Robust Fault Diagnosis Research Articles

Support-Vector Machine Approach for Robust Fault Diagnosis of Electric Vehicle Permanent Magnet Synchronous Motor

Permanent magnet synchronous motor (PMSM) is a leading technology for electric vehicles (EVs) and other high-performance industrial applications. These challenging applications demand robust fault diagnosis schemes, but conventional strategies based on models, system knowledge, and signal transformation have limitations that degrade the agility of diagnosing faults. These methods require extremely detailed design and consideration to remain robust against noise and disturbances in the actual application. Recent advancements in artificial intelligence and machine learning have proven to be promising next-generation solutions for fault diagnosis. In this paper, a support-vector machine (SVM) utilizing sparse representation is developed to perform sensor fault diagnosis of a PMSM. A simulation model of the pertinent PMSM drive system for automotive applications is used to generate a set of labelled training example sets that the SVM uses to determine margins between normal and faulty operating conditions. The PMSM model includes input as a torque reference profile and disturbance as a constant road grade, against both of which faults must be detectable. Even with limited training, the SVM classifier developed in this paper is capable of diagnosing faults with a high degree of accuracy, suggesting that such methods are feasible for the demanding fault diagnosis challenge in PMSM.

Bond Graph Based Model for Robust Fault Diagnosis

Bond Graph Based Model for Robust Fault Diagnosis

Moving Integration Filter-Based Open-Switch Fault-Diagnosis Method for Three-Phase Induction Motor Drive Systems

Reliable fault-diagnosis is essential to the induction motor drive systems in some special applications. In this article, we present a simple and robust fault-diagnosis scheme for three-phase induction motor drive systems. As the proposed fault-diagnosis method is based on the framework of model predictive control, many shared data can be fully utilized, and the computation burden is greatly reduced. To improve the robustness of fault detection, a moving integration filter-based residuals' construction method is proposed, which reduces both the false alarms rate and the rate of missed detection. According to the order of the constructed residuals and the sign of current errors, it is easy to accomplish the task of fault isolation. Experimental results are presented to demonstrate the effectiveness of the proposed fault-diagnosis method.

Fault Diagnosis of PMSG Stator Inter-Turn Fault Using Extended Kalman Filter and Unscented Kalman Filter

Since the permeant magnet synchronous generator (PMSG) has many applications in particular safety-critical applications, enhancing PMSG availability has become essential. An effective tool for enhancing PMSG availability and reliability is continuous monitoring and diagnosis of the machine. Therefore, designing a robust fault diagnosis (FD) and fault tolerant system (FTS) of PMSG is essential for such applications. This paper describes an FD method that monitors online stator winding partial inter-turn faults in PMSGs. The fault appears in the direct and quadrature (dq)-frame equations of the machine. The extended Kalman filter (EKF) and unscented Kalman filter (UKF) were used to detect the percentage and the place of the fault. The proposed techniques have been simulated for different fault scenarios using Matlab®/Simulink®. The results of the EKF estimation responses simulation were validated with the practical implementation results of tests that were performed with a prototype PMSG used in the Arab Academy For Science and Technology (AAST) machine lab. The results showed impressive responses with different operating conditions when exposed to different fault states to prevent the development of complete failure.

Finding faults: A scoping study of fault diagnostics for Industrial Cyber–Physical Systems

