Wavelet Transform and Neural Networks in Fault Diagnosis of a Motor Rotor

In the motor fault diagnosis technique, vibration and stator current frequency components of detection are two main means. This article will discuss the signal detection method based on vibration fault. Because the motor vibration signal is a non-stationary random signal, fault signals often contain a lot of time-varying, burst proper- ties of ingredients. The traditional Fourier signal analysis can not effectively extract the motor fault characteristics, but are also likely to be rich in failure information but a weak signal as noise. Therefore, we introduce wavelet packet transforms to extract the fault characteristics of the signal information. Obtained was the result as the neural network input signal, using the L-M neural network optimization method for training, and then used the BP net- work for fault recognition. This paper uses Matlab software to simulate and confirmed the method of motor fault di- agnosis validity and accuracy

Connected Components-based Colour Image Representations of Vibrations for a Two-stage Fault Diagnosis of Roller Bearings Using Convolutional Neural Networks

Roller bearing failure is one of the most common faults in rotating machines.Various techniques for bearing fault diagnosis based on faults feature extraction have been proposed.But feature extraction from fault signals requires expert prior information and human labour.Recently,deep learning algorithms have been applied extensively in the condition monitoring of rotating machines to learn features automatically from the input data.Given its robust performance in image recognition,the convolutional neural network(CNN)architecture has been widely used to learn automatically discriminative features from vibration images and classify health conditions.This paper proposes and evaluates a two-stage method RGBVI-CNN for roller bearings fault diagnosis.The first stage in the proposed method is to generate the RGB vibration images(RGBVIs)from the input vibration signals.To begin this process,first,the 1-D vibration signals were converted to 2-D grayscale vibration Images.Once the conversion was completed,the regions of interest(ROI)were found in the converted 2-D grayscale vibration images.Finally,to produce vibration images with more discriminative characteristics,an algorithm was applied to the 2-D grayscale vibration images to produce connected components-based RGB vibration images(RGBVIs)with sets of colours and texture features.In the second stage,with these RGBVIs a CNN-based architecture was employed to learn automatically features from the RGBVIs and to classify bearing health conditions.Two cases of fault classification of rolling element bearings are used to validate the proposed method.Experimental results of this investigation demonstrate that RGBVI-CNN can generate advantageous health condition features from bearing vibration signals and classify the health conditions under different working loads with high accuracy.Moreover,several classification models trained using RGBVI-CNN offered high performance in the testing results of the overall classification accuracy,precision,recall,and F-score.

An Interpretable Denoising Layer for Neural Networks Based on Reproducing Kernel Hilbert Space and its Application in Machine Fault Diagnosis

Deep learning algorithms based on neural networks make remarkable achievements in machine fault diagnosis,while the noise mixed in measured signals harms the prediction accuracy of networks.Existing denoising methods in neural networks,such as using complex network architectures and introducing sparse techniques,always suffer from the difficulty of estimating hyperparameters and the lack of physical interpretability.To address this issue,this paper proposes a novel interpretable denoising layer based on reproducing kernel Hilbert space(RKHS)as the first layer for standard neural networks,with the aim to combine the advantages of both traditional signal processing technology with physical interpretation and network modeling strategy with parameter adaption.By investigating the influencing mechanism of parameters on the regularization procedure in RKHS,the key parameter that dynamically controls the signal smoothness with low computational cost is selected as the only trainable parameter of the proposed layer.Besides,the forward and backward propagation algorithms of the designed layer are formulated to ensure that the selected parameter can be automatically updated together with other parameters in the neural network.Moreover,exponential and piecewise functions are introduced in the weight updating process to keep the trainable weight within a reasonable range and avoid the ill-conditioned problem.Experiment studies verify the effectiveness and compatibility of the proposed layer design method in intelligent fault diagnosis of machinery in noisy environments.

