Deep Variational Autoencoder Classifier for Intelligent Fault Diagnosis Adaptive to Unseen Fault Categories

被引:65
作者
He, Anqi [1 ]
Jin, Xiaoning [1 ]
机构
[1] Northeastern Univ, Predict Informat Res Lab, Boston, MA 02115 USA
基金
美国国家科学基金会;
关键词
Training; Anomaly detection; Probabilistic logic; Feature extraction; Fault diagnosis; Computational modeling; Standards; Ball bearing; deep learning (DL); deep variational autoencoder (VAE); intelligent fault diagnostics; novelty detection; ROTATING MACHINERY; NETWORKS;
D O I
10.1109/TR.2021.3090310
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
With the rapid development of artificial intelligence (AI) in recent years, fault diagnostics for industrial applications have leaped toward partially or fully automatic provided by the capability of analyzing massive condition monitoring data from sensors and actuators. Generally, AI-based fault diagnostics can achieve high accuracy when failure types appear in training dataset and testing dataset are the same. These diagnostic methods could be invalidated for applications dealing with unprecedented faults because the pretrained classifier for diagnostics tends to misclassify the novel instances into existing known classes. In order to address these limitations of conventional diagnostic approaches, we propose a unified diagnostics framework that can achieve novel fault detection and known fault classification tasks together. Through jointly training a variational autoencoder and a deep neural networks classifier, we convert the original entangled raw data into latent variables with Gaussian probabilistic distributions in the latent space and utilize the probabilistic latent variables to detect novel samples against known fault classes or classify them into one of the existing fault classes if they are not novel. The effectiveness of our proposed joint-training framework is validated through experimental studies on two different bearing datasets. Compared with the state-of-the-art methods in the literature, our unified framework is able to not only accurately detect the novel fault classes but also achieve high classification accuracy of known fault classes.
引用
收藏
页码:1581 / 1595
页数:15
相关论文
共 32 条
[1]   Fault Detection and Severity Identification of Ball Bearings by Online Condition Monitoring [J].
Abdeljaber, Osama ;
Sassi, Sadok ;
Avci, Onur ;
Kiranyaz, Serkan ;
Ibrahim, Abdelrahman Aly ;
Gabbouj, Moncef .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2019, 66 (10) :8136-8147
[2]   Fault Detection and Identification Methodology Under an Incremental Learning Framework Applied to Industrial Machinery [J].
Carino, Jesus A. ;
Delgado-Prieto, Miguel ;
Antonio Iglesias, Jose ;
Sanchis, Araceli ;
Zurita, Daniel ;
Millan, Marta ;
Ortega Redondo, Juan Antonio ;
Romero-Troncoso, Rene .
IEEE ACCESS, 2018, 6 :49755-49766
[3]  
Doersch C., 2021, ARXIV PREPRINT ARXIV
[4]   LEFE-Net: A Lightweight Efficient Feature Extraction Network With Strong Robustness for Bearing Fault Diagnosis [J].
Fang, Hairui ;
Deng, Jin ;
Zhao, Bo ;
Shi, Yan ;
Zhou, Jianye ;
Shao, Siyu .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2021, 70
[5]   Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings [J].
Gan, Meng ;
Wang, Cong ;
Zhu, Chang'an .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2016, 72-73 :92-104
[6]  
Goodfellow I, 2016, ADAPT COMPUT MACH LE, P1
[7]   A recurrent neural network based health indicator for remaining useful life prediction of bearings [J].
Guo, Liang ;
Li, Naipeng ;
Jia, Feng ;
Lei, Yaguo ;
Lin, Jing .
NEUROCOMPUTING, 2017, 240 :98-109
[8]  
Hendrycks D, 2019, P INT C LEARN REPR
[9]   Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data [J].
Jia, Feng ;
Lei, Yaguo ;
Lin, Jing ;
Zhou, Xin ;
Lu, Na .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2016, 72-73 :303-315
[10]  
Jin B., 2019, 2019 IEEE International Conference on Prognostics and Health Management (ICPHM), P1