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.

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.

Research on Remote Monitoring and Fault Diagnosis Technology of Numerical Control Machine

Based on the internet technology,it has become possible to complete remote monitoring and fault diagnosis for the numerical control machine.In order to capture the micro-shock signal induced by the incipient fault on the rotating parts,the reso- nance demodulation technology is utilized in the system.As a subsystem of the remote monitoring system,the embedded data acquisi- tion instrument not only integrates the demodulation board but also complete the collection and preprocess of monitoring data from different machines.Furthermore,through connecting to the internet,the data can be transferred to the remote diagnosis center and data reading and writing function can be finished in the database.At the same time,the problem of the IP address floating in the dial-up of web server is solved by the dynamic DNS technology.Finally,the remote diagnosis software developed on the Lab VIEW platform can analyze the monitoring data from manufacturing field.The research results have indicated that the equipment status can be monitored by the system effectively.

Study on Fault Diagnosis of Rotating Machinery with Hybrid Neural Networks

With the help of the feedforward neural network diagnostic method, the hybrid diagnostic networks corresponding to information in multiple symptom domains are built and the comprehensive judgment is carried out with weighted average method. Meanwhile, this method has the ability of self learning and self adaptation in order to adapt both the complexity of vibrations produced practically and the pluralistic potent of vibration symptoms induced really for large rotating machinery, especially for turbogenerators. The reliability and precision of diagnosis with this method is heightened. It seems that the method can take more practical value in engineering applications.

A Modified Feedforward Neural Network Model for Fault Diagnosis of Rotating Machinery

ＡＭｏｄｉｆｉｅｄＦｅｅｄｆｏｒｗａｒｄＮｅｕｒａｌＮｅｔｗｏｒｋＭｏｄｅｌｆｏｒＦａｕｌｔＤｉａｇｎｏｓｉｓｏｆＲｏｔａｔｉｎｇＭａｃｈｉｎｅｒｙＺａｎｇＣｈａｏｐｉｎｇ（臧朝平）ＧａｏＷｅｉ（高）（ＮＥＲＣＴＶ，ＳｏｕｔｈｅａｓｔＵｎｉｖｅｒｓ...

Application of Kernel GDA to Performance Monitoring and Fault Diagnosis for Rotating Machinery

Faults in rotating machine are difficult to detect and identify,especially when the system is complex and nonlinear.In order to solve this problem,a novel performance monitoring and fault diagnosis method based on kernel generalized discriminant analysis(kernel GDA,KGDA)was proposed.Through KGDA,the data were mapped from the original space to the high-dimensional feature space.Then the statistic distance between normal data and test data was constructed to detect whether a fault was occurring.If a fault had occurred,similar analysis was used to identify the type of faults.The effectiveness of the proposed method was evaluated by simulation results of vibration signal fault dataset in the rotating machinery,which was scalable to different rotating machinery.

Product Maintenance Oriented Remote Monitoring and Diagnosis System

A research on maintenance oriented remote monitoring and diagnosis modular as well as the data transportation technique is carried out. An opened and modularized data share framework integrated with virtual graphic transportation is presented to realize the data exchange. As a result, it implements a real-time monitoring, diagnosis and maintenance system based on WWW. An effective support technique for the real-time remote fault diagnosis, maintenance and entire life cycle design of products is supplied.

Remote Monitoring and Diagnosis System for High-speed Wire Rolling Mills

Traditional fault diagnosis systems of rolling mills mostly use single machine monitoring net,which leads the re- al-time data running only in the enterprise locally and can not monitor and manage the high-speed wire rolling mills between units, workshops and factories concentratedly.A new-type structure of remote diagnosis system for high-speed wire rolling mills is pre- sented in this paper.The signal processing,computer network and remote diagnosis etc techniques are used to predictive maintenance manage the rolling mills units in this system.The new structure reinforced the remote feedback function,made up the existing fault diagnosis systems’ insufficiency in the extension and the function,promoted resource sharing and avoided the repeat develop- ment.The remote diagnosis example shows that the system can monitor and diagnose the fault information of remote machine timely and effectively.

Design and implementation of an expert system for remote fault diagnosis in ship lift

In this paper an expert system for remote fault diagnosis in the ship lift was developed by analysis of the fault tree and combination with VPN. The fault tree was constructed based on the operation condition of the ship lift. The diagnosis model was constructed by hierarchical classification of the fault tree structure, and the inference mechanism was given. Logical structure of the fault diagnosis in the ship lift was proposed. The implementation of the expert system for remote fault diagnosis in the ship lift was discussed, and the expert system developed was realized on the VPN virtual network. The system was applied to the Gaobaozhou ship lift project, and it ran successfully.

