Neural Network Based Fault Diagnosis Research Articles

Neural network-based fault diagnosis and fault-tolerant control for nonlinear systems with output measurement noise

Neural network-based fault diagnosis and fault-tolerant control for nonlinear systems with output measurement noise

A graph neural network based fault diagnosis strategy for power communication networks

ABSTRACT The power communication network (PCN) is the backbone network of the power system. However, faulty nodes in the network may cause communication interruptions, seriously affecting the reliable operation of the power system. Therefore, accurate diagnosis of faulty nodes is crucial for timely detection, localization, and troubleshooting. Based on graph neural networks, we propose a Neighbour Selection and Merge Fault Diagnosis (NSMFD) strategy, which aims to identify faulty nodes capturing graph structure information and node feature information. First, we construct a graph representation of PCN, where nodes represent devices in the network and edges represent the connections between devices. Then, we use sampling and aggregation in node embedding to capture adjacent feature information of nodes, gradually fuse and update node representations through graph convolutional layers, which could be applied as the input layer of diagnostic process. Finally, we use softmax and cross entropy loss function to get a probabilistic representation and optimize it by backpropagation for prediction. We conduct experiments using real PCN datasets and compare it with other advanced diagnostic methods in terms of accuracy, false positive rate, and false negative rate. Compared with diagnostic methods, our method can accurately identify faulty nodes and achieve timely fault detection and recovery.

Back Propagation Neural Network-Based Fault Diagnosis and Fault Tolerant Control of Distributed Drive Electric Vehicles Based on Sliding Mode Control-Based Direct Yaw Moment Control

Distributed-drive vehicles utilize independent drive motors on the four-wheel hubs. The working conditions of the wheel-hub motors are so harsh that the motors are prone to failing under different driving conditions. This study addresses the impact of drive motor faults on vehicle performance, particularly on slippery roads where sudden faults can lead to accidents. A fault-tolerant control system integrating motor fault diagnosis and a direct yaw moment control (DYC) based fault-tolerant controller are proposed to ensure the stability of the vehicle during various motor faults. Due to the difficulty of identifying the parameters of the popular permanent magnet synchronous wheel hub motors (PMSMs), the system employs a model-free backpropagation neural network (BPNN)-based fault detector. Turn-to-turn short circuits, open-phase faults, and diamagnetic faults are considered in this research. The fault detector is trained offline and utilizes rotor speed and phase currents for online fault detection. The system assigns the torque outputs from both healthy and faulted motors based on fault categories using sliding mode control (SMC)-based DYC. Simulations with four-wheel electric vehicle models demonstrate the accuracy of the fault detector and the effectiveness of the fault-tolerant controller. The proposed system is prospective and has potential for the development of distributed electric vehicles.

Early fault diagnosis strategy for high-speed train suspension systems based on model-agnostic meta-learning

Early fault diagnosis of suspension systems is essential for the safe operation of high-speed trains. However, neural network-based fault diagnosis methods have two remaining issues: the fault samples are difficult to obtain in practice and the early fault features are too weak to be extracted directly from the raw vibration signals using neural networks. A novel strategy is proposed for early faults diagnosis in suspension systems (i.e. component performance degradation within 20%) by integrating a new sample reconstruction method, a new grouping normalisation method, and model-agnostic meta-learning (MAML) algorithm. First, the 1D raw vibration signals are converted to 2D feature matrices consisting of artificial features using the sample reconstruction method; meanwhile, the grouping normalisation method is used to enhance the early weak fault features in the feature matrices. Second, MAML specialises in few-shot model training for early fault diagnosis, with the feature matrices as the training samples. Finally, the results are compared with those obtained using other current methods. The numerical results show that the proposed strategy yielded excellent performance in the few-shot early faults diagnosis of suspension systems, achieving a maximum accuracy of 94.75%.

Research on neural network-based fault diagnosis and prediction method for power communication equipment

