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.

scholarly journals Research on Multi-Domain Fault Diagnosis of Gearbox of Wind Turbine Based on Adaptive Variational Mode Decomposition and Extreme Learning Machine Algorithms

Energies ◽  
2020 ◽  
Vol 13 (6) ◽  
pp. 1375 ◽  
Author(s):  
Hui Li ◽  
Bangji Fan ◽  
Rong Jia ◽  
Fang Zhai ◽  
Liang Bai ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Extreme Learning Machine ◽  
Grey Wolf Optimizer ◽  
Mechanical Equipment ◽  
Variational Mode Decomposition ◽  
Time Frequency ◽  
Mode Decomposition ◽  
Fault Features ◽  
Frequency Domains ◽  
Learning Machine

Since variational mode decomposition (VMD) was proposed, it has been widely used in condition monitoring and fault diagnosis of mechanical equipment. However, the parameters K and α in the VMD algorithm need to be set before decomposition, which causes VMD to be unable to decompose adaptively and obtain the best result for signal decomposition. Therefore, this paper optimizes the VMD algorithm. On this basis, this paper also proposes a method of multi-domain feature extraction of signals and combines an extreme learning machine (ELM) to realize comprehensive and accurate fault diagnosis. First, VMD is optimized according to the improved grey wolf optimizer; second, the feature vectors of the time, frequency, and time-frequency domains are calculated, which are synthesized after dimensionality reduction; ultimately, the synthesized vectors are input into the ELM for training and classification. The experimental results show that the proposed method can decompose the signal adaptively, which produces the best decomposition parameters and results. Moreover, this method can extract the fault features of the signal more completely to realize accurate fault identification.

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.

scholarly journals A New Intelligent Fault Diagnosis Method of Rotating Machinery under Varying-Speed Conditions Using Infrared Thermography

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-12 ◽  
Author(s):  
Yongbo Li ◽  
Xianzhi Wang ◽  
Shubin Si ◽  
Xiaoqiang Du
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Infrared Thermography ◽  
Rotating Machinery ◽  
Support Vector ◽  
Intelligent Fault Diagnosis ◽  
Fault Features ◽  
Diagnosis Method ◽  
Systematic Framework ◽  
Machinery Fault Diagnosis

A novel systematic framework, infrared thermography- (IRT-) based method, for rotating machinery fault diagnosis under nonstationary running conditions is presented in this paper. In this framework, IRT technique is first applied to obtain the thermograph. Then, the fault features are extracted using bag-of-visual-word (BoVW) from the IRT images. In the end, support vector machine (SVM) is utilized to automatically identify the fault patterns of rotating machinery. The effectiveness of proposed method is evaluated using lab experimental signal of rotating machinery. The diagnosis results show that the IRT-based method has certain advantages in classification rotating machinery faults under nonstationary running conditions compared with the traditional vibration-based method.

scholarly journals Fault Diagnosis Method for Rotating Machinery Based on Hierarchical Amplitude-Aware Permutation Entropy and Pairwise Feature Proximity

2021 ◽  
Vol 2021 ◽  
pp. 1-18
Author(s):  
Ling Shu ◽  
Jinxing Shen ◽  
Xiaoming Liu
Keyword(s):  
Time Series ◽  
Fault Diagnosis ◽  
Low Frequency ◽  
Rotating Machinery ◽  
Permutation Entropy ◽  
Support Vector ◽  
Feature Vectors ◽  
Fault Features ◽  
Diagnosis Method ◽  
Frequency Features

