A Deep Learning Based Fault Diagnosis Method Combining Domain Knowledge and Transfer Learning

被引:1
作者
Choudhury, Madhurjya Dev [1 ]
Kleijn, W. Bastiaan [1 ]
Blincoe, Kelly [2 ]
Dhupia, Jaspreet Singh [3 ]
机构
[1] Victoria Univ Wellington, Sch Engn & Comp Sci, Wellington, New Zealand
[2] Univ Auckland, Dept Elect Comp & Software Engn, Auckland, New Zealand
[3] Univ Auckland, Dept Mech & Mechatron Engn, Auckland, New Zealand
来源
2023 29TH INTERNATIONAL CONFERENCE ON MECHATRONICS AND MACHINE VISION IN PRACTICE, M2VIP 2023 | 2023年
关键词
deep learning; fault diagnosis; domain knowledge; transfer learning; pattern recognition;
D O I
10.1109/M2VIP58386.2023.10413425
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Deep learning (DL) based fault diagnosis methods have gained considerable attention in the field of machine health monitoring due to their powerful feature learning capabilities. However, embedding domain diagnosis knowledge into the DL framework to obtain enhanced features having better correlation with the exact health conditions of machine elements for improved fault predictions is still an open challenge. In this paper, a fault diagnosis method combining two-dimensional (2D) image representations of squared envelop spectrum (SES) of vibration signals of bearings, a critical machine element, and a pretrained convolutional neural network (CNN) is proposed. SES is one of the most efficient indicator for the assessment of second order cyclostationary symptoms of damages, which are typically observed in bearings. In this paper, we integrate this knowledge in designing a DL framework for efficient fault diagnosis in bearings. The proposed method is tested and evaluated on an experimental bearing vibration dataset collected under different operating and fault conditions. Experimental results demonstrate that the proposed method can achieve a high diagnosis accuracy and present a better generalization ability both in balanced and imbalanced data scenarios.
引用
收藏
页数:6
相关论文
共 20 条
[1]   Bearing signal models and their effect on bearing diagnostics [J].
Borghesani, P. ;
Smith, W. A. ;
Randall, R. B. ;
Antoni, J. ;
El Badaoui, M. ;
Peng, Z. .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2022, 174
[2]   Testing second order cyclostationarity in the squared envelope spectrum of non-white vibration signals [J].
Borghesani, P. ;
Pennacchi, P. ;
Ricci, R. ;
Chatterton, S. .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2013, 40 (01) :38-55
[3]   Deep Learning based Time-Frequency Image Enhancement Method for Machinery Health Monitoring [J].
Choudhury, Madhurjya D. ;
Blincoe, Kelly ;
Dhupia, Jaspreet S. .
2023 IEEE/ASME INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS, AIM, 2023, :852-857
[4]   A Methodology to Handle Spectral Smearing in Gearboxes Using Adaptive Mode Decomposition and Dynamic Time Warping [J].
Choudhury, Madhurjya D. ;
Hong, Liu ;
Dhupia, Jaspreet S. .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2021, 70
[5]   A novel tacholess order analysis method for bearings operating under time-varying speed conditions [J].
Choudhury, Madhurjya Dev ;
Hong, Liu ;
Dhupia, Jaspreet Singh .
MEASUREMENT, 2021, 186
[6]   An Overview of Fault Diagnosis of Industrial Machines Operating Under Variable Speeds [J].
Choudhury, Madhurjya Dev ;
Blincoe, Kelly ;
Dhupia, Jaspreet Singh .
ACOUSTICS AUSTRALIA, 2021, 49 (02) :229-238
[7]   A Generic Intelligent Bearing Fault Diagnosis System Using Compact Adaptive 1D CNN Classifier [J].
Eren, Levent ;
Ince, Turker ;
Kiranyaz, Serkan .
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2019, 91 (02) :179-189
[8]   Intelligent Fault Diagnosis Method Based on Full 1-D Convolutional Generative Adversarial Network [J].
Guo, Qingwen ;
Li, Yibin ;
Song, Yan ;
Wang, Daichao ;
Chen, Wu .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2020, 16 (03) :2044-2053
[9]   Hierarchical adaptive deep convolution neural network and its application to bearing fault diagnosis [J].
Guo, Xiaojie ;
Chen, Liang ;
Shen, Changqing .
MEASUREMENT, 2016, 93 :490-502
[10]   Convolutional neural network and its pretrained models for image classification and object detection: A survey [J].
Jena, Biswajit ;
Nayak, Gopal Krishna ;
Saxena, Sanjay .
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2022, 34 (06)