Abstract In this paper, facing the digital development of the power grid and the status quo of massive power communication equipment access and targeting the demand for highly intelligent operation and maintenance management of the power grid, combined with neural network technology, we propose an intelligent diagnosis model of power communication equipment faults. Adopting BERT as the vector embedding layer to obtain the vector sequence of fault text, designing a fault entity recognition model for power communication equipment based on BERT-BiGRU-CRF, and completing the construction of the relationship set of fault text. The proposed knowledge graph-based power communication equipment fault intelligent diagnosis model combined with the WBLA-based power communication equipment fault severity level recognition algorithm to obtain different severity fault information, from which a TFIDF-COS-based power communication equipment fault intelligent diagnosis algorithm is designed to realize intelligent diagnosis of power communication equipment faults. After testing, the TFIDF-COS algorithm can get the best optimization effect when the number of hidden layers of the selected algorithm is 1, and the initial learning rate is 0.05, and its accuracy rate can be kept above 98%. Compared with the traditional fault diagnosis system, in terms of the order of magnitude 100M, 500M, 1G, and 5G, the running time is reduced by 322s, 1874s, 4617s, and 7467s, and the accuracy rate is increased by 2.33%, 2.6%, 32.02%, and 61.4%, respectively. Therefore, this paper realizes the accurate positioning of power communication equipment faults and provides technical support for intelligent operation and maintenance of the power grid.

Artificial Neural Network-Based Fault Diagnosis of Gearbox using Empirical Mode Decomposition from Vibration Response

This paper presents a gearbox defect diagnosis based on vibration behaviour. In order to record the vibration response under various circumstances, an industrial gearbox was used as the basis for an experimental setup. The signals resulting from gear wear were processed using an empirical mode decomposition for two operating time intervals (zero-hour running time and thirty-hour running time). The first three intrinsic mode functions and the corresponding frequency response were detected. The ten statistical parameters most sensitive to gear wear were selected using an evaluation method based on Euclidean distance. Using the identified features, an artificial neural network (ANN) was trained to track the gearbox for the selected future data set. The neural network received its input from the statistical parameters, and its output was the number of gearbox running hours. To achieve faster convergence, the radial basis function and the backpropagation neural network were compared. The superiority of the proposed strategy is demonstrated by comparing the performance of ANN. For monitoring the condition of industrial gears, the proposed strategy is found to be effective and trustworthy.

Multi-scale Transformer-CNN domain adaptation network for complex processes fault diagnosis

Despite the breakthroughs in deep neural network-based fault diagnosis, the model mismatch problem owing to the changes in data distribution remains challenging. To fuse deep features for cross-mode feature modeling, a Transformer-convolutional neural network (TrCNN) based multi-scale distribution alignment network is proposed. In the source domain stage, a concatenated structure of Transformer and convolutional neural network (CNN) extracts deep diagnostic information by combining global and local approaches. In the transfer stage, alignment is performed on the complex features extracted from different CNN substructures at multiple scales. Multi-scale feature alignment allows aligning information from various aspects while maintaining the discriminability of the data. The effectiveness and feasibility of the proposed method were demonstrated through experiments conducted on the Tennessee-Eastman (TE) process and industrial three-phase flow (TFF) equipment.

Attention gate guided multiscale recursive fusion strategy for deep neural network-based fault diagnosis

Rolling bearings are crucial for ensuring the safe and stable operation of electromechanical systems. Although deep learning has been widely used in fault diagnosis of rolling bearings, it is unable to accurately diagnose faults when the system operates under multiple working conditions. Therefore, it is essential to conduct research on fault diagnosis of rolling bearings under multiple working conditions to ensure the reliable operation of electromechanical systems. The potential features related to working conditions may be reflected in the different layers of the deep neural network (DNN). However, information loss during the process of layer-by-layer feature extraction may result in the loss of potential features related to changes in working conditions, which in turn affects the fault diagnosis results. This study focused on developing a multiscale recursive fusion strategy for a DNN by designing a new attention model with a lower computational burden. The proposed multiscale recursive fusion strategy guided by the attention mechanism can help correctly characterize the potential features related to variations in working conditions by allocating more attention to useful information and less attention to useless information on the adjacent layers of the DNN. Experimental tests for fault diagnosis of rolling bearings verified that the proposed method is superior to existing methods for fault diagnosis when the system is operated under multiple working conditions.

Interpretation and explanation of convolutional neural network-based fault diagnosis model at the feature-level for building energy systems

Interpretation and explanation of convolutional neural network-based fault diagnosis model at the feature-level for building energy systems

Rolling bearing fault diagnosis based on multi-scale weighted visibility graph and multi-channel graph convolution network

Current data-driven fault diagnosis methods are prone to overfitting and a decrease in accuracy when working with only a limited number of labeled samples. Additionally, existing graph neural network-based fault diagnosis methods often fail to comprehensively utilize both global and local features. To address these challenges, we propose a rolling bearing fault diagnosis method based on multi-scale weighted visibility graph and a multi-channel graph convolutional network (MCGCN). Our approach converts vibration signals into multiple weighted graphs from the perspective of geometric meaning and extracts local node feature information and global topology information of graphs using MCGCN. Experimental results demonstrate that our method achieves excellent performance under both sufficient and limited data conditions, providing a promising approach for real-world industrial bearing fault diagnosis.

