Proposed Fault Diagnosis Research Articles

A Novel Diagnostic Method for Single and Dual Power Switch Open-Circuit Faults of Six-Phase FTPMSM System Even in Fault Tolerant Operation

This article proposes a new diagnostic method based on average current Park vector (ACPV) for single and dual power switch open-circuit faults of six-phase fault-tolerant permanent magnet synchronous motor (FTPMSM) system, which can be applied for the system both in nonfault and fault tolerant operation conditions. The fault diagnosis structure is composed of two parts: the ACPV moduli-based fault detection and the ACPV polarity-based fault location. By analyzing the ACPV before and after the fault, the normalized ACPV moduli-based fault detection is proposed by using the ACPV components in three orthogonal subspaces, which has good robustness to the speed and load changes. The ACPV polarity-based fault location is then proposed to locate the faulted power switches of the FTPMSM system. Finally, the effectiveness of the proposed fault diagnosis method is validated by a six-phase FTPMSM experimental platform. The fault diagnosis approach has the advantageous features of simple implementation, good robustness to various disturbances, no requirement of the extra sensors, and low computational burden, which can achieve single and dual power switch open-circuit fault diagnosis for the FTPMSM system both in normal and fault tolerant operation conditions.

Online Diagnosis and Ride-Through Operation for Cascaded H-Bridge Converter Based STATCOM With a Single Open-Circuit IGBT

To address the most commonly seen single insulated gate bipolar transistor (IGBT) open-circuit fault problems in cascaded H-bridge (CHB) converter based static synchronous compensator, a simple online fault diagnosis method and the corresponding ride-through operation approach are proposed. The method can quickly determine the exact location of the open-circuit IGBT through three steps, via analyzing the relationships between the dc bias in the three-phase output current of CHB converter, the transient dc rail voltage variations with respect to the averaged dc rail voltage, and the response of dc rail voltage and output current when the modulation approach of the faulty power module is adjusted. Afterwards, a fault ride-through approach is adopted to seamlessly transfer the modulation approach of faulty H-bridge module and it behaves as a half-bridge to provide a half of the rated output ac voltage. Meanwhile, the corresponding dc offset voltage from this faulty module is compensated by producing the same dc voltage in the healthy phase legs to avoid the dc bias in the three-phase output current. It has been demonstrated that the proposed fault diagnosis approach and the fault ride-through approach are effective in various adverse situations including grid voltage sudden disturbances and the load power sudden changes. Comprehensive simulated and experimental results have been provided to validate the effectiveness of the proposed approach.

Cycle temporal algorithm-based multivariate statistical methods for fault diagnosis in chemical processes

Multivariate statistical process monitoring methods are often used in chemical process fault diagnosis. In this article, (I) the cycle temporal algorithm (CTA) combined with the dynamic kernel principal component analysis (DKPCA) and the multiway dynamic kernel principal component analysis (MDKPCA) fault detection algorithms are proposed, which are used for continuous and batch process fault detections, respectively. In addition, (II) a fault variable identification model based on reconstructed-based contribution (RBC) model that paves the way for determining the cause of the fault are proposed. The proposed fault diagnosis model was applied to Tennessee Eastman (TE) process and penicillin fermentation process for fault diagnosis. And compare with other fault diagnosis methods. The results show that the proposed method has better detection effects than other methods. Finally, the reconstruction-based contribution (RBC) model method is used to accurately locate the root cause of the fault and determine the fault path.

