scholarly journals An SDP Characteristic Information Fusion-Based CNN Vibration Fault Diagnosis Method

2019 ◽  
Vol 2019 ◽  
pp. 1-14 ◽  
Author(s):  
Xiaoxun Zhu ◽  
Jianhong Zhao ◽  
Dongnan Hou ◽  
Zhonghe Han
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Information Fusion ◽  
Fault Identification ◽  
High Complexity ◽  
Test Rig ◽  
Rotor Vibration ◽  
Vibration Signals ◽  
Image Identification ◽  
Diagnosis Method

This study proposes a symmetrized dot pattern (SDP) characteristic information fusion-based convolutional neural network (CNN) fault diagnosis method to resolve issues of high complexity, nonlinearity, and instability in original rotor vibration signals. The method was used to conduct information fusion of real modal components of vibration signals and SDP image identification using CNN in order to achieve vibration fault diagnosis. Compared with other graphic processing methods, the proposed method more fully expressed the characteristics of different vibration signals and thus presented variations between different vibration states in a simpler and more intuitive way. The proposed method was experimentally investigated using simulation signals and rotor test-rig signals, and its validity and advancements were demonstrated using experimental analysis. By using CNN through deep learning to adaptively extract SDP characteristic information, vibration fault identification was ultimately realized.

scholarly journals Intelligent Model-based Integrity Assessment of Nonstationary Mechanical System

2021 ◽  
Author(s):  
Hanxin Chen ◽  
Yuzhuo Miao ◽  
Yongting Chen ◽  
Lu Fang ◽  
Li Zeng ◽  
...  
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Particle Filter ◽  
Mechanical System ◽  
Centrifugal Pump ◽  
Bp Neural Network ◽  
Vibration Signal ◽  
Fault Identification ◽  
Integrity Assessment ◽  
Diagnosis Method

The fault diagnosis model for nonstationary mechanical system is proposed in the condition monitoring. The algorithm with an improved particle filter and Back Propagation for intelligent fault identification is developed, which is used to reduce the noise of the experimental vibration signals to delete the negative effect of the noise on the feature extraction of the original vibration signal. The proposed integrated method is applied for the trouble shoot of the impellers inside the centrifugal pump. The principal component analysis (PCA) method optimizes the clean vibration signal to choose the optimal eigenvalue features.The constructed BP neural network is trained to get the condition models for fault identification. The proposed novel model is compared with the BP neural network based on traditional PF and particle swarm optimization particle filter (PSO-PF) algorithm. The BP neural network diagnosis method based on the improved PF algorithm is much better for the integrity assessment of the centrifugal pump impeller. This method is much significant for big data mining in the fault diagnosis method of the complex mechanical system.

scholarly journals Remaining Useful Life Prediction and Fault Diagnosis of Rolling Bearings Based on Short-Time Fourier Transform and Convolutional Neural Network

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Shuang Zhou ◽  
Maohua Xiao ◽  
Petr Bartos ◽  
Martin Filip ◽  
Guosheng Geng
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Life Prediction ◽  
Remaining Useful Life ◽  
Fault Identification ◽  
Rolling Bearings ◽  
Time Frequency ◽  
Diagnosis Method ◽  
Useful Life ◽  
Short Time

Rolling bearings play a pivotal role in rotating machinery. The remaining useful life prediction and fault diagnosis of bearings are crucial to condition-based maintenance. However, traditional data-driven methods usually require manual extraction of features, which needs rich signal processing theory as support and is difficult to control the efficiency. In this study, a bearing remaining life prediction and fault diagnosis method based on short-time Fourier transform (STFT) and convolutional neural network (CNN) has been proposed. First, the STFT was adopted to construct time-frequency maps of the unprocessed original vibration signals that can ensure the true and effective recovery of the fault characteristics in vibration signals. Then, the training time-frequency maps were used as an input of the CNN to train the network model. Finally, the time-frequency maps of testing signals were inputted into the network model to complete the life prediction or fault identification of rolling bearings. The rolling bearing life-cycle datasets from the Intelligent Management System were applied to verify the proposed life prediction method, showing that its accuracy reaches 99.45%, and the prediction effect is good. Multiple sets of validation experiments were conducted to verify the proposed fault diagnosis method with the open datasets from Case Western Reserve University. Results show that the proposed method can effectively identify the fault classification and the accuracy can reach 95.83%. The comparison with the fault diagnosis classification effects of backpropagation (BP) neural network, particle swarm optimization-BP, and genetic algorithm-BP further proves its superiority. The proposed method in this paper is proved to have strong ability of adaptive feature extraction, life prediction, and fault identification.

