scholarly journals Rotating Machinery Fault Diagnosis Method by Combining Time-Frequency Domain Features and CNN Knowledge Transfer

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8168
Author(s):  
Lihao Ye ◽  
Xue Ma ◽  
Chenglin Wen
Keyword(s):  
Fault Diagnosis ◽  
Knowledge Transfer ◽  
Frequency Domain ◽  
Rotating Machinery ◽  
Domain Model ◽  
Small Samples ◽  
Target Domain ◽  
Time Frequency ◽  
Diagnosis Method ◽  
Deep Cnn

Aiming at the problem of fault diagnosis when there are only a few labeled samples in the large amount of data collected during the operation of rotating machinery, this paper proposes a fault diagnosis method based on knowledge transfer in deep learning. First, we describe the data collected during the operation as a two-dimensional image with both time and frequency-domain characteristics. Second, we transform the trained source domain model into a shallow model suitable for small samples in the target domain, and we train the shallow model with small samples with labels. Third, we input a large number of unlabeled samples into the shallow model, and the output result of the system is regarded as the label of the input sample. Fourth, we combine the original data and the data annotated by the shallow model to train the new deep CNN fault diagnosis model so as to realize the migration of knowledge from the expert system to the deep CNN. The newly built deep CNN model is used for the online fault diagnosis of rotating machinery. The FFCNN-SVM shallow model tagger method proposed in this paper compares the fault diagnosis results with other transfer learning methods at this stage, and its correct rate has been greatly improved. This method provides new ideas for future fault diagnosis under small samples.

Fault Detection and Discrimination of Rotating Machinery Using Frequency Symptom Parameter and Bayesian Network

2013 ◽  
Vol 470 ◽  
pp. 683-688
Author(s):  
Hai Yang Jiang ◽  
Hua Qing Wang ◽  
Peng Chen
Keyword(s):  
Fault Diagnosis ◽  
Fault Detection ◽  
Bayesian Network ◽  
Frequency Domain ◽  
Evaluation Method ◽  
Roller Bearing ◽  
Rotating Machinery ◽  
Discrimination Index ◽  
Vibration Signals ◽  
Diagnosis Method

This paper proposes a novel fault diagnosis method for rotating machinery based on symptom parameters and Bayesian Network. Non-dimensional symptom parameters in frequency domain calculated from vibration signals are defined for reflecting the features of vibration signals. In addition, sensitive evaluation method for selecting good non-dimensional symptom parameters using the method of discrimination index is also proposed for detecting and distinguishing faults in rotating machinery. Finally, the application example of diagnosis for a roller bearing by Bayesian Network is given. Diagnosis results show the methods proposed in this paper are effective.

scholarly journals A Fault Diagnosis Method of Rolling Mill Bearing at Low Frequency and Overload Condition Based on Integration of EEMD and GA-DBN

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Jiang Ji ◽  
Chen Zhao ◽  
Yongqin Wang ◽  
Tuanmin Zhao ◽  
Xinyou Zhang
Keyword(s):  
Fault Diagnosis ◽  
Frequency Domain ◽  
Rolling Mill ◽  
Rolling Force ◽  
Low Frequency ◽  
Frequency Domain Analysis ◽  
Fault Classification ◽  
Low Speed ◽  
Time Frequency ◽  
Diagnosis Method

To solve the problems of difficult fault signal recognition and poor diagnosis effect of different damage in the same position in rolling mill bearing at low speed, a fault diagnosis method of rolling mill bearing based on integration of EEMD and DBN was proposed. The vibration signals in horizontal, axial, and vertical directions were decomposed and reconstructed by EEMD, and frequency domain analysis was carried out by using refined spectrum. Then, the signal's time-frequency domain index, rolling force, and torque component feature vector were input into genetic algorithm (GA) to optimize DBN model classification. In order to verify the effectiveness of the method, the experimental study was carried out on the two-high experimental rolling mill. The results show that EEMD combined with thinning spectrum can solve the problem of fault feature extraction well. Compared with time-frequency domain characteristic input, the prediction accuracy of DBN model is obviously improved. And the accuracy of GA-DBN model is higher, and the accuracy is 98.3%, and the time taken to diagnose is significantly reduced. Finally, the fault classification of different parts of bearings and the fault diagnosis of different damage in the same part are realized, which provides a good theoretical basis for the fault diagnosis of low-speed bearings and has important engineering significance.