A Study on a Remote Monitoring and Diagnosis System and Its Application

Remote monitoring and diagnosis （RMD） is a new kind of monitoring and diagnosis technology that combines computer science, communication technology and fault diagnosis technology. Via the Internet a remote monitoring and diagnosis system can be established. In this paper, the model of an Internet based remote monitoring and diagnosis system is presented; the function of every part of the RMD system is discussed. Then, we introduce a practical example of a remote monitoring and diagnosis system that we established in a factory; its traits and functions are described.

Comparative Study of Combined Fault Diagnosis Schemes Based on Convolutional Neural Network

In this paper, comparative combined fault diagnosis schemes are studied including vibration analysis, acoustic signal analysis and thermal image analysis based on the Convolutional Neural Network (CNN). The advantage of the CNN structure is that it does not need manual feature extraction or selection, which requires prior knowledge of specific machinery dynamics. The vibration and acoustic signals were transformed into spectrograms, which are effective for the diagnostic analysis by using CNN. Comparatively, the thermal images were directly analyzed using CNN. The effectiveness of the CNN-based diagnosis methods was investigated through the analysis of different experimental data, i.e., vibration, acoustic signals and thermal images, which were collected from a test rig where different types of faults are induced on the roller bearing and shaft. The results show that the thermal image analysis and acoustic signal analysis could achieve relatively higher accuracy rate compared to vibration analysis. Moreover, the advantage is easy-deployment because of the non-contact way during signal acquisition. With the CNN-based fault diagnosis method for the three different signals collected, the accuracy of different signal predictions for combined faults can be compared, and the effective method can be applied to fault diagnosis of other industrial rotating machinery.

The Diagnosis of Reciprocating Machinery by Bayesian Networks

A Bayesian Network is a reasoning tool based on probability theory and has many advantages that other reasoning tools do not have. This paper discusses the basic theory of Bayesian networks and studies the problems in constructing Bayesian networks. The paper also constructs a Bayesian diagnosis network of a reciprocating compressor. The example helps us to draw a conclusion that Bayesian diagnosis networks can diagnose reciprocating machinery effectively.

Research on remote hydro-generator sets diagnosis system

A type of remote monitoring and diagnosis system is brought forward which based on Matlab Web Server.Firstly,wavelet packet decomposition is introduced to acquire energy features of which reflect hydrogenerator sets performance to be Feature Parameter.Then these Feature Parameters can be adopted as BP Neural Network input variable to realize fault diagnosis.Most of all,it is the first time to adopt Matlab Web Server to hydro-generator sets faults diagnosis field to implement distributed remote monitoring and diagnosis system.Therefore,remote diagnosis application is independent from the OS used on server side.There is no need for software maintenance by clients.And clients can finish remote diagnosis by Web Browser and without installation of Matlab-software.Client users can monitor and diagnose hydro-generator sets by Browser.Finally,further research work is pointed out such as hydro-generator sets fault modeling,accelerating BP Neural Network learning speed and convergence property,improving data transfer speed of Matlab Web Server to meet the needs of real-time diagnosis for hydropower generator sets.

Intelligent Examination Monitoring and Maintenance for the Safety of Operation of Flexible Manufacturing Systems

Based on the system of electric power supply for flexible manufacturing systems (FMS), a study has been carried out on the intelligent safety examination, monitoring and maintenance of its running environment. On the basis of the specific feature of the power supply network of an FMS, real time monitoring system of the power supply network and the fault diagnostic expert system for the power equipment have been designed. This system can diagnose not only definite fault phenomena, but also fuzzy, uncertain fault phenomena as well. Fault diagnostic knowledge base for the power equipment has been founded hierarchy architecture model and the method of fault tree analysis. Feasibility of this system has been proved by computer simulation.

Rotating machinery fault diagnosis based on convolutional neural network and infrared thermal imaging

Rotating machinery is widely applied in industrial applications.Fault diagnosis of rotating machinery is vital in manufacturing system,which can prevent catastrophic failure and reduce financial losses.Recently,Deep Learning(DL)-based fault diagnosis method becomes a hot topic.Convolutional Neural Network(CNN)is an effective DL method to extract the features of raw data automatically.This paper develops a fault diagnosis method using CNN for InfRared Thermal(IRT)image.First,IRT technique is utilized to capture the IRT images of rotating machinery.Second,the CNN is applied to extract fault features from the IRT images.In the end,the obtained features are fed into the Softmax Regression(SR)classifier for fault pattern identification.The effectiveness of the proposed method is validated using two different experimental data.Results show that the proposed method has a superior performance in identification various faults on rotor and bearings comparing with other deep learning models and traditional vibration-based method.