Context:As Industrial Cyber–Physical Systems (ICPS) become more connected and widely-distributed, often operating in safety-critical environments, we require innovative approaches to detect and diagnose the faults that occur in them. Objective:We profile fault identification and diagnosis techniques employed in the aerospace, automotive, and industrial control domains. Each of these sectors has adopted particular methods to meet their differing diagnostic needs. By examining both theoretical presentations as well as case studies from production environments, we present a profile of the current approaches being employed and identify gaps. Methodology:A scoping study was used to identify and compare fault detection and diagnosis methodologies that are presented in the current literature. We created categories for the different diagnostic approaches via a pilot study and present an analysis of the trends that emerged. We then compared the maturity of these approaches by adapting and using the NASA Technology Readiness Level (TRL) scale. Results:Fault identification and analysis studies from 127 papers published from 2004 to 2019 reveal a wide diversity of promising techniques, both emerging and in-use. These range from traditional Physics-based Models to Data-Driven Artificial Intelligence (AI) and Knowledge-Based approaches. Hybrid techniques that blend aspects of these three broad categories were also encountered. Predictive diagnostics or prognostics featured prominently across all sectors, along with discussions of techniques including Fault trees, Petri nets and Markov approaches. We also profile some of the techniques that have reached the highest Technology Readiness Levels, showing how those methods are being applied in real-world environments beyond the laboratory. Conclusions:Our results suggest that the continuing wide use of both Model-Based and Data-Driven AI techniques across all domains, especially when they are used together in hybrid configuration, reflects the complexity of the current ICPS application space. While creating sufficiently-complete models is labor intensive, Model-free AI techniques were evidenced as a viable way of addressing aspects of this challenge, demonstrating the increasing sophistication of current machine learning systems. Connecting ICPS together to share sufficient telemetry to diagnose and manage faults is difficult when the physical environment places demands on ICPS. Despite these challenges, the most mature papers present robust fault diagnosis and analysis techniques which have moved beyond the laboratory and are proving valuable in real-world environments.

Fault diagnosis of an industrial gas turbine based on the thermodynamic model coupled with a multi feedforward artificial neural networks

In the study presented in this paper, the deterioration in the performance of an industrial gas turbine during the operation design point was simulated by using the thermodynamic principle and a multi feedforward artificial neural networks (MFANN) system. Initially the thermodynamic model was constructed using the components performance map technique, that entailed calculating the operating point which was compliant with the performance map for each component. The various design operation points were generated by changing the engine component’s efficiency or outer environmental conditions and simulating the engine’s performance for each case. The MFANN model was constructed by using these operation points for the training and testing stage. In this way, the two MFANN models were established. The aim of the first model was to calculate the engine’s performance while the second model was used to detect the deterioration of the components of the engine This paper presents a robust fault diagnosis system for gas turbine degradation detection with the aim of improving energy efficiency.

Robust fault diagnosis and fault tolerant control for PEMFC system based on an augmented LPV observer

In order to improve the safety and reliability of proton exchange membrane fuel cell system, this paper proposes a novel robust fault observer for the fault diagnosis and reconstruction of the PEMFC air management system. First, considering the complexity and large computation of the nonlinear PEMFC system, a linear parameter-varying (LPV) model is introduced to describe the system behavior and reduce the computation cost. Then, an augmented state observer based on the LPV model is proposed for simultaneously estimating the internal states and component faults. The robustness is guaranteed by taking the system disturbances and measurement noises into consideration when designing the observer gain. The observer design is transformed into a process of solving a set of linear inequality matrices. According to the results, the augmented robust observer can accurately estimate the system states and faults under different conditions. Moreover, to realize the fault tolerant control of the air supply, the oxygen stoichiometry estimator is designed taking consideration of system fault information and a corresponding controller is employed for air compressor voltage following the net power maximization strategy.

Decision Making Method for Nonparametric Diagnosis in Nonlinear Dynamic Systems

The problem of robust fault diagnosis in nonlinear dynamic systems under presence of disturbances is studied within the scope of analytical redundancy conception. Solution of the problem assumes residual generation by checking redundancy relations existing among system inputs and outputs measured over a finite time window followed by decision making through evaluation of the residuals. Nonparametric method is considered for residual generation. To make decision, the unified method is developed whose feature is it combines the threshold logic of decision making and the residuals comparing with the fault syndromes evaluated on-line. Joint application of both nonparametric method for residual generation and unified method for decision making gives the possibility to develop the universal diagnostic platform for different systems described by ordinary nonlinear differential equations of the same structure but distinguished by these equations coefficients values.

Nonlinear robust fault diagnosis of power plant gas turbine using Monte Carlo-based adaptive threshold approach

This paper addresses the robust fault diagnosis of power plant gas turbine as an uncertain nonlinear system using a new adaptive threshold method. In order to determine the bounds of the adaptive threshold and to identify neural network thresholds modelling, an approach based on Monte Carlo simulation is employed. To evaluate the performance of the proposed fault detection method, a fault sensitivity analysis is provided. In addition, the neural network-based estimators are considered to estimate the magnitude of faults according to the values of residuals. The proposed fault diagnosis system is evaluated during different scenarios. The obtained results indicate the high sensitivity, accuracy, and robustness of the proposed method for fault detection and isolation in the nonlinear uncertain systems, even in dealing with small faults.