A Study on Integrated Wavelet Neural Networks in Fault Diagnosis Based on Information Fusion

The tight wavelet neural network was constituted by taking the nonlinear Morlet wavelet radices as the excitation function. The idiographic algorithm was presented. It combined the advantages of wavelet analysis and neural networks. The integrated wavelet neural network fault diagnosis system was set up based on both the information fusion technology and actual fault diagnosis, which took the sub-wavelet neural network as primary diagnosis from different sides, then came to the conclusions through decision-making fusion. The realizable policy of the diagnosis system and established principle of the sub-wavelet neural networks were given. It can be deduced from the examples that it takes full advantage of diversified characteristic information, and improves the diagnosis rate.

Bearings Intelligent Fault Diagnosis by 1-D Adder Neural Networks

Integrated with sensors,processors,and radio frequency(RF)communication modules,intelligent bearing could achieve the autonomous perception and autonomous decision-making,guarantying the safety and reliability during their use.However,because of the resource limitations of the end device,processors in the intelligent bearing are unable to carry the computational load of deep learning models like convolutional neural network(CNN),which involves a great amount of multiplicative operations.To minimize the computation cost of the conventional CNN,based on the idea of AdderNet,a 1-D adder neural network with a wide first-layer kernel(WAddNN)suitable for bearing fault diagnosis is proposed in this paper.The proposed method uses the l1-norm distance between filters and input features as the output response,thus making the whole network almost free of multiplicative operations.The whole model takes the original signal as the input,uses a wide kernel in the first adder layer to extract features and suppress the high frequency noise,and then uses two layers of small kernels for nonlinear mapping.Through experimental comparison with CNN models of the same structure,WAddNN is able to achieve a similar accuracy as CNN models with significantly reduced computational cost.The proposed model provides a new fault diagnosis method for intelligent bearings with limited resources.

ENGINE SENSOR FAULT DIAGNOSIS USING MAIN AND DECENTRALIZED NEURAL NETWORKS

This Paper presents a methodology for solving the sensor failure detection, isolation and accommodation of aeroengine control systems using on line learning neural networks(NN), which has one main NN and a set of decentralized NNs. Changes in the system dynamics are monitored by the on line learning NN. When a failure occurs in some sensor, the sensor failure detection can be accomplished with high precision, and the sensor failure accommodation can be achieved by replacing the value from the failed sensor with its estimate from the decentralized NN. By integrating the optimal estimation and failure logic, this method can detect soft failures. Simulation of one kind of turboshaft engine control system with this multiple neural network architecture shows that the ANN developed can detect and isolate hard and soft sensor failures timely and provide accurate accommodation.

Reconstruction based approach to sensor fault diagnosis using auto-associative neural networks

Fault diagnostics is an important research area including different techniques.Principal component analysis(PCA)is a linear technique which has been widely used.For nonlinear processes,however,the nonlinear principal component analysis(NLPCA)should be applied.In this work,NLPCA based on auto-associative neural network(AANN)was applied to model a chemical process using historical data.First,the residuals generated by the AANN were used for fault detection and then a reconstruction based approach called enhanced AANN(E-AANN)was presented to isolate and reconstruct the faulty sensor simultaneously.The proposed method was implemented on a continuous stirred tank heater(CSTH)and used to detect and isolate two types of faults(drift and offset)for a sensor.The results show that the proposed method can detect,isolate and reconstruct the occurred fault properly.

Research on Rotating Machinery Fault Diagnosis Based on Improved Multi-target Domain Adversarial Network

Aiming at the problems of low efficiency,poor anti-noise and robustness of transfer learning model in intelligent fault diagnosis of rotating machinery,a new method of intelligent fault diagnosis of rotating machinery based on single source and multi-target domain adversarial network model(WDMACN)and Gram Angle Product field(GAPF)was proposed.Firstly,the original one-dimensional vibration signal is preprocessed using GAPF to generate the image data including all time series.Secondly,the residual network is used to extract data features,and the features of the target domain without labels are pseudo-labeled,and the transferable features among the feature extractors are shared through the depth parameter,and the feature extractors of the multi-target domain are updated anatomically to generate the features that the discriminator cannot distinguish.The modelt through adversarial domain adaptation,thus achieving fault classification.Finally,a large number of validations were carried out on the bearing data set of Case Western Reserve University(CWRU)and the gear data.The results show that the proposed method can greatly improve the diagnostic efficiency of the model,and has good noise resistance and generalization.

