Accurate Detection of Bearing Faults Using Difference Visibility Graph and Bi-Directional Long Short-Term Memory Network Classifier

被引:19
作者
Roy, Sayanjit Singha [1 ]
Chatterjee, Soumya [2 ]
Roy, Saptarshi [3 ]
Bamane, Pradip [1 ]
Paramane, Ashish [1 ]
Rao, U. Mohan [4 ]
Nazir, Muhammad Tariq [5 ]
机构
[1] NIT Silchar, Elect Engn Dept, Silchar 788010, Assam, India
[2] Birla Inst Technol, Elect & Elect Engn Dept, Ranchi 835215, Bihar, India
[3] MirMadan Mohanlal Govt Polytech, Elect & Engn Dept, Palasi 741156, India
[4] Univ Quebec Chicoutimi, Dept Appl Sci, Chicoutimi, PQ G7H 2B1, Canada
[5] Univ New South Wales, Sch Elect Engn & Telecommun, Sydney, NSW 2052, Australia
关键词
Vibrations; Time series analysis; Rolling bearings; Feature extraction; Signal processing algorithms; Convolutional neural networks; Induction motors; Classification; fault diagnosis; graph theory; induction motors (IMs); long short-term memory (LSTM); neural network; INDUCTION MACHINES; DIAGNOSIS; VIBRATION; SIGNALS; LSTM;
D O I
10.1109/TIA.2022.3167658
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
This article proposes a novel bearing fault detection framework for the real-time condition monitoring of induction motors based on difference visibility graph (DVG) theory. In this regard, the vibration signals of healthy as well as different rolling bearing defects were acquired from both fan-end and drive-end accelerometers. These data were recorded for three different bearing defects and under four loading conditions. The acquired vibration time series were converted to a topological network using DVG. From the transformed vibration data in the graph domain, degree distribution (DD) was selected as feature to discriminate different fault networks. Using analysis of variance test and false discovery rate correction, most discriminative DD features were selected. These features were subsequently fed as inputs to a deep learning model, i.e., a bidirectional long short-term memory network classifier for fault classification. In this study, 112 classification problems have been addressed, and for all of them, the proposed approach delivered very high fault detection accuracy. Finally, the classification performance of the proposed framework is compared with other well-known deep-learning classifiers all of which delivered satisfactory results.
引用
收藏
页码:4542 / 4551
页数:10
相关论文
共 50 条
[41]   Online Driver Distraction Detection Using Long Short-Term Memory [J].
Woellmer, Martin ;
Blaschke, Christoph ;
Schindl, Thomas ;
Schuller, Bjoern ;
Faerber, Berthold ;
Mayer, Stefan ;
Trefflich, Benjamin .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2011, 12 (02) :574-582
[42]   Portable Sleep Apnea Syndrome Screening and Event Detection Using Long Short-Term Memory Recurrent Neural Network [J].
Chang, Hung-Chi ;
Wu, Hau-Tieng ;
Huang, Po-Chiun ;
Ma, Hsi-Pin ;
Lo, Yu-Lun ;
Huang, Yuan-Hao .
SENSORS, 2020, 20 (21) :1-17
[43]   Detection of long-term effect in forecasting municipal solid waste using a long short-term memory neural network [J].
Niu, Dongjie ;
Wu, Fan ;
Dai, Shijin ;
He, Sheng ;
Wu, Boran .
JOURNAL OF CLEANER PRODUCTION, 2021, 290
[44]   Accurate detection of sleep apnea with long short-term memory network based on RR interval signals [J].
Faust, Oliver ;
Barika, Ragab ;
Shenfield, Alex ;
Ciaccio, Edward J. ;
Acharya, U. Rajendra .
KNOWLEDGE-BASED SYSTEMS, 2021, 212
[45]   Online Pre-Diagnosis of Multiple Faults in Proton Exchange Membrane Fuel Cells by Convolutional Neural Network Based Bi-Directional Long Short-Term Memory Parallel Model with Attention Mechanism [J].
Chen, Junyi ;
Ran, Huijun ;
Chen, Ziyang ;
Kwan, Trevor Hocksun ;
Yao, Qinghe .
ENERGIES, 2025, 18 (10)
[46]   Magnetic Resonance Imaging Brain Segmentation Using Bi-Directional Convolutional Long Short-Term Memory U-Net With Densely Connected Convolutions [J].
Alanazi, Meshari D. ;
Maraoui, Amna ;
Werda, Imen ;
Ben Atitallah, Ahmed ;
Alanazi, Turki M. ;
Albekairi, Mohammed ;
Sahbani, Anis ;
Yousef, Amr .
IEEE ACCESS, 2025, 13 :75847-75860
[47]   Automated detection of atrial fibrillation using long short-term memory network with RR interval signals [J].
Faust, Oliver ;
Shenfield, Alex ;
Kareem, Murtadha ;
San, Tan Ru ;
Fujita, Hamido ;
Acharya, U. Rajendra .
COMPUTERS IN BIOLOGY AND MEDICINE, 2018, 102 :327-335
[48]   Bi-Directional Long Short-Term Memory Neural Network Modeling of Data Retention Characterization in 3-D Triple-Level Cell NAND Flash Memory [J].
Jang, Hyundong ;
Park, Chanyang ;
Nam, Kihoon ;
Yun, Hyeok ;
Cho, Kyeongrae ;
Yoon, Jun-Sik ;
Choi, Hyun-Chul ;
Kang, Ho-Jung ;
Park, Min Sang ;
Sim, Jaesung ;
Baek, Rock-Hyun .
IEEE TRANSACTIONS ON ELECTRON DEVICES, 2022, 69 (08) :4241-4247
[49]   Automated Sleep Apnea Detection in Raw Respiratory Signals Using Long Short-Term Memory Neural Networks [J].
Van Steenkiste, Tom ;
Groenendaal, Willemijn ;
Deschrijver, Dirk ;
Dhaene, Tom .
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2019, 23 (06) :2354-2364
[50]   Spatial-temporal features-based EEG emotion recognition using graph convolution network and long short-term memory [J].
Zheng, Fa ;
Hu, Bin ;
Zheng, Xiangwei ;
Zhang, Yuang .
PHYSIOLOGICAL MEASUREMENT, 2023, 44 (06)