Takagi–Sugeno Fuzzy Observer-Based Magnetorheological Damper Fault Diagnosis Using a Support Vector Machine

In this article, a magnetorheological (MR) damper fault diagnosis algorithm is proposed. Recently, various studies have been proposed fault diagnosis methods for this damper system, however, these methods use a displacement sensor in addition to the two accelerometers mounted on the commercial vehicle. The use of this sensor configuration limits the application of the algorithm proposed so far to commercial vehicles. In order to overcome this limitation, this article proposes an MR damper fault diagnosis algorithm that uses only two accelerometers. Based on these sensors, the states of the vehicle suspension system are estimated by a Takagi-Sugeno (T-S) fuzzy unknown input observer. This observer scheme can estimate the states of the damper even under conditions affected by damper hysteresis and unknown road elevation. Using the Lyapunov stability theorem, the stability of the proposed observer with an unmeasured premise variable is verified. In addition, a support vector machine (SVM) classifier is used to determine damper condition without empirically set thresholds. In this article, a fault flag is generated by data-driven machine learning algorithms, reducing the design effort while at the same time achieving optimal performance. The proposed algorithm is verified using a quarter-car test rig and test results confirm that the proposed algorithm exhibits robust performance in various road conditions. Consequently, the MR damper fault diagnosis algorithm proposed in this article can reduce the effort in designing a diagnosis algorithm while using inexpensive production sensors applied to a vehicle.

Multiple Open-Circuit Fault Diagnosis Method in NPC Rectifiers Using Fault Injection Strategy

This article proposes an open-circuit fault diagnosis method in power semiconductors of three-level neutral-point-clamped (3L-NPC) rectifiers by using a fault injection strategy. To enhance the anti-interference ability of the diagnosis method, an improvement is made in the traditional calculation method of phase-to-phase pole voltage residuals by selectively adopting the quantifying operation according to the current level. Then, the normalized and quantified residuals are obtained as the diagnosis variables. All signals for calculations are derived from the controller and pre-existing sensors, avoiding the requirement of extra hardware. To improve the diagnosis accuracy and speed, a fault injection strategy is designed. A preidentification method provides guidance for choosing the type of fault to inject. On this basis, the fault injection is implemented by revising the switching signals sent from the modulation module for a short time. In this way, inner-switch faults and outer-switch faults are easier to be differentiated, and the misdiagnosis of simultaneous multiple-switch faults is avoided. Therefore, the proposed diagnosis method is accessible to detect single-switch faults as well as multiple-switch faults in 3L-NPC rectifiers more accurately and fast. The experiments are carried out to confirm the effectiveness and the robustness of the proposed fault diagnosis method.

Severity Estimation for Interturn Short-Circuit and Demagnetization Faults through Self-Attention Network.

This study presents a novel interturn short-circuit fault (ISCF) and demagnetization fault (DF) diagnosis strategy based on a self-attention-based severity estimation network (SASEN). We analyze the effects of the ISCF and DF in a permanent-magnet synchronous machine and select appropriate inputs for estimating the fault severities, i.e., a positive-sequence voltage and current and negative-sequence voltage and current. The chosen inputs are fed into the SASEN to estimate fault indicators for quantifying the fault severities of the ISCF and DF. The SASEN comprises an encoder and decoder based on a self-attention module. The self-attention mechanism enhances the high-dimensional feature extraction and regression ability of the network by concentrating on specific sequence representations, thereby supporting the estimation of the fault severities. The proposed strategy can diagnose a hybrid fault in which the ISCF and DF occur simultaneously and does not require the exact model and parameters essential for the existing method for estimating the fault severity. The effectiveness and feasibility of the proposed fault diagnosis strategy are demonstrated through experimental results based on various fault cases and load torque conditions.

Stacking ensemble based fault diagnosis approach for improved operation of photovoltaic arrays

ABSTRACT The operation of photovoltaic (PV) systems, like any other system, in fault free environment ensures maximum performance. Hence, accurate and timely fault identification of PV system demands greater importance. Present investigation proposes a stacking ensemble-based PV array fault diagnosis method, which is integrated with automatic feature engineering and selection technique, handling of imbalanced dataset for unbiased classification. The proposed ensemble utilizes decision tree (DT), random forest (RF), extra trees (EXT), extreme gradient boosting machine (XGBoost) as base learners, and light gradient boosting machine (LightGBM) as both base and meta-learner. To validate the proposed technique, a test system of 4.8kWp capacity has been built using the MATLAB/Simulink environment incorporating one-year real-time irradiance and module temperature data. Irradiance, module temperature, voltage, current, and power are collected as primary raw data which are then concocted using the autofeat python library for automatic feature engineering and selection. Subsequently, the proposed fault diagnosis strategy is built in python 3.8.5 using the engineered and class label balanced dataset, prepared using the synthetic minority over-sampling technique (SMOTE). Results demonstrate promising performance of the proposed ensemble technique with 97.04% accuracy in classifying the different faults in the PV array, which accounts for approximately 1–3% improvement over other individual machine learning (ML) models.