Wear Fault Diagnosis of Machinery Based on Neural Networks and Gray Relationships

In this paper, the regular characteristic of -wear particles related to fault type of machines based on condition monitoring of reciprocal machinery is discussed. The typical -wear particles spectrum is established according to the equipment structure , friction and wear rule and the characteristic of 'wear particles; The identification technology of wear particles is proposed based on neural networks and a gray relationship ; an intelligent wear particles identification system is designed. The diagnosis example shows that this system can promote the accuracy and the speed of wear particles identification.

Fault Diagnosis of 5G Networks Based on Digital Twin Model

Fault diagnosis of 5G networks faces the challenges of heavy reliance on human experience and insufficient fault samples and relevant monitoring data.The digital twin technology can realize the interaction between virtual space and physical space through the fusion of model and data,providing a new paradigm for fault diagnosis.In this paper,we first propose a network digital twin model and apply it to 5G network diagnosis.We then use an improved Average Wasserstein GAN with Gradient Penalty(AWGAN-GP)method to discover and predict failures in the twin network.Finally,we use XGBoost algorithm to locate the faults in physical network in real time.Extensive simulation results show that the proposed approach can significantly increase fault prediction and diagnosis accuracy in the case of a small number of labeled failure samples in 5G networks.

Attention-based long short-term memory fully convolutional network for chemical process fault diagnosis

A correct and timely fault diagnosis is important for improving the safety and reliability of chemical processes. With the advancement of big data technology, data-driven fault diagnosis methods are being extensively used and still have considerable potential. In recent years, methods based on deep neural networks have made significant breakthroughs, and fault diagnosis methods for industrial processes based on deep learning have attracted considerable research attention. Therefore, we propose a fusion deeplearning algorithm based on a fully convolutional neural network(FCN) to extract features and build models to correctly diagnose all types of faults. We use long short-term memory(LSTM) units to expand our proposed FCN so that our proposed deep learning model can better extract the time-domain features of chemical process data. We also introduce the attention mechanism into the model, aimed at highlighting the importance of features, which is significant for the fault diagnosis of chemical processes with many features. When applied to the benchmark Tennessee Eastman process, our proposed model exhibits impressive performance, demonstrating the effectiveness of the attention-based LSTM FCN in chemical process fault diagnosis.

Multifault diagnosis in WSN using a hybrid metaheuristic trained neural network

Wireless sensor networks are susceptible to failures of nodes and links due to various physical or computational reasons.Some physical reasons include a very high temperature,a heavy load over a node,and heavy rain.Computational reasons could be a third-party intrusive attack,communication conflicts,or congestion.Automated fault diagnosis has been a well-studied problem in the research community.In this paper,we present an automated fault diagnosis model that can diagnose multiple types of faults in the category of hard faults and soft faults.Our proposed model implements a feed-forward neural network trained with a hybrid metaheuristic algorithm that combines the principles of exploration and exploitation of the search space.The proposed methodology consists of different phases,such as a clustering phase,a fault detection and classification phase,and a decision and diagnosis phase.The implemented methodology can diagnose composite faults,such as hard permanent,soft permanent,intermittent,and transient faults for sensor nodes as well as for links.The proposed implementation can also classify different types of faulty behavior for both sensor nodes and links in the network.We present the obtained theoretical results and computational complexity of the implemented model for this particular study on automated fault diagnosis.The performance of the model is evaluated using simulations and experiments conducted using indoor and outdoor testbeds.