Application of Virtual Instrument on Condition Monitoring and Fault Diagnosis System of the Rotating Machinery

2012 ◽  
Vol 542-543 ◽  
pp. 161-164
Author(s):  
Yong Ying Du ◽  
Yu Ning Wang ◽  
Ming Ang Yin
Keyword(s):  
Fault Diagnosis ◽  
Data Acquisition ◽  
Frequency Domain ◽  
Condition Monitoring ◽  
Domain Analysis ◽  
Frequency Domain Analysis ◽  
Rotating Machinery ◽  
Waveform Data ◽  
Time Frequency ◽  
Acceleration Sensors

In the paper it can be easier to realize the acquisition of the rotating machinery vibration signal and condition monitoring through the configuration the platform of virtual instrumentation. For the data acquisition it is enough to be plus with two acceleration sensors and a counter. The system is divided into parameter setting module, data acquisition, storage and display module, amplitude domain analysis module, time-domain analysis module, frequency domain analysis module, time-frequency domain analysis module and fault diagnosis module. The signal acquisition is got by using the PCI-6024E data acquisition card. And it is can be saved as binary data stream files and waveform data file according to the requirements of the sequence data processing. Signal analysis is conducted by using LabVIEW software and draw out the vibration spectrum diagram in order to achieve fault diagnosis of rotating machinery.

Research on the Time-Frequency Analysis Method to Extract Early Fault Features of Rotating Machinery

2012 ◽  
Vol 190-191 ◽  
pp. 1371-1375
Author(s):  
Ping Hua Ju ◽  
Gen Bao Zhang
Keyword(s):  
Fault Diagnosis ◽  
Rotating Machinery ◽  
Mechanical Equipment ◽  
Analysis Method ◽  
Time Frequency ◽  
Fault Features ◽  
Common Diagnosis ◽  
Diagnosis Method ◽  
Weak Fault ◽  
Basic Features

Early fault features of rotating machinery is very weak and is disturbed by strong noise generally. how to more accurately extract early (weak) fault features from signals is still a hot and difficult point of research of the discipline. An intensive study is given to basic features of rotating machinery early faults and common diagnosis method, And also summarized the research status of early diagnosis in the field of mechanical equipment signal feature extraction and fault diagnosis, analyzed the current problems, and finally briefly pointed out the development of early fault diagnosis in machinery applications.

A Fault Diagnosis Method for Substation Grounding Grid Based on the Square-Wave Frequency Domain Model

2012 ◽  
Vol 19 (1) ◽  
pp. 63-72 ◽  
Author(s):  
Peng-He Zhang ◽  
Jun-Jia He ◽  
Dan-Dan Zhang ◽  
Lan-Min Wu
Keyword(s):  
Fault Diagnosis ◽  
Frequency Domain ◽  
Domain Model ◽  
Wave Frequency ◽  
Scale Model ◽  
Frequency Model ◽  
Square Wave ◽  
Grounding Grid ◽  
Diagnosis Method ◽  
Grid Based

A Fault Diagnosis Method for Substation Grounding Grid Based on the Square-Wave Frequency Domain ModelCurrent methods of fault diagnosis for the grounding grid using DC or AC are limited in accuracy and cannot be used to identify the locations of the faults. In this study, a new method of fault diagnosis for substation grounding grids is proposed using a square-wave. A frequency model of the grounding system is constructed by analyzing the frequency characteristics of the soil and the grounding conductors into which two different frequency square-wave sources are injected. By analyzing and comparing the corresponding information of the surface potentials of the output signals, the faults of the grounding grid can be diagnosed and located. Our method is verified by software simulation, scale model experiments and field experiments.

scholarly journals Graph-domain features and their application in rotating machinery fault diagnosis

2021 ◽  
Vol 1207 (1) ◽  
pp. 012008
Author(s):  
Yiyuan Gao ◽  
Wenliao Du ◽  
Xiaoyun Gong ◽  
Dejie Yu
Keyword(s):  
Fault Diagnosis ◽  
Frequency Domain ◽  
Time Domain ◽  
Mechanical Vibration ◽  
Rotating Machinery ◽  
Support Vector ◽  
Fisher Score ◽  
Fault Features ◽  
Diagnosis Method ◽  
Diagnosis Accuracy

Abstract To more effectively extract the non-stationary and non-linear fault features of mechanical vibration signals, a novel fault diagnosis method for rotating machinery is proposed combining time-domain, frequency-domain with graph-domain features. Different from the conventional time-domain and frequency-domain features, the graph-domain features generated from horizontal visibility graphs can extract the fault information hidden in the graph topology. Aiming at the problem that too many features will lead to information redundancy, the Fisher score algorithm is applied to select several of sensitive features which are then fed into the support vector machine to diagnose the faults of rotating machinery. Experimental results indicate features extracted from the three domains can be used to obtain higher diagnosis accuracy than that extracted from any single domain or dual domains.

Sign in / Sign up

Export Citation Format

Share Document