Data-Driven Fault Diagnosis Using Deep Canonical Variate Analysis and Fisher Discriminant Analysis

Ping Wu, Siwei Lou, Xujie Zhang, Jiajun He, Yichao Liu, Jinfeng Gao

Research output: Contribution to journalArticleScientificpeer-review

Abstract

In this article, a novel data-driven fault diagnosis method by combining deep canonical variate analysis and Fisher discriminant analysis (DCVA-FDA) is proposed for complex industrial processes. Inspired by the recently developed deep canonical correlation analysis, a new nonlinear canonical variate analysis (CVA) called DCVA is first developed by incorporating deep neural networks into CVA. Based on DCVA, a residual generator is designed for the fault diagnosis process. FDA is applied in the feature space spanned by residual vectors. Then, a Bayesian inference classifier is performed in the reduced dimensional space of FDA to label the class of process data. A continuous stirred-tank reactor and an industrial benchmark of the Tennessee Eastman process are carried out to test the performance of DCVA-FDA fault diagnosis. The experimental results demonstrate that the proposed DCVA-FDA fault diagnosis is able to significantly improve the fault diagnosis performance when compared to other methods also examined in this article.

Original languageEnglish
Article number9220844
Pages (from-to)3324-3334
Number of pages11
JournalIEEE Transactions on Industrial Informatics
Volume17
Issue number5
DOIs
Publication statusPublished - 2021

Keywords

  • Bayesian classifier
  • canonical variate analysis (CVA)
  • deep neural networks (DNN)
  • fault diagnosis
  • Fisher discriminant analysis (FDA)
  • residual generator

Fingerprint Dive into the research topics of 'Data-Driven Fault Diagnosis Using Deep Canonical Variate Analysis and Fisher Discriminant Analysis'. Together they form a unique fingerprint.

Cite this