A novel hierarchical training architecture for Siamese Neural Network based fault diagnosis method under small sample

Although current deep learning-based fault diagnosis methods have made great progress, the accuracy of these models is usually attained based on many balanced training samples, which is quite difficult to meet in real industrial scenarios. In this paper, a Siamese Neural Network (SNN) based fault diagnosis method under small sample conditions is proposed and a novel hierarchical training architecture is designed to train model efficiently. Through pre-training and secondary training of the feature extractor, the SNN training stagnation problem caused by input data is addressed, which fully exploits the deep features of small sample data. Then, a classifier is added to construct the final fault diagnosis network, which improves the diagnosis speed under large test samples, and realizes accurate and efficient fault diagnosis under small sample conditions. Finally, experiments using real rotating machinery datasets show the feasibility and accuracy of the proposed method under small sample.

Track and hunt metaheuristic based deep neural network based fault diagnosis model for the voltage source inverter under varying load conditions

Induction motors act as the pillars for industries and are preferable in various applications due to the characteristics of stability and sturdiness. The stability level should be efficiently maintained in order to monitor and analyze the faults that occur in three-phase Voltage Source Inverter. In this research, fault prediction occurs in the inverter under various load conditions is performed using the proposed track and hunt meta-heuristic-based deep neural network. The open circuit fault is generated in the three-phase voltage source inverter transistor under varying load conditions and is determined using the proposed track and hunt optimization. The proposed track and hunt meta-heuristic is developed by hybridizing the characteristics of hunting and tracking. After the data acquisition, the features are extracted from the collected faulty data in the form of three-phase current, voltage, torque, and speed. The Deep Neural Network classifier is trained using the obtained features and the faulty switches are identified through the average value of the three-phase current. The three-phase induction motor is connected as a load for the voltage source inverter with reference to the frequency variation. The prediction performance of track and hunt- deep learning classifier reveals that the percentage improvement of 10–15% is acquired for the developed method.

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.

Intelligent fault diagnosis framework of microgrid based on cloud–edge integration

This paper proposes an intelligent diagnosis framework of microgrid based on cloud–edge integration. First, the digital twin model of the microgrid is established on the cloud server. Based on the model, the operation data of the microgrid in various conditions can be obtained. Then, the neural network-based fault diagnosis model is trained on the cloud server by using the data provided by the digital twin model. Next, the trained neural network is downloaded to the edge device for the offline fault diagnosis of the microgrid. The proposed method is implemented based on the well-known digital twin platform CloudPSS and test results demonstrate the effectiveness. Extensive tests have been conducted on this framework using fully connected neural network algorithms with an accuracy rate of over 95%.

Neural network-based fault diagnosis for spacecraft with single-gimbal control moment gyros

This paper proposes a neural network-based fault diagnosis scheme to address the problem of fault isolation and estimation for the Single-Gimbal Control Moment Gyroscopes (SGCMGs) of spacecraft in a periodic orbit. To this end, a disturbance observer based on neural network is developed for active anti-disturbance, so as to improve the accuracy of fault diagnosis. The periodic disturbance on orbit can be decoupled with fault by resorting to the fitting and memory ability of neural network. Subsequently, the fault diagnosis scheme is established based on the idea of information fusion. The data of spacecraft attitude and gimbals position are combined to implement fault isolation and estimation based on adaptive estimator and neural network. Then, an adaptive sliding mode controller incorporating the disturbance and fault estimation results is designed to achieve active fault-tolerant control. In addition, the paper gives the proof of the stability of the proposed schemes, and the simulation results show that the proposed scheme achieves better diagnosis and control results than compared algorithm.

A multi-scale convolutional neural network based fault diagnosis model for complex chemical processes

The chemical production process is a special dynamic and complex system. It has the characteristics of instability and danger, thus making safety management in the production process very difficult. To support the long-term and stable operation of the chemical process, timely and accurate fault diagnosis is very necessary. Aiming at the high-dimensional nonlinearity of chemical process data, this paper proposes a fault diagnosis method in chemical process that is based on multi-scale convolutional neural network (MsCNN) combined with matrix diagram. This model uses software to convert the pre-processed time series signal data of the chemical process into sets of matrix diagrams, and then uses the MsCNN model to accurately diagnose various types of faults in the chemical production process. Taking Tennessee Eastman (TE) process fault data set as an example, verification shows good simulation results in detection accuracy and loss. This method can create high-precision judgments on fault types, which is beneficial to timely elimination of faults and avoidance of safety accidents. The results show that the new model proposed in this paper has good potential in the field of fault diagnosis in chemical processes, and is also reliable, practical and scientific.