Robust Fault Diagnosis of Stochastic Discrete Event Systems

We investigate the problem of robust fault diagnosis of stochastic discrete-event systems against model uncertainty. In this problem, we assume that the actual behavior of the system is unknown a priori and the true model of the system belongs to a set of possible models described by probabilistic automata. The goal of this problem is to almost successfully detect the occurrence of fault in the sense that, first, no false alarm can be made, and second, the misdetection rate is smaller than a given threshold $\epsilon$ after some delay $K$ even without knowing the true model a priori . A condition termed as robust $(\epsilon,K)$ -diagnosability is proposed to capture the existence of such a robust diagnoser that satisfies the above-mentioned requirements. We also propose the notions of robust $\epsilon$ -diagnosability and robust A-diagnosability, which require that a given misdetection rate $\epsilon$ can be achieved with some delay and any arbitrarily small misdetection rate can be achieved, respectively. For each condition, an effective verification algorithm is also proposed. Our results generalize previous works on fault diagnosis of stochastic discrete-event systems by taking model uncertainty and specific misdetection rate into account.

Active Fault-Tolerant Control of a Quadcopter against Time-Varying Actuator Faults and Saturations Using Sliding Mode Backstepping Approach

Fault-tolerant control is becoming an interesting topic because of its reliability and safety. This paper reports an active fault-tolerant control method for a quadcopter unmanned aerial vehicle (UAV) to handle actuator faults, disturbances, and input constraints. A robust fault diagnosis based on the H ∞ scheme was designed to estimate the magnitude of a time-varying fault in the presence of disturbances with unknown upper bounds. Once the fault estimation was complete, a fault-tolerant control scheme was proposed for the attitude system, using adaptive sliding mode backstepping control to accommodate the actuator faults, despite actuator saturation limitation and disturbances. The Lyapunov theory was applied to prove the robustness and stability of the closed-loop system under faulty operation. Simulation results show the effectiveness of the fault diagnosis scheme and proposed controller for handling actuator faults.

Robust Observer-Based Fault Estimation for Lipschitz Nonlinear Systems with State-Coupled Disturbance: A Dissipativity Approach

In this paper, a robust fault diagnosis method is proposed to estimate the states and faults simultaneously for a special class of Lipschitz nonlinear systems. In the model of system, fault is considered as a linear and additive function and disturbance as a nonlinear function coupled with the system states. An augmented system is constructed by forming a vector composed of states and faults, and a Luenberger observer is designed for fault estimation. The nonlinear function of state-coupled disturbance is replaced by a Lipschitz matrix. In order to reduce the conservatism of the problem, this matrix depends on both the states and disturbances. This approach attempts to attenuate the effects of the state-coupled disturbances using the dissipativity theory such that the existing problem finally leads to solving convex optimization problems. The necessary conditions for the existence of such an observer are expressed. Finally the performance of the proposed method is simulated on a robot, and the results indicate good performance of the proposed method.

Robust fault detection of a class of uncertain linear parabolic PDEs

Robustness to uncertainties is one of the main challenges in model-based fault diagnosis. Robust fault diagnosis is a mature research area for Ordinary Differential Equation (ODE) systems. However, robust diagnostics for systems modeledby Partial Differential Equations (PDEs) is significantly under-explored in existing literature. Spatio-temporal evolution of faults make PDE fault diagnosis more challenging, as compared to its ODE counterpart where the fault evolves only temporally. Furthermore, robustness to uncertainties, that is, distinguishing the effect of uncertainties from faults is another key design challenge in fault diagnosis. This paper presents a robust fault diagnosis scheme for a class of uncertain linear parabolic PDEs. The proposed scheme consists of two subsystems: (i) Residual Generator and, (ii) Adaptive Threshold Generator. The Residual Generatoris a PDE observer whose output error is treated as a residual signal. Ideally, the residual signal should be zero if there is no fault and non-zero otherwise. However, the residual signal is non-zero even under non-faulty conditions, due to the presence of uncertainties. To achieve robustness against such uncertainties, we design a novel Adaptive Threshold Generatorthat generates an adaptive threshold. Finally, we illustrate the proposed scheme via simulation case studies on battery thermal fault detection.

