SIMULATION INVESTIGATION OF AEROENGINE FAULT DIAGNOSIS USING NEURAL NETWORKS

Traditional scheduled maintenance systems are costly, labor intensive, and typically provide noncomprehensive detection and diagnosis of engine faults. The engine monitoring system (EMS) on modern aircrafts has the potential to provide maintenance personnel with valuable information for detecting and diagnosing engine faults. In this paper, an RBF neural network approach is applied to aeroengine gas path fault diagnosis. It can detect multiple faults and quantify the amount of deterioration of the various engine components as a function of measured parameters. The results obtained demonstrate that the accuracy of diagnosis is consistent with practical requirements. The approach takes advantage of the nonlinear mapping feature of neural networks to capture the appropriate characteristics of an aeroengine. The methodology is generic and applicable to other similar plants having high complexity.

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.

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.

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.

Deep Learning Based Data Fusion for Sensor Fault Diagnosis and Tolerance in Autonomous Vehicles

Environmental perception is one of the key technologies to realize autonomous vehicles.Autonomous vehicles are often equipped with multiple sensors to form a multi-source environmental perception system.Those sensors are very sensitive to light or background conditions,which will introduce a variety of global and local fault signals that bring great safety risks to autonomous driving system during long-term running.In this paper,a real-time data fusion network with fault diagnosis and fault tolerance mechanism is designed.By introducing prior features to realize the lightweight network,the features of the input data can be extracted in real time.A new sensor reliability evaluation method is proposed by calculating the global and local confidence of sensors.Through the temporal and spatial correlation between sensor data,the sensor redundancy is utilized to diagnose the local and global confidence level of sensor data in real time,eliminate the fault data,and ensure the accuracy and reliability of data fusion.Experiments show that the network achieves state-of-the-art results in speed and accuracy,and can accurately detect the location of the target when some sensors are out of focus or out of order.The fusion framework proposed in this paper is proved to be effective for intelligent vehicles in terms of real-time performance and reliability.

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.

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

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.

Application of data fusion method to fault diagnosis of nuclear power plant

The work condition of nuclear power plant (NPP) is very bad, which makes ithas faults easily. In order to diagnose (he faults real time, the fusion diagnosis system is built.The data fusion fault diagnosis system adopts data fusion method and divides the fault diagnosisinto three levels, which are data fusion level, feature level and decision level. The feature leveluses three parallel neural networks whose structures are the same. The purpose of using neuralnetworks is mainly to get basic probability assignment ( BPA) of D-S evidence theory, and the neuralnetworks in feature level are used for local diagnosis. D-S evidence theory is adopted to integratethe local diagnosis results in decision level. The reactor coolant system is the study object andwe choose 2# steam generator U-tubes break of the reactor coolant system as a diagnostic example.The experiments prove that the fusion diagnosis system can satisfy the fault diagnosis requirementof complicated system, and verify that the fusion fault diagnosis system can realize the faultdiagnosis of NPP on line timely.

APPLICATION OF MULTI-SENSOR DATA FUSION BASED ON FUZZY NEURAL NETWORK IN ROTA TING MECHANICAL FAILURE DIAGNOSIS

At present, multi-se nsor fusion is widely used in object recognition and classification, since this technique can efficiently improve the accuracy and the ability of fault toleranc e. This paper describes a multi-sensor fusion system, which is model-based and used for rotating mechanical failure diagnosis. In the data fusion process, the fuzzy neural network is selected and used for the data fusion at report level. By comparing the experimental results of fault diagnoses based on fusion data wi th that on original separate data,it is shown that the former is more accurate than the latter.

Data Fusion Fault Diagnosis Based on Wavelet Transform and Neural Network

According to the time-frequency localization characteristic of the wavelet transform (WT)and the nonlinear reflection of the neural network,this paper presents the neural network data fusion fault diagnosis method based on wavelet transform.The network construction and the signal processing steps are introduced in detail.The correct result was attained by using this method in rotary machinery fault diagnosis.It proves the method efficient in fault diagnosis, which is expected to have a wide application.