Adaptive multiscale convolutional neural network model for chemical process fault diagnosis

Intelligent fault recognition techniques are essential to ensure the long-term reliability of manufacturing.Due to the variations in material,equipment and environment,the process variables monitored by sensors contain diverse data characteristics at different time scales or in multiple operating modes.Despite much progress in statistical learning and deep learning for fault recognition,most models are constrained by abundant diagnostic expertise,inefficient multiscale feature extraction and unruly multimode condition.To overcome the above issues,a novel fault diagnosis model called adaptive multiscale convolutional neural network(AMCNN)is developed in this paper.A new multiscale convolutional learning structure is designed to automatically mine multiple-scale features from time-series data,embedding the adaptive attention module to adjust the selection of relevant fault pattern information.The triplet loss optimization is adopted to increase the discrimination capability of the model under the multimode condition.The benchmarks CSTR simulation and Tennessee Eastman process are utilized to verify and illustrate the feasibility and efficiency of the proposed method.Compared with other common models,AMCNN shows its outstanding fault diagnosis performance and great generalization ability.

Fault detection and diagnosis of permanent-magnetic DC motors based on current analysis and BP neural networks

In order to guarantee quality during mass serial production of motors, a convenient approach on how to detect and diagnose the faults of a permanent-magnetic DC motor based on armature current analysis and BP neural networks was presented in this paper. The fault feature vector was directly established by analyzing the armature current. Fault features were extracted from the current using various signal processing methods including Fourier analysis, wavelet analysis and statistical methods. Then an advanced BP neural network was used to finish decision-making and separate fault patterns. Finally, the accuracy of the method in this paper was verified by analyzing the mechanism of faults theoretically. The consistency between the experimental results and the theoretical analysis shows that four kinds of representative faults of low power permanent-magnetic DC motors can be diagnosed conveniently by this method. These four faults are brush fray, open circuit of components, open weld of components and short circuit between armature coils. This method needs fewer hardware instruments than the conventional method and whole procedures can be accomplished by several software packages developed in this paper.

Fault Diagnosis of Power Electronic Circuits Based on Adaptive Simulated Annealing Particle Swarm Optimization

In the field of energy conversion,the increasing attention on power electronic equipment is fault detection and diagnosis.A power electronic circuit is an essential part of a power electronic system.The state of its internal components affects the performance of the system.The stability and reliability of an energy system can be improved by studying the fault diagnosis of power electronic circuits.Therefore,an algorithm based on adaptive simulated annealing particle swarm optimization(ASAPSO)was used in the present study to optimize a backpropagation(BP)neural network employed for the online fault diagnosis of a power electronic circuit.We built a circuit simulation model in MATLAB to obtain its DC output voltage.Using Fourier analysis,we extracted fault features.These were normalized as training samples and input to an unoptimized BP neural network and BP neural networks optimized by particle swarm optimization(PSO)and the ASAPSO algorithm.The accuracy of fault diagnosis was compared for the three networks.The simulation results demonstrate that a BP neural network optimized with the ASAPSO algorithm has higher fault diagnosis accuracy,better reliability,and adaptability and can more effectively diagnose and locate faults in power electronic circuits.

Feature evaluation and extraction based on neural network in analog circuit fault diagnosis

Choosing the right characteristic parameter is the key to fault diagnosis in analog circuit. The feature evaluation and extraction methods based on neural network are presented. Parameter evaluation of circuit features is realized by training results from neural network; the superior nonlinear mapping capability is competent for extracting fault features which are normalized and compressed subsequently. The complex classification problem on fault pattern recognition in analog circuit is transferred into feature processing stage by feature extraction based on neural network effectively, which improves the diagnosis efficiency. A fault diagnosis illustration validated this method.

Intelligent Fault Diagnosis for Planetary Gearbox Using Transferable Deep Q Network Under Variable Conditions with Small Training Data

Effective fault diagnosis of planetary gearboxes is critical for ensuring the safety and dependability of mechanical drive systems.Nevertheless,variable conditions and inadequate fault data bring huge challenges to its practical fault diagnosis.Taking this into account,this study presents a new intelligent fault diagnosis(IFD)approach for planetary gearbox using a transferable deep Q network(TDQN)that merges deep reinforcement learning(DRL)and transfer learning(TL).First,a DRL environment simulation is designed by a predefined classification Markov decision process.Then,leveraging varied-size convolutions and residual learning,a multiscale residual convolutional neural network agent for TDQN is created to automatically learn meaningful features directly from vibration signals while avoiding model degradation.Next,a large source dataset is obtained from complex conditions,and this agent learns an IFD policy via autonomous interaction with the data environment.Finally,a parameter-based TL strategy is adopted to retrain the model on target datasets with variable conditions and small training data,which is conducted by fine-tuning the model parameters gained from the source task to accomplish target tasks.The results show that this TDQN outperforms not only state-of-the-art methods in a source task with an accuracy of 98.53%but also in two target tasks with 99.63%and 98.37%,respectively.

