A Novel Fault Feature Selection and Diagnosis Method for Rotating Machinery With Symmetrized Dot Pattern Representation

被引:16
作者
Tang, Gang [1 ]
Hu, Hao [1 ]
Kong, Jian [1 ]
Liu, Haoxiang [1 ]
机构
[1] Beijing Univ Chem Technol, Coll Mech & Elect Engn, Beijing 100029, Peoples R China
基金
国家重点研发计划; 中国国家自然科学基金;
关键词
Feature extraction; Vibrations; Machinery; Fault diagnosis; Time-frequency analysis; Image texture; Gray-scale; feature ranking; multiscale analysis; optimal class distance ratio; symmetrized dot pattern (SDP); variational mode decomposition (VMD); VARIATIONAL MODE DECOMPOSITION; MULTISCALE ANALYSIS; NEURAL-NETWORK; INFORMATION;
D O I
10.1109/JSEN.2022.3227099
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Fault diagnosis methods based on machine learning have made great progress for rotating machinery. The main steps of the machine learning process involve feature extraction, selection, and classification. Feature selection improves classification accuracy and reduces diagnosis time by selecting the better features. Due to the difficulty of traditional feature selection methods to rank the feature importance of each class, the best subset of features could hardly be obtained. Therefore, this article proposes a new feature selection method to address the shortcomings of the above traditional methods, called Feature Ranking based on Optimal Class Distance Ratio (FROCDR), which can choose the optimal features between every two classes of samples to obtain feature ranking that is conducive to classification. In order to comprehensively extract the fault information in the signal, the multiscale analysis and the variational mode decomposition (VMD) method are applied to process the vibration signals under different scales and frequency bands, and the processed signals are visualized by symmetrized dot pattern (SDP). In addition, features are extracted from the obtained SDP images, and the proposed FROCDR method is used to select the best subset of features. The final diagnosis task is accomplished by a random forest (RF) classifier. Experimental cases of bearing and gear data show that the proposed method has higher diagnostic accuracy and stability.
引用
收藏
页码:1447 / 1461
页数:15
相关论文
共 31 条
[1]   Bearing fault diagnosis with varying conditions using angular domain resampling technology, SDP and DCNN [J].
Gu, Yingkui ;
Zeng, Lei ;
Qiu, Guangqi .
MEASUREMENT, 2020, 156
[2]   Intelligent Fault Diagnosis Approach Based on Composite Multi-Scale Dimensionless Indicators and Affinity Propagation Clustering [J].
Hu, Qin ;
Zhang, Qi ;
Si, Xiao-Sheng ;
Sun, Guo-Xi ;
Qin, Ai-Song .
IEEE SENSORS JOURNAL, 2020, 20 (19) :11439-11453
[3]   Machinery Fault Diagnosis Scheme Using Redefined Dimensionless Indicators and mRMR Feature Selection [J].
Hu, Qin ;
Si, Xiao-Sheng ;
Qin, Ai-Song ;
Lv, Yun-Rong ;
Zhang, Qing-Hua .
IEEE ACCESS, 2020, 8 :40313-40326
[4]   A rotating machinery fault diagnosis method based on multi-scale dimensionless indicators and random forests [J].
Hu, Qin ;
Si, Xiao-Sheng ;
Zhang, Qing-Hua ;
Qin, Ai-Song .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2020, 139 (139)
[5]   Fault diagnosis and severity analysis of rolling bearings using vibration image texture enhancement and multiclass support vector machines [J].
Jha, Rakesh Kumar ;
Swami, Preety D. .
APPLIED ACOUSTICS, 2021, 182
[6]   Intelligent fault diagnosis of rolling bearing and gear system under fluctuating load conditions using image processing technique [J].
Jha, Rakesh Kumar ;
Swami, Preety D. .
JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY, 2020, 34 (10) :4107-4115
[7]   Series Arc Fault Detection Based on Random Forest and Deep Neural Network [J].
Jiang, Jun ;
Li, Wei ;
Wen, Zhe ;
Bie, Yifan ;
Schwarz, Harald ;
Zhang, Chaohai .
IEEE SENSORS JOURNAL, 2021, 21 (15) :17171-17179
[8]   Data-driven time-frequency analysis method based on variational mode decomposition and its application to gear fault diagnosis in variable working conditions [J].
Li, Fuhao ;
Li, Rong ;
Tian, Lili ;
Chen, Lin ;
Liu, Jian .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2019, 116 :462-479
[9]   Study on planetary gear fault diagnosis based on variational mode decomposition and deep neural networks [J].
Li, Yong ;
Cheng, Gang ;
Liu, Chang ;
Chen, Xihui .
MEASUREMENT, 2018, 130 :94-104
[10]   A method based on refined composite multi-scale symbolic dynamic entropy and ISVM-BT for rotating machinery fault diagnosis [J].
Li, Yongbo ;
Liang, Xihui ;
Wei, Yu ;
Wang, Xianzhi .
NEUROCOMPUTING, 2018, 315 :246-260