The Fault Diagnosis Method of Diesel Based on Wavelet Pocket and BP Neural Network

2014 ◽  
Vol 635-637 ◽  
pp. 910-913 ◽  
Author(s):  
Hong Hui Sun ◽  
Jun Xu ◽  
Qing Hua Zhang ◽  
Hong Xia Wang
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Adaptive Learning ◽  
Bp Neural Network ◽  
Wavelet Packet ◽  
Vibration Signals ◽  
Signal Energy ◽  
Time Frequency ◽  
Diagnosis Method ◽  
Neural Network Algorithm

Because of the well time-frequency spectrum disposal capability of wavelet packet, the wavelet packet algorithm is used to analyze the time - frequency characteristics of diesel vibration signals. The signal energy distributing characteristics based on wavelet packet transform. are extracted and taken as diagnostic characteristic vector, then improved BP neural network algorithm that connects additional momentum with self-adaptive learning rate was used to classify and recognize faults of diesel valves. The experimental results show the fault diagnosis method of diesel based on wavelet pocket and BP neural network is effective and feasible.

scholarly journals Fault Diagnosis of Subway Traction Motor Bearing Based on Information Fusion under Variable Working Conditions

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Yanwei Xu ◽  
Weiwei Cai ◽  
Tancheng Xie
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Working Conditions ◽  
Information Fusion ◽  
Working Condition ◽  
Rolling Bearing ◽  
Traction Motor ◽  
Bearing Fault ◽  
Diagnosis Method ◽  
Motor Bearing

Under the variable working condition, the fault signal of the rolling bearing contains rich characteristic information. In view of the problem that the traditional fault diagnosis method of the rolling bearing depends on the prior knowledge and expert experience too much and the low recognition rate of some faults with the single signal, one method of rolling bearing fault diagnosis based on information fusion under the variable working condition is proposed. Firstly, one test and multi-information acquisition system of the rolling bearing is built. Secondly, the metro traction motor bearing nu216 is selected as the research object, and to prefabricate the defects, the data of acoustic emission and vibration acceleration signals during the test of the bearing is acquired. Then, the original signal is processed and extracted by the wavelet packet decomposition, and the normalized feature information is fused by the convolution neural network. Finally, the two-dimensional convolution neural network model is established to diagnose the bearing fault of the metro traction motor under different conditions. The test results show that the intelligent fault diagnosis method of the subway traction motor bearing based on information fusion under variable working conditions can accurately identify the fault type of the bearing, while the load and speed change. When the neural network training set and the test set cover the same working conditions, the accuracy can reach 100%.

The Motor Fault Diagnosis Based on Neural Network and the Theory of D-S Evidence

2013 ◽  
Vol 683 ◽  
pp. 881-884 ◽  
Author(s):  
Chang Fei Sun ◽  
Zhi Shan Duan ◽  
Yang Yang ◽  
Miao Wang ◽  
Li Jie Hu
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Information Fusion ◽  
Threshold Value ◽  
Fusion Technology ◽  
Independent Evidence ◽  
Modes Of Failure ◽  
Processing Data ◽  
Single Feature ◽  
Diagnosis Method

In order to reduce the uncertainty of the traditional method that use a single parameter in the motor fault diagnosis, create a reliable motor fault diagnosis model by using multivariate information fusion technology and the combination of neural network and the theory of D-S evidence .First, fusion the information of many kinds of sensors, preliminary identify the modes of failure, find the information of different fault feature by analysing and processing data, establish the domain of feature. Then part diagnose the domain of feature by using neural network. The local diagnosis results form independent evidence body. Calculate the credibility of the fault distribution of each evidence body for recognition framework. It is difficult to discriminant fault types by directly using these reliability distribution. So choose appropriate D-S evidence formula to fusion each evidence body and further process and analyse the information of evidence. The credibility of the distribution is nearer and nearer to the judgement threshold value of fault types with one fusion, and the rest of the credibility distribution of the fault is more and more smaller. So the basic reliability distribution has better peak and separability, the diagnose results is more accurate, and finally achieve accurate diagnosis of the motor fault. The diagnosis example shows that the diagnosis method based on neural network and the theory of D-S evidence can realize comprehensive diagnosis of motor fault by using multi-resources information. The reliability and accuracy of this diagnosis method are far higher than that of the local diagnosis using single feature. It improves the precision of the motor fault diagnosis.

Research on Mechanical Fault Identification Based on Improved SVM

2010 ◽  
Vol 97-101 ◽  
pp. 4257-4260
Author(s):  
Dong Di Chen ◽  
Jia Wei Xiang ◽  
Yong Teng Zhong
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Present Method ◽  
Classification Problem ◽  
Fault Identification ◽  
Support Vector ◽  
Statistical Features ◽  
Operational Conditions ◽  
Diagnosis Method ◽  
Artificial Neural Network Ann

Fault diagnosis of machinery is in essence a kind of classification problem. Utilizing the desirable classification ability of support vector machine (SVM) for fewer samples, a novel fault diagnosis method based on improved SVM was proposed. Some statistical features were extracted to reflect the equipment operational conditions and were input into fault classifier to attain the final diagnostic result. Experimental signals of gearbox were analyzed using the present method. The results of improved SVM were compared with those of artificial neural network (ANN). It indicates that the proposed method have better classification ability than that of ANN.