Quick Learning Mechanism With Cross-Domain Adaptation for Intelligent Fault Diagnosis

The fault diagnostic model trained for a laboratory case machine fails to perform well on the industrial machines running under variable operating conditions. For every new operating condition of such machines, a new diagnostic model has to be trained which is a time-consuming and uneconomical process. Therefore, we propose a quick learning mechanism that can transform the existing diagnostic model into a new model suitable for industrial machines operating in different conditions. The proposed method uses the Net2Net transformation followed by a fine-tuning to cancel/minimize the maximum mean discrepancy between the new data and the previous one. The fine-tuning of the model requires a very less amount of labeled target samples and very few iterations of training. Therefore, the proposed method is capable of learning the new target data pattern quickly. The effectiveness of the proposed fault diagnosis method has been demonstrated on the Case Western Reserve University dataset, Intelligent Maintenance Systems bearing dataset, and Paderborn university dataset under the wide variations of the operating conditions. It has been validated that the diagnostic model trained on artificially damaged fault datasets can be used to quickly train another model for a real damage dataset.

Design and implementation of robust corrective control systems with permanent sensor faults

This paper presents fault diagnosis and fault-tolerant corrective control for a class of asynchronous sequential machines (ASMs). In the considered problem setting, a permanent fault may occur to the sensor in the feedback channel so that the distorted state feedback is forced to be generated after a fault occurrence. We propose a scheme of identifying the permanent sensor fault only by observing the feedback value measured in the form of state bursts. Based on the diagnosis method, we address a novel design algorithm for a state-feedback corrective controller that matches the stable-state behavior of the closed-loop system to that of a reference model, while accommodating the permanent damage to the sensor. Hardware experiments on the field-programmable gate array (FPGA) circuit are provided to demonstrate the applicability of the proposed fault diagnosis and fault-tolerant corrective control methodology.

Rolling Bearing Fault Diagnosis Based on Markov Transition Field and Residual Network.

Data-driven rolling-bearing fault diagnosis methods are mostly based on deep-learning models, and their multilayer nonlinear mapping capability can improve the accuracy of intelligent fault diagnosis. However, problems such as gradient disappearance occur as the number of network layers increases. Moreover, directly taking the raw vibration signals of rolling bearings as the network input results in incomplete feature extraction. In order to efficiently represent the state characteristics of vibration signals in image form and improve the feature learning capability of the network, this paper proposes fault diagnosis model MTF-ResNet based on a Markov transition field and deep residual network. First, the data of raw vibration signals are augmented by using a sliding window. Then, vibration signal samples are converted into two-dimensional images by MTF, which retains the time dependence and frequency structure of time-series signals, and a deep residual neural network is established to perform feature extraction, and identify the severity and location of the bearing faults through image classification. Lastly, experiments were conducted on a bearing dataset to verify the effectiveness and superiority of the MTF-ResNet model. Features learned by the model are visualized by t-SNE, and experimental results indicate that MTF-ResNet showed better average accuracy compared with several widely used diagnostic methods.

An Intelligent Process Fault Diagnosis System based on Andrews Plot and Convolutional Neural Network

This paper proposes an intelligent process fault diagnosis system based on the techniques of Andrews plot and convolutional neural network. The proposed fault diagnosis method extracts features from the on-line process measurements using Andrews function. To address the uncertainty of setting the proper dimension of extracted features in Andrews function, a convolutional neural network is used to further extract diagnostic information from the Andrews function outputs. The outputs of the convolutional neural network are then fed to a single hidden layer neural network to obtain the final fault diagnosis result. The proposed fault diagnosis system is compared with a conventional neural network based fault diagnosis system. Applications to a simulated CSTR process show that the proposed fault diagnosis system gives much better performance than the conventional neural network based fault diagnosis system. It reveals that the use of Andrews function and convolutional neural network can improve the diagnosis performance.