Fault Detection and Diagnosis of a Gearbox in Marine Propulsion Systems Using Bispectrum Analysis and Artificial Neural Networks

A marine propulsion system is a very complicated system composed of many mechanical components.As a result,the vibration signal of a gearbox in the system is strongly coupled with the vibration signatures of other components including a diesel engine and main shaft.It is therefore imperative to assess the coupling effect on diagnostic reliability in the process of gear fault diagnosis.For this reason,a fault detection and diagnosis method based on bispectrum analysis and artificial neural networks (ANNs) was proposed for the gearbox with consideration given to the impact of the other components in marine propulsion systems.To monitor the gear conditions,the bispectrum analysis was first employed to detect gear faults.The amplitude-frequency plots containing gear characteristic signals were then attained based on the bispectrum technique,which could be regarded as an index actualizing forepart gear faults diagnosis.Both the back propagation neural network (BPNN) and the radial-basis function neural network (RBFNN) were applied to identify the states of the gearbox.The numeric and experimental test results show the bispectral patterns of varying gear fault severities are different so that distinct fault features of the vibrant signal of a marine gearbox can be extracted effectively using the bispectrum,and the ANN classification method has achieved high detection accuracy.Hence,the proposed diagnostic techniques have the capability of diagnosing marine gear faults in the earlier phases,and thus have application importance.

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.

Bearing fault diagnosis based on a multiple-constraint modal-invariant graph convolutional fusion network

Multisensor data fusionmethod can improve the accuracy of bearing fault diagnosis,in order to address the problems of single-sensor data types and the insufficient exploration of redundancy and complementarity between different modal data in most existing multisensor data fusion methods for bearing fault diagnosis,a bearing fault diagnosis method based on a Multiple-Constraint Modal-Invariant Graph Convolutional Fusion Network(MCMI-GCFN)is proposed in this paper.Firstly,a Convolutional Autoencoder(CAE)and Squeeze-and-Excitation Block(SE block)are used to extract features of raw current and vibration signals.Secondly,the model introduces source domain classifiers and domain discriminators to capture modal invariance between different modal data based on domain adversarial training,making use of the redundancy and complementarity between multimodal data.Then,the spatial aggregation property of Graph Convolutional Neural Networks(GCN)is utilized to capture the dependency relationship between current and vibration modes with similar time step features for accurately fusing contextual semantic information.Finally,the validation is conducted on the public bearing damage current and vibration dataset from Paderborn University.The experimental results showed that the delivered fusion method achieved a bearing fault diagnosis accuracy of 99.6%,which was about 9%–11.4%better than that with nonfusion methods.

Data fusion for fault diagnosis using multi-class Support Vector Machines

Multi-source multi-class classification methods based on multi-class Support Vector Machines and data fusion strategies are proposed in this paper. The centralized and distributed fusion schemes are applied to combine information from several data sources. In the centralized scheme, all information from several data sources is centralized to construct an input space. Then a multi-class Support Vector Machine classifier is trained. In the distributed schemes, the individual data sources are proc-essed separately and modelled by using the multi-class Support Vector Machine. Then new data fusion strategies are proposed to combine the information from the individual multi-class Support Vector Machine models. Our proposed fusion strategies take into account that an Support Vector Machine (SVM) classifier achieves classification by finding the optimal classification hyperplane with maximal margin. The proposed methods are applied for fault diagnosis of a diesel engine. The experimental results showed that almost all the proposed approaches can largely improve the diagnostic accuracy. The robustness of diagnosis is also improved because of the implementation of data fusion strategies. The proposed methods can also be applied in other fields.