Fault Diagnosis Method for the Rolling Bearing Based on Information Fusion and BP Neural Network

2012 ◽  
Vol 538-541 ◽  
pp. 1956-1961 ◽  
Author(s):  
Jin Min Zhang ◽  
Yin Hua Huang ◽  
Si Ming Wang
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Information Fusion ◽  
Bp Neural Network ◽  
Back Propagation ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Back Propagation Neural Network ◽  
Weighted Fusion ◽  
Diagnosis Method

Abstract. In order to diagnose the fault of rolling bearing by the vibration signal, a new method of fault diagnosis based on weighted fusion and BP (Back Propagation) neural network was put forward. At first, the vibration signal from the sensors was wave filtered through the method of correlation function, then the fused signal was obtained by the classical adaptive weighted fusion method, the multi-type characteristics parameters was to be as a neural network input. Finally, the fault diagnosis of rolling bearing was realized by the BP neural network, and the results show that the multi-sensor information fusion fault diagnosis method can be proved effectively to achieve the fault diagnosis of rolling bearing.

Data-Driven Based Gas Path Fault Diagnosis for Turbo-Shaft Engine

2012 ◽  
Vol 249-250 ◽  
pp. 400-404 ◽  
Author(s):  
Feng Lu ◽  
Tie Bin Zhu ◽  
Yi Qiu Lv
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Information Fusion ◽  
Rbf Neural Network ◽  
Evidence Theory ◽  
Aircraft Engine ◽  
Data Driven ◽  
Support Vector ◽  
Diagnosis Method ◽  
Gas Path Fault

In order to improve diagnostic accuracy and reduce the rate of misdiagnosis to the aircraft engine gas path faulty, the methods based on data-driven and information fusion are developed and analyzed. BP neural network (NN) and RBF neural network based on data-driven single gas path fault diagnosis method is introduced firstly. Design gas path performance estimators and the fault type classification for turbo-shaft engine. Then the gas path fused diagnostic structure based on D-S evidence theory and least squares support vector machine are developed. Comparisons of the turbo-shaft engine gas path fault diagnosis verify the feasibility and effectiveness of the gas path fault diagnosis based on information fusion.

The Engine Fault Diagnosis with RBFNN Based on AIC

2012 ◽  
Vol 468-471 ◽  
pp. 1066-1069
Author(s):  
Qiang Huang ◽  
Xiao Zhuo Ouyang ◽  
Cheng Wang
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Diesel Engine ◽  
Rbf Neural Network ◽  
Information Criterion ◽  
Vibration Signals ◽  
The Neural Network ◽  
Rotary Machines ◽  
Diagnosis Method ◽  
Diagnosis Model

In this paper, an engine diagnosis method with high precision and quickly response is proposed. Firstly, the Akaike Information Criterion (AIC) is used to improve the performance of the neural network to build the fault diagnosis model. Then the vibration signals are analyzed to estimate the states of the diesel engine. Finally, the five states of diesel engine are set to validate the veracity of diagnosis method. According to experiment and simulation researches, it indicates that the diagnosis method with RBF neural network based on AIC is effective. The veracity of identification is 100% to the single fault. It is a valuable reference to the vibration diagnosis for other complex rotary machines.

scholarly journals Bearing Fault Diagnosis via Improved One-Dimensional Multi-Scale Dilated CNN

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7319
Author(s):  
Jiajun He ◽  
Ping Wu ◽  
Yizhi Tong ◽  
Xujie Zhang ◽  
Meizhen Lei ◽  
...  
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Vibration Signals ◽  
Maintenance Costs ◽  
One Dimensional ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis ◽  
Multi Scale ◽  
Diagnosis Method

Bearings are the key and important components of rotating machinery. Effective bearing fault diagnosis can ensure operation safety and reduce maintenance costs. This paper aims to develop a novel bearing fault diagnosis method via an improved multi-scale convolutional neural network (IMSCNN). In traditional convolutional neural network (CNN), a fixed convolutional kernel is often employed in the convolutional layer. Thus, informative features can not be fully extracted for fault diagnosis. In the proposed IMSCNN, a 1D dimensional convolutional layer is used to mitigate the effect of noise contained in vibration signals. Then, four dilated convolutional kernels with different dilation rates are integrated to extract multi-scale features through the inception structure. Experimental results from the popular CWRU and PU datasets show the superiority of the proposed method by comparison with other related methods.

Sign in / Sign up

Export Citation Format

Share Document