With a view to solving the defect that multiscale amplitude-aware permutation entropy (MAAPE) can only quantify the low-frequency features of time series and ignore the high-frequency features which are equally important, a novel nonlinear time series feature extraction method, hierarchical amplitude-aware permutation entropy (HAAPE), is proposed. By constructing high and low-frequency operators, this method can extract the features of different frequency bands of time series simultaneously, so as to avoid the issue of information loss. In view of its advantages, HAAPE is introduced into the field of fault diagnosis to extract fault features from vibration signals of rotating machinery. Combined with the pairwise feature proximity (PWFP) feature selection method and gray wolf algorithm optimization support vector machine (GWO-SVM), a new intelligent fault diagnosis method for rotating machinery is proposed. In our method, firstly, HAPPE is adopted to extract the original high and low-frequency fault features of rotating machinery. After that, PWFP is used to sort the original features, and the important features are filtered to obtain low-dimensional sensitive feature vectors. Finally, the sensitive feature vectors are input into GWO-SVM for training and testing, so as to realize the fault identification of rotating machinery. The performance of the proposed method is verified using two data sets of bearing and gearbox. The results show that the proposed method enjoys obvious advantages over the existing methods, and the identification accuracy reaches 100%.

Fault Diagnosis of Rotating Machinery Due to Clearance Using Hilbert-Huang Transform

2009 ◽  
Author(s):  
Yeon-Sun Choi
Keyword(s):  
Fault Diagnosis ◽  
Rotating Machinery ◽  
Analysis Method ◽  
Hilbert Huang Transform ◽  
Time Frequency ◽  
Frequency Information ◽  
Stationary Signals ◽  
Signal Processing Methods ◽  
The Impact ◽  
Conventional Signal

The faults in rotating machinery, caused by the clearance between the rotor and the stator, commonly lie on partial rub and looseness. These problems cause malfunctions in rotating machinery since they create strange vibrations coming from impact and friction. However, non-linear and non-stationary signals due to impact and friction are difficult to identify. Therefore, exact time and frequency information are needed for identifying these signals. For this purpose, a newly developed time-frequency analysis method, HHT(Hilbert-Huang Transform), is applied to the signals of partial rub and looseness from the experiment RK-4 rotor kit. Conventional signal processing methods such as FFT, STFT and CWT were compared to verify the effectiveness of fault diagnosis using HHT. The results showed that the impact signals were generated regularly when partial rub occurred but that intermittent impact and friction occurred irregularly when looseness occurred. The time and frequency information was represented exactly by using HHT in both cases, which makes clear fault diagnosis between partial rub and looseness.

Optimal resonance-based signal sparse decomposition and its application to fault diagnosis of rotating machinery

2016 ◽  
Vol 231 (24) ◽  
pp. 4670-4683 ◽  
Author(s):  
Dingcheng Zhang ◽  
Dejie Yu ◽  
Xing Li
Keyword(s):  
Fault Diagnosis ◽  
Decomposition Method ◽  
Rotating Machinery ◽  
Mechanical Equipment ◽  
Vibration Signals ◽  
Weak Fault ◽  
Main Components ◽  
The Hilbert Transform ◽  
Types Of Faults ◽  
Fault Characteristic

The fault diagnosis of rotating machinery is quite important for the security and reliability of the overall mechanical equipment. As the main components in rotating machinery, the gear and the bearing are the most vulnerable to faults. In actual working conditions, there are two common types of faults in rotating machinery: the single fault and the compound fault. However, both of them are difficult to detect in the incipient stage because the weak fault characteristic signals are usually submerged by strong background noise, thus increasing the difficulty of the weak fault feature extraction. In this paper, a novel decomposition method, optimal resonance-based signal spares decomposition, is applied for the detection of those two types of faults in the rotating machinery. This method is based on the resonance-based signal spares decomposition, which can nonlinearly decompose vibration signals of rotating machinery into the high and the low resonance components. To extract the weak fault characteristic signals in the presence of strong noise effectively, the genetic algorithm is used to obtain the optimal decomposition parameters. Then, the optimal high and low resonance components, which include the fault characteristic signals of rotating machinery, can be obtained by using the resonance-based signal spares decomposition method with the optimal decomposition parameters. Finally, the high and the low resonance components are subject to the Hilbert transform demodulation analysis; the faults of rotating machinery can be diagnosed based on the obtained envelop spectra. The optimal resonance-based signal spares decomposition method is successfully applied to the analysis of the simulation and experiment vibration signals. The analysis results demonstrate that the proposed method can successfully extract the fault features in rotating machinery.

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