Parallel multi-fusion convolutional neural networks based fault diagnosis of rotating machinery under noisy environments

Fault diagnosis has a great significance in preventing serious failures of rotating machinery and avoiding huge economic losses. The performance of the existing fault diagnosis approaches might be affected by two factors, i.e., the quality of fault features extracted from monitoring signals and the capability of fault diagnosis model. This paper proposes a new fault diagnosis method combined mel-frequency cepstral coefficients (MFCC) with a designed parallel multi-fusion convolutional neural network (MFCNN) Specifically, a MFCC-based feature extraction method is defined to reduce the noise components in monitoring signal of rotating machinery and extract more useful low-frequency fault information for downstream task. Furthermore, a novel MFCNN is designed to enrich the high-level features after each convolution operation by using multiple activation functions, so as to improve the quality of the obtained fault features. Meanwhile, a new parallel MFCNN is constructed by using a defined structural ensemble operation to improve its diagnostic performance in different noise environments. Two typical bearing and gearbox failure datasets are applied to evaluate the performance of the proposed fault diagnosis method. The experimental results indicate that the proposed parallel MFCNN has the better diagnostic performance than other methods.

A fault diagnosis model for proton exchange membrane fuel cell based on impedance identification with differential evolution algorithm

An effective online fault diagnosis system is of great significance to improve the reliability of fuel cell vehicles. In this paper, a fault diagnosis model for proton exchange membrane fuel cells is proposed. Firstly, the tests of electrochemical impedance spectroscopy under different fault types (flooding, drying, air starvation) and fault degrees (minor, moderate, severe) are carried out, and each polarization loss of the fuel cell is denoted by an equivalent circuit model (ECM). Then, the parameters of the ECM are identified by the proposed random mutation differential evolution algorithm. Furthermore, the parameters identified under different fault conditions are used to train and test a probabilistic neural network-based fault diagnosis model. The fault diagnosis model achieves diagnosis accuracies of 100% for the fault type and 96.67% for the fault degree. By setting operating conditions with different fault degrees, the fault diagnosis model proposed in this paper can realize the fault type and fault degree diagnosis, effectively avoiding the misjudgment of fault types, and is effective for improving the reliability of the fuel cell system.

Hierarchical fault-tolerant control for over-actuated hypersonic reentry vehicles

This paper proposes a performance-focused and deep learning-based hierarchical fault-tolerant control framework for over-actuated hypersonic reentry vehicles. The hierarchical fault tolerance mechanism refers to the fault tolerance that can be realized both in the control allocation and control layers. First, a long short-term memory neural network-based fault diagnosis unit is proposed to solve the difficult problem of diagnosing actuator fault information under multisource disturbances. Based on the diagnosed fault information, the robust least-squares control allocation method is deployed to distribute the desired control moment to the actuator and achieve fault tolerance in the control allocation layer. Then, combined with a fixed time extended state observer, an improved multiple-degree-of-freedom prescribed performance control method is used to compensate the lumped disturbances, including control allocation error, ensure the prescribed tracking performance, and realize fault tolerance in the control layer. Finally, the theoretical analysis proves the stability of the proposed hierarchical fault-tolerant control scheme, and the effectiveness is verified by numerical simulation.

An Intelligent Process Fault Diagnosis System Based on Neural Networks and Andrews Plot

This paper proposes a neural network-based process fault diagnosis system with Andrews plot for information pre-processing to enhance the performance of online process fault diagnosis. By using features extracted from Andrews plot as the inputs to a neural network, as a classifier, the diagnosis speed and reliability are improved. A method for determining the important features in the Andrews function is proposed. The proposed fault diagnosis system is applied to a simulated continuous stirred tank reactor process and is compared with two conventional neural network-based fault diagnosis systems: scheme B where the monitored measurements are directly fed to a neural network after scaling and scheme C where the monitored measurements are converted to qualitative trend data before feeding to a neural network. Of all the considered faults, the proposed fault diagnosis system diagnosed the abrupt faults on average 5.45 s and 2.66 s earlier than schemes B and C, respectively and diagnosed the incipient faults on average 13.82 s and 5.09 s earlier than schemes B and C, respectively. The results reveal that Andrews plot method utilized in online process monitoring has a great potential in industrial process monitoring.