Adaptive Fuzzy-Based Fault-Tolerant Control of a Continuum Robotic System for Maxillary Sinus Surgery

Continuum robots represent a class of highly sensitive, multiple-degrees-of-freedom robots that are biologically inspired. Because of their flexibility and accuracy, these robots can be used in maxillary sinus surgery. The design of an effective procedure with high accuracy, reliability, robust fault diagnosis, and fault-tolerant control for a surgical robot for the sinus is necessary to maintain the high performance and safety necessary for surgery on the maxillary sinus. Thus, a robust adaptive hybrid observation method using an adaptive, fuzzy auto regressive with exogenous input (ARX) Laguerre Takagi–Sugeno (T–S) fuzzy robust feedback linearization observer for a surgical robot is presented. To address the issues of system modeling, the fuzzy ARX-Laguerre technique is represented. In addition, a T–S fuzzy robust feedback linearization observer is applied to a fuzzy ARX-Laguerre to improve the accuracy of fault estimation, reliability, and robustness for the surgical robot in the presence of uncertainties. For fault-tolerant control in the presence of uncertainties and unknown conditions, an adaptive fuzzy observation-based feedback linearization technique is presented. The effectiveness of the proposed algorithm is tested with simulations. Experimental results show that the proposed method reduces the average position error from 35 mm to 2.45 mm in the presence of faults.

A Newly Robust Fault Detection and Diagnosis Method for High-Speed Trains

Incipient faults in high-speed trains are usually masked by noises and disturbances from process and sensors, which severely increases the difficulty of incipient fault detection and diagnosis. By introducing Hellinger distance into multivariate statistical analysis framework, this paper develops a robust detection and diagnosis method for incipient faults under the principal component analysis. The proposed method can detect all incipient sensor faults in traction systems of high-speed trains in real time by comparing reference probability density functions (PDFs) with the online estimated PDFs. According to the fault detection information, an accurate fault diagnosis can be achieved online through Bayesian inference. Key advantages of the proposed method are its salient robustness to unknown noises and disturbances, as well as the high sensitivity to incipient faults. In addition, the proposed method does not require any information on system models of high-speed trains or any human intervention. The effectiveness of the proposed method has been firstly proven by mathematical derivations and then been verified by numerical simulations. Finally, the proposed method has been applied to the practical experiment platform of the high-speed trains.

A Fault Diagnosis Algorithm for Microgrid Three-Phase Inverter Based on Trend Relationship of Adjacent Fold Lines

Fault diagnosis of a microgrid inverter is susceptible to asymmetric interference such as overcurrent component and bias component. It may lead to uncertain fluctuation of diagnosis features, even false alarm and erroneous triggering of protection units. Therefore, for a microgrid inverter, a robust fault diagnosis algorithm is necessary to cope with such asymmetric interference. Motivated by this observation, first, a new fault feature extraction method is proposed in this paper by the trend relationship of adjacent fold lines for data curve. It can be used to extract the fault feature and it is not affected by asymmetric interference. Second, a trend encoding method is proposed to encode the trend feature of a fold line, which is well visualized, easily identified, stored, and calculated. Third, two main indexes are calculated by the encoded features to represent the degree of abnormal and location information. Fourth, the diagnosis results are realized through the logical relation operations. Compared with the existing fault diagnosis algorithms, multiswitches fault can be accurately diagnosed in the case of asymmetric interference. Finally, the detailed experiment results and comparisons are shown to validate the proposed algorithm.

