Deep Canonical Correlation Analysis Using Sparsity-Constrained Optimization for Nonlinear Process Monitoring

This article proposes an efficient nonlinear process monitoring method (DCCA-SCO) by integrating canonical correlation analysis (CCA), deep autoencoder neural networks (DAENNs), and sparsity-constrained optimization (SCO). Specifically, DAENNs are first used to learn a nonlinear function automatical...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on industrial informatics 2022-10, Vol.18 (10), p.6690-6699
Main Authors: Xiu, Xianchao, Miao, Zhonghua, Yang, Ying, Liu, Wanquan
Format: Article
Language:English
Subjects:
Canonical correlation analysis (CCA)
Correlation
Correlation analysis
deep autoencoder neural networks (DAENNs)
Diesel generators
Fault detection
Feature extraction
Image reconstruction
Informatics
Kernel
Monitoring
Neural networks
