to analyze the evolution of different fault indicators. The results show clear differences between healthy and faulty conditions during the transient regime.

Fault Diagnosis Techniques for Nuclear Power Plants: A Review from the Artificial Intelligence Perspective

Fault diagnosis plays an important role in complex and safety-critical systems such as nuclear power plants (NPPs). With the development of artificial intelligence (AI), extensive research has been carried out for fast and efficient fault diagnosis based on intelligent methods. This paper presents a review of various AI-based system-level fault diagnosis methods for NPPs. We first discuss the development history of AI. Based on this exposition, AI-based fault diagnosis techniques are classified into knowledge-driven and data-driven approaches. For knowledge-driven methods, we discuss both the early if–then-based fault diagnosis techniques and the current new theory-based ones. The principles, application, and comparative analysis of the representative methods are systematically described. For data-driven strategies, we discuss single-algorithm-based techniques such as ANN, SVM, PCA, DT, and clustering, as well as hybrid techniques that combine algorithms together. The advantages and disadvantages of both knowledge-driven and data-driven methods are compared, illustrating the tendency to combine the two approaches. Finally, we provide some possible future research directions and suggestions.