Fault Diagnosis for Manifold Absolute Pressure Sensor(MAP) of Diesel Engine Based on Elman Neural Network Observer

Intake system of diesel engine is a strong nonlinear system, and it is difficult to establish accurate model of intake system; and bias fault and precision degradation fault of MAP of diesel engine can＇t be diagnosed easily using model-based methods. Thus, a fault diagnosis method based on Elman neural network observer is proposed. By comparing simulation results of intake pressure based on BP network and Elman neural network, lower sampling error magnitude is gained using Elman neural network, and the error is less volatile. Forecast accuracy is between 0.015？0.017 5 and sample error is controlled within 0？0.07. Considering the output stability and complexity of solving comprehensively, Elman neural network with a single hidden layer and with 44 nodes is presented as intake system observer. By comparing the relations of confidence intervals of the residual value between the measured and predicted values, error variance and failures in various fault types. Then four typical MAP faults of diesel engine can be diagnosed： complete failure fault, bias fault, precision degradation fault and drift fault. The simulation results show： intake pressure is observable and selection of diagnostic strategy parameter reasonably can increase the accuracy of diagnosis;the proposed fault diagnosis method only depends on data and structural parameters of observer, not depends on the nonlinear model of air intake system. A fault diagnosis method is proposed not depending system model to observe intake pressure, and bias fault and precision degradation fault of MAP of diesel engine can be diagnosed based on residuals.

FAULT DIAGNOSIS OF ROTATING MACHINERY USING KNOWLEDGE-BASED FUZZY NEURAL NETWORK

A novel knowledge-based fuzzy neural network （KBFNN） for fault diagnosis is presented. Crude rules were extracted and the corresponding dependent factors and antecedent coverage factors were calculated firstly from the diagnostic sample based on rough sets theory. Then the number of rules was used to construct partially the structure of a fuzzy neural network and those factors were implemented as initial weights, with fuzzy output parameters being optimized by genetic algorithm. Such fuzzy neural network was called KBFNN. This KBFNN was utilized to identify typical faults of rotating machinery. Diagnostic results show that it has those merits of shorter training time and higher right diagnostic level compared to general fuzzy neural networks.

Employing adaptive fuzzy computing for RCP intelligent control and fault diagnosis

Loss of coolant accident(LOCA),loss of fluid accident(LOFA),and loss of vacuum accident(LOVA)are the most severe accidents that can occur in nuclear power reactors(NPRs).These accidents occur when the reactor loses its cooling media,leading to uncontrolled chain reactions akin to a nuclear bomb.This article is focused on exploring methods to prevent such accidents and ensure that the reactor cooling system remains fully controlled.The reactor coolant pump(RCP)has a pivotal role in facilitating heat exchange between the primary cycle,which is connected to the reactor core,and the secondary cycle associated with the steam generator.Furthermore,the RCP is integral to preventing catastrophic events such as LOCA,LOFA,and LOVA accidents.In this study,we discuss the most critical aspects related to the RCP,specifically focusing on RCP control and RCP fault diagnosis.The AI-based adaptive fuzzy method is used to regulate the RCP’s speed and torque,whereas the neural fault diagnosis system(NFDS)is implemented for alarm signaling and fault diagnosis in nuclear reactors.To address the limitations of linguistic and statistical intelligence approaches,an integration of the statistical approach with fuzzy logic has been proposed.This integrated system leverages the strengths of both methods.Adaptive fuzzy control was applied to the VVER 1200 NPR-RCP induction motor,and the NFDS was implemented on the Kori-2 NPR-RCP.