A Robust fault diagnosis and forecasting approach based on Kalman filter and Interval Type-2 Fuzzy Logic for efficiency improvement of centrifugal gas compressor system

The paper proposes a robust faults detection and forecasting approach for a centrifugal gas compressor system, the mechanism of this approach used the Kalman filter to estimate and filtering the unmeasured states of the studied system based on signals data of the inputs and the outputs that have been collected experimentally on site. The intelligent faults detection expert system is designed based on the interval type-2 fuzzy logic. The present work is achieved by an important task which is the prediction of the remaining time of the system under study to reach the danger and/or the failure stage based on the Auto-regressive Integrated Moving Average (ARIMA) model, where the objective within the industrial application is to set the maintenance schedules in precisely time. The obtained results prove the performance of the proposed faults diagnosis and detection approach which can be used in several heavy industrial systems

Fault Diagnosis for Rolling Bearings Based on Fine-Sorted Dispersion Entropy and SVM Optimized with Mutation SCA-PSO.

Rolling bearings are a vital and widely used component in modern industry, relating to the production efficiency and remaining life of a device. An effective and robust fault diagnosis method for rolling bearings can reduce the downtime caused by unexpected failures. Thus, a novel fault diagnosis method for rolling bearings by fine-sorted dispersion entropy and mutation sine cosine algorithm and particle swarm optimization (SCA-PSO) optimized support vector machine (SVM) is presented to diagnose a fault of various sizes, locations and motor loads. Vibration signals collected from different types of faults are firstly decomposed by variational mode decomposition (VMD) into sets of intrinsic mode functions (IMFs), where the decomposing mode number K is determined by the central frequency observation method, thus, to weaken the non-stationarity of original signals. Later, the improved fine-sorted dispersion entropy (FSDE) is proposed to enhance the perception for relationship information between neighboring elements and then employed to construct the feature vectors of different fault samples. Afterward, a hybrid optimization strategy combining advantages of mutation operator, sine cosine algorithm and particle swarm optimization (MSCAPSO) is proposed to optimize the SVM model. The optimal SVM model is subsequently applied to realize the pattern recognition for different fault samples. The superiority of the proposed method is assessed through multiple contrastive experiments. Result analysis indicates that the proposed method achieves better precision and stability over some relevant methods, whereupon it is promising in the field of fault diagnosis for rolling bearings.

Robust Fault Diagnosis for Discrete-Time Switched System with Unknown State Delays Subject to Component Faults

This paper investigates the problem of fault detection and diagnosis in a class of discrete-time switched systems with unknown state delays against component faults. First, a polytopic learning observers(LOs) is proposed to reconstruct both the system state and the loss of actuator effectiveness. The proposed LOs technique is also extended to the system with unknown time delays and external disturbance. Then the sufficient conditions for the convergence of LOs and the uniformly ultimately boundedness of the switched system are proved using the switched Lyapunov function approach and H_inf techniques. Finally, three kinds of fault signals are provided to verify the effectiveness of the developed techniques. The simulation results show that the reconstructed error of the fault signal is maintained within 1.9% after the convergence process, while the implicated error of the reconstructed signal for normal components can be limited to less than 2% in the most serious case.

A novel transfer learning method for robust fault diagnosis of rotating machines under variable working conditions

Vibration signals are closely linked with health conditions of rotating machines and widely used in fault diagnosis. Unfortunately, traditional vibration signal-based fault diagnosis methods are under a universal assumption that the target vibration signals for application and the available vibration signals for model training are collected from the same distribution, which is always impractical in real-world scenarios due to working condition variation. For robust fault diagnosis under variable working conditions, although some transfer learning-based methods are proposed, they mostly aim at aligning only the marginal distribution discrepancy of datasets, which is validated not sufficient in some cases. Hence, we propose a new transfer learning method called improved joint distribution adaptation (IJDA) to align both the marginal and conditional distributions of datasets more comprehensively. Meanwhile, built on it, a working condition-robust fault diagnosis method is developed, which utilizes vibration signals and is mainly composed of three parts. Firstly, a new data augmentation method is developed to generate more useful samples for imbalanced vibration signals, which innovatively uses noise to boost network performance. Secondly, sparse filtering (SF) is employed to reduce the input dimension of IJDA. Finally, IJDA is utilized to firstly extract both sharing and principal features and then diagnose the features. Experiments on vibration signal datasets of roller bearings and a gearbox and comparisons with other methods verify its effectiveness and applicability.