Functional Safety Analysis and Design of Sensors in Robot Joint Drive System

The reliable operation of the sensors of robot joint drive systems (RJDs) is a key factor in ensuring the safety of equipment and personnel. Over the years, additional safety-related systems have been designed to prevent safety incidents caused by robot failures, ignoring the functional safety issues of the robot sensors themselves. In view of this, based on IEC61508, a functional safety analysis and design method for sensors of RJDs is proposed in this paper. Firstly, the hazard analysis and risk assessment clarified the goals that the safety protection function of the RJD’s sensor should achieve. Then, by establishing the motor drive model and transmission model, a model-based sensor fault diagnosis and isolation strategy is proposed. Considering the fault-tolerant operation of system, a fail-operational hardware architecture of the safety-related system is designed. Markov analysis shows that the safety integrity level (SIL) of safety-related systems can reach SIL3. Finally, experiments are designed to validate the proposed fault diagnosis and fault tolerance strategy. The results show that the safety-related system can effectively locate sensor failures, realize fault-tolerant control when a single sensor fails and perform safe torque off (STO) protection when multiple sensors fail.

Active Fault-Tolerant Control for Near-Space Hypersonic Vehicles

Due to the harsh working environment, Near-Space Hypersonic Vehicles (NSHVs) have the characteristics of frequent faults, which seriously affect flight safety. However, most researches focus on active fault-tolerant control for actuator faults. In order to fill the gap of active fault-tolerant control for sensor faults, this paper presents an Active Fault-Tolerant Control (AFTC) strategy for NSHVs based on Active Disturbance Rejection Control (ADRC) combined with fault diagnosis and evaluation. With the proposed AFTC strategy, both sensor faults and actuator faults can be compensated within 0.5 s. Wavelet packet decomposition and Kernel Extreme Learning Machine (KELM) are associated to ensure the high accuracy and real-time ability of fault diagnosis. Simulation results show that the proposed fault diagnosis method can significantly reduce the divergence of diagnosis results by up to 98%. The fault information is used to generate tolerant compensation, which is combined with the ADRC to achieve AFTC. Statistical results indicate that AFTC has significantly lower static error than ADRC. The proposed AFTC method endows NSHVs with the ability to complete missions even when various types of faults appear. Its advantages are demonstrated in comparison with other fault diagnosis and tolerant control methods.

A Fault Diagnosis System for a Pipeline Robot Based on Sound Signal Recognition.

Timely and accurate identification of fault types at the early stage of minor faults is significant for cutting off fault evolution. In order to have a clear understanding of the pipeline robot’s own situation in the pipeline, this paper proposes a fault diagnosis system for pipeline robots based on sound signal recognition. This can effectively reduce the probability of serious faults such as shutdown and loss of control in the pipeline without affecting the safe operation of the pipeline robot, which is a key issue to improve the reliability of the pipeline robot. The system consists of a combination of three parts: hardware, software, and algorithm. On the one hand, Raspberry Pi is the core module, while on the other hand, it is also responsible for the data transmission between the various modules, including storing the original sound signals collected by the sensors and transmitting the diagnosis results to the upper computer software interface. The proposed system is validated on the dataset collected by the data experimentation platform. The experimental results show that the proposed fault prediction method obtains advanced results on this dataset, verifying the effectiveness and stability of the proposed fault diagnosis system for pipeline robots based on sound signal recognition.