Real-time condition monitoring and fault diagnosis in switched reluctance motors with Kohonen neural network

The faults in switched reluctance motors(SRMs) were detected and diagnosed in real time with the Kohonen neural network. When a fault happens, both financial losses and undesired situations may occur. For these reasons, it is important to detect the incipient faults of SRMs and to diagnose which faults have occurred. In this study, a test rig was realized to determine the healthy and faulty conditions of SRMs. A data set for the Kohonen neural network was created with implemented measurements. A graphical user interface(GUI) was created in Matlab to test the performance of the Kohonen artificial neural network in real time. The data of the SRM was transferred to this software with a data acquisition card. The condition of the motor was monitored by marking the data measured in real time on the weight position graph of the Kohonen neural network. This test rig is capable of real-time monitoring of the condition of SRMs, which are used with intermittent or continuous operation, and is capable of detecting and diagnosing the faults that may occur in the motor. The Kohonen neural network used for detection and diagnosis of faults of the SRM in real time with Matlab GUI was embedded in an STM32 processor. A prototype with the STM32 processor was developed to detect and diagnose the faults of SRMs independent of computers.

Decision Support System for Maintenance Management Using Bayesian Networks

The maintenance process has undergone several major developments that have led to proactive considerations and the transformation fiom the traditional ＂fail and fix＂ practice into the ＂predict and prevent＂ proactive maintenance methodology. The anticipation action, which characterizes this proactive maintenance strategy is mainly based on monitoring, diagnosis, prognosis and decision-making modules. Oil monitoring is a key component of a successful condition monitoring program. It can be used as a proactive tool to identify the wear modes of rubbing pans and diagnoses the faults in machinery. But diagnosis relying on oil analysis technology must deal with uncertain knowledge and fuzzy input data. Besides other methods, Bayesian Networks have been extensively applied to fault diagnosis with the advantages of uncertainty inference; however, in the area of oil monitoring, it is a new field. This paper presents an integrated Bayesian network based decision support for maintenance of diesel engines.

基于自适应深度残差网络的旋转机械故障诊断方法

针对深度残差网络无法在噪声环境下精确诊断的问题,提出了一种基于直接快速迭代滤波(direct fast iterative filtering,DFIF)和自适应深度残差网络(adaptive deep residual network,AResNet)的方法,并将其应用于噪声环境下旋转机械的故障诊断中。首先,在采集的振动信号中增加不同强度的噪声,再经DFIF分解得到若干个本征模态函数(intrinsic mode function,IMF)分量,选取综合评价指标值最小的IMF分量作为输入样本;其次,提出了自适应残差单元(adaptive residual building unit,ARBU),ARBU通过计算各个通道的最优系数,自适应地放大故障敏感特征和抑制无关特征,能够更好地替代传统的残差单元;最后,基于ARBU构造AResNet,输入样本经过AResNet得到故障诊断结果。将所提方法应用于噪声背景下旋转机械的故障诊断中,在两个不同数据集中进行了验证。研究结果表明,与现有方法相比,所提方法具有更高的噪声鲁棒性、稳定性和更优的计算效率,且能够更好地解决旋转机械在噪声背景下故障特征难以有效挖掘的问题。

造纸机械工作状态智能化计算机监控系统设计研究

随着智能制造时代的降临,造纸业正面临着自动化、智能化改革的考验。如今,造纸机械数量、种类和复杂程度不断提升,再加上机械设备7×24 h不间断运行,其故障频率呈现暴增趋势。如何以智能化手段对造纸机械工作状态进行实时监测与控制,是现今造纸行业亟待解决的问题之一。基于此,分析了现代造纸机械智能化监控系统需具备的功能与采用的技术,出于成本和监控可靠性考虑,提出一种在线监测为主、离线监测为辅的复合监测控制系统,探究了系统硬件平台的搭建、系统软件的设计,并进行了造纸机械工作状态监测与常见故障诊断测试,验证了该系统可准确监测造纸机械异常工作状态、辨别故障类型,具有一定的可行性。

变转速极低标签率下旋转机械故障诊断的图注意力网络

在极低标签率情况下,现有的图神经网络(graph neural network,GNN)在图构造时存在节点间的关联信息挖掘不充分等问题。工业生产中,旋转机械常工作在变转速工况下,且标记故障样本代价高昂。针对上述两个问题,基于JS(Jenson-Shannon)相对熵和动态图注意力网络(dynamic graph attention network,DGAT),提出了一种熵-图注意力网络,并将其应用于极低标签率下变转速工况的旋转机械半监督故障诊断中。首先,设计了基于JS相对熵的图构造方法,用于充分挖掘GNN中样本间的关联信息。其次,构建基于熵-动态图注意力网络的半监督学习模型,通过动态注意力机制进一步挖掘样本中故障敏感特征。最后,将所提方法在变转速工况下轴承和齿轮箱数据集上进行验证,结果表明所提方法能够在标签率不超过1%的极低情况下准确诊断出旋转机械的不同故障类型,且性能优于其它常用的图神经网络。