Fault diagnosis method of hydraulic system based on fusion of neural network and D-S evidence theory

According to fault type diversity and fault information uncertainty problem of the hydraulic driven rocket launcher servo system（HDRLSS） , the fault diagnosis method based on the evidence theory and neural network ensemble is proposed. In order to overcome the shortcomings of the single neural network, two improved neural network models are set up at the com-mon nodes to simplify the network structure. The initial fault diagnosis is based on the iron spectrum data and the pressure, flow and temperature（PFT） characteristic parameters as the input vectors of the two improved neural network models, and the diagnosis result is taken as the basic probability distribution of the evidence theory. Then the objectivity of assignment is real-ized. The initial diagnosis results of two improved neural networks are fused by D-S evidence theory. The experimental results show that this method can avoid the misdiagnosis of neural network recognition and improve the accuracy of the fault diagnosis of HDRLSS.

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.

Rough set and radial basis function neural network based insulation data mining fault diagnosis for power transformer

Rough set (RS) and radial basis function neural network (RBFNN) based insulation data mining fault diagnosis for power transformer is proposed. On the one hand rough set is used as front of RBFNN to simplify the input of RBFNN and mine the rules. The mined rules whose “confidence” and “support” is higher than requirement are used to offer fault diagnosis service for power transformer directly. On the other hand the mining samples corresponding to the mined rule, whose “confidence and support” is lower than requirement, are used to be training samples set of RBFNN and these samples are clustered by rough set. The center of each clustering set is used to be center of radial basis function, i.e., as the hidden layer neuron. The RBFNN is structured with above base, which is used to diagnose the case that can not be diagnosed by mined simplified valuable rules based on rough set. The advantages and effectiveness of this method are verified by testing.

Effects of various information scenarios on layer-wise relevance propagation-based interpretable convolutional neural networks for air handling unit fault diagnosis

Deep learning(DL),especially convolutional neural networks(CNNs),has been widely applied in air handling unit(AHU)fault diagnosis(FD).However,its application faces two major challenges.Firstly,the accessibility of operational state variables for AHU systems is limited in practical,and the effectiveness and applicability of existing DL methods for diagnosis require further validation.Secondly,the interpretability performance of DL models under various information scenarios needs further exploration.To address these challenges,this study utilized publicly available ASHRAE RP-1312 AHU fault data and employed CNNs to construct three FD models under three various information scenarios.Furthermore,the layer-wise relevance propagation(LRP)method was used to interpret and explain the effects of these three various information scenarios on the CNN models.An R-threshold was proposed to systematically differentiate diagnostic criteria,which further elucidates the intrinsic reasons behind correct and incorrect decisions made by the models.The results showed that the CNN-based diagnostic models demonstrated good applicability under the three various information scenarios,with an average diagnostic accuracy of 98.55%.The LRP method provided good interpretation and explanation for understanding the decision mechanism of CNN models for the unlimited information scenarios.For the very limited information scenario,since the variables are restricted,although LRP can reveal key variables in the model’s decision-making process,these key variables have certain limitations in terms of data and physical explanations for further improving the model’s interpretation.Finally,an in-depth analysis of model parameters—such as the number of convolutional layers,learning rate,βparameters,and training set size—was conducted to examine their impact on the interpretative results.This study contributes to clarifying the effects of various information scenarios on the diagnostic performance and interpretability of LRP-based CNN models for AHU FD,which helps provide improved reliability of DL models in practical applications.

INTELLIGENT FUSION FOR AEROENGINE WEAR FAULT DIAGNOSIS

Four common oil analysis techniques, including the ferrography analysis （FA）, the spectrometric oil analysis （SOA）, the particle count analysis （PCA）, and the oil quality testing （OQT）, are used to implement the military aeroengine wear fault diagnosis during the test drive process. To improve the precision and the reliability of the diagnosis, the aeroengine wear fault fusion diagnosis method based on the neural networks （NN） and the Dempster-Shafter （D-S） evidence theory is proposed. Firstly, according to the standard value of the wear limit, original data are pre-processed into Boolean values. Secondly, sub-NNs are established to perform the single diagnosis, and their training samples are dependent on experiences from experts. After each sub-NN is trained, diagnosis results are obtained. Thirdly, the diagnosis results of each sub-NN are considered as the basic probability allocation value to faults. The improved D-S evidence theory is applied to the fusion diagnosis, and the final fusion results are obtained. Finally, the method is verified by a diagnosis example.