Open Circuit Fault Diagnosis in Five-Level Cascaded H-Bridge Inverter

The development of power electronic converter, especially multilevel converter, is remarkable for several decades. The complex switching and increased power of semiconductor devices are prime reasons for faults in multilevel inverters and have raised question about reliability. To improve the reliability, a cost-effective solution in terms of fault diagnosis is essential. In this context, this study proposed an open circuit fault (OCF) diagnosis technique for a switching device in a five-level cascaded H-bridge multilevel inverter using fuzzy logic control. The OCF features like output voltage total harmonic distortion (THD) and normalized average output voltage are fuzzed as input variables of the fuzzy logic controller. These input variables are divided into various triangular antecedent membership function (MF). The output produced by the fuzzy controller as consequent MFs is divided into different levels to identify the faulty switch. In order to make a complete fault-tolerant structure, a reduced modulation index-based postfault control is suggested to get a balanced output voltage. The MATLAB/Simulink results and prototype results are the evidence to support the proposed fault diagnosis technique.

Fault Diagnosis Method of Six-Phase Permanent Magnet Synchronous Motor Based on Vector Space Decoupling

Compared with the three-phase motor, the six-phase motor has lower torque ripple and higher fault tolerance performance, which makes it widely used in aviation, ships, industrial manufacturing, and other application fields. However, the probability of failure of the polyphase motor system increases with the increase in the number of phases. In order to deal with the open phase fault and power switch fault of the six-phase inverter, a fault diagnosis method for the six-phase inverter based on vector space decoupling (VSD) is proposed. The open phase fault index is first determined according to the VSD decoupling inverse transform and the current constraints. The fault index is then optimized from the perspective of preventing misdiagnosis and improving reliability, and the open phase fault can be diagnosed in one fundamental cycle. In addition, the current trajectory of harmonic plane after switch fault is analyzed, and the back propagation (BP) neural network is used to identify the harmonic plane current trajectory of different types of switch fault. Finally, the correctness and feasibility of the proposed fault diagnosis method are verified by simulations and experiments. The obtained results demonstrate that the proposed method can quickly and accurately locate the open phase fault and switch fault without additional hardware. The proposed method is simple, efficient, and robust.

Fault Diagnosis Method for Rolling Bearing Based on Sparse Principal Subspace Discriminant Analysis

Rolling bearings are omnipresent parts in industrial fields. To comprehensively reflect the status of rolling bearing and improve the classification accuracy, fusion information is widely used in various studies, which may result in high dimensionality, redundancy information of dataset, and time consumption. Thus, it is of crucial significance in extracting optimal features from high-dimensional and redundant feature space for classification. In this study, a fault diagnosis of rolling bearings model based on sparse principal subspace discriminant analysis is proposed. It extracts sparse discrimination information, meanwhile preserving the main energy of original dataset, and the sparse regularization term and sparse error term constrained by l2,1-norm are introduced to improve the performance of feature extraction and the robustness to noise and outliers. The multi-domain feature space involved a time domain, frequency domain, and time-frequency domain is first derived from the original vibration signals. Then, the intrinsic geometric features extracted by sparse principal subspace discriminant analysis are fed into a support vector machine classifier to recognize different operating conditions of bearings. The experimental results demonstrated that the feasibility and effectiveness of the proposed fault diagnosis model based on a sparse principal subspace discriminant analysis algorithm can achieve higher recognition accuracy than fisher discriminant analysis and its extensions, and it is relatively insensitive to the impact of noise and outliers owing to the sparse property.

Intelligent fault diagnosis of photovoltaic array based on variable predictive models and I–V curves

Photovoltaic (PV) arrays are installed in outdoors and continuously exposed to harsh environmental conditions, which are susceptible to suffer from abnormal and various kinds of faults, reduce the efficiency of power conversion and the lifetime of PV modules, and even cause electric shock and fire. In recent years, many methods of machine learning and deep learning have been successfully applied in the field of fault diagnosis for PV array. However, these methods still exist some issues: neural network training requires a large number of data samples and is prone to overfitting and underfitting; network structure and hyperparameters are difficult to determine, mainly rely on extensive experiments; The kernel extreme learning machine (KELM) and support vector machine (SVM) require kernel functions and hyper parameter adjustment, and the selection of kernel functions and hyperparameter will directly affect the accuracy of fault diagnosis; To solve the above issues, an intelligent fault diagnosis method for PV array based on the variable predictive models and I–V curves is proposed. Firstly, the impact of different operating states on the I–V curve of PV array under standard test condition (STC) is analyzed. Then, the five-dimensional effective feature variables are extracted from the key points of the measured I-V curve as input of the fault diagnosis model. Since the output of the electrical characteristics of the PV array is affected by faults and environmental factors, the extracted feature variables are normalized to eliminate the influence of environmental factors. Finally, the normalized feature variables are used as the input of variable predictive model to identify the fault types of the PV array, which reduces the computational cost and avoids the problem that the kernel function and hyperparameter are difficult to determine. Moreover, the proposed method is verified by simulation and measured data and compared with other machine learning algorithms. The results indicate that the proposed fault diagnosis method has high accuracy and reliability.

Fault Diagnosis Method of Waterproof Valves in Engineering Mixing Machinery Based on a New Adaptive Feature Extraction Model

Due to the complex working medium of oil in construction engineering, the waterproof valve in mixing machinery can easily cause different degrees of failure. Moreover, under adverse working conditions and complicated noise backgrounds, it is very difficult to detect the fault of waterproof valves. Thus, a fault diagnosis method is proposed, especially for the fault detection of waterproof valves as a key component in the construction of mixing machinery. This fault diagnosis method is based on a new adaptive feature extraction model, with multi-path signals to the improved deep residual shrinkage network–stacked denoising convolutional autoencoder (named DRSN–SDCAE). Firstly, the noisy vibration signals collected by the two vibration sensors are preprocessed, and then transmitted to the parallel structure improved DRSN–SDCAE for adaptive denoising and feature extraction. Finally, these results are fused through the feature fusion strategy to realize the effective fault diagnosis of the waterproof valve. The effectiveness of this method was verified through theory and experiments. The experimental results show that the proposed fault diagnosis method based on the improved DRSN–SDCAE model can automatically and effectively extract fault features from noise for fault diagnosis without relying on signal processing technology and diagnosis experiences. When compared with other intelligent fault diagnosis methods, the features extracted from multi-path inputs were more comprehensive than those extracted from single-path inputs, and contained more complete features of hidden data, which significantly improved fault diagnosis accuracy based on these fault features. The contribution of this paper is to learn fault features autonomously in signals with strong and complex noise through a deep network structure, which extends the fault diagnosis method to the field of construction machinery to improve the safe operation and maintainability of engineering machinery.

A novel multivariate signal processing-based fault diagnosis approach of rotating machinery under various operating conditions

Compared with signals collected by the single sensor, the collected multivariate signals contain more information to reflect the state of mechanical equipment, which has a positive effect on fault diagnosis. However, different acquisition channels and various operating conditions interfere with the extraction of fault features of rotating machinery. To solve this problem, taking rolling bearings as an example in this paper, a novel method is adopted to alleviate these interferences and combined with an improved extreme learning machine (ELM) to achieve intelligent fault diagnosis of rolling bearings under various operating conditions. First, adaptive projection intrinsically transformed multivariate empirical mode decomposition is used to decompose multivariate signals and obtain intrinsic mode functions of each channel to construct feature matrices. Then, nuisance attribute projection (NAP) is employed to alleviate the interference components in the feature matrix, which are originated from different channels and operating conditions. Finally, vectors belonging to the processed feature matrix as samples are input into the proposed weighted extreme learning machine (WELM) for intelligent fault classification. The weighted matrix of the WELM can compress the dimension of the sample and extract sensitive features, and the effectiveness of the proposed fault diagnosis model via the above methods is verified by experiments. Furthermore, comparative experiments show that the proposed fault diagnosis model has higher accuracy than the model combined with NAP and traditional single-hidden layer feedforward neural network or ELM. Therefore, the proposed fault diagnosis model may potentially aid experts on fault diagnosis of rotating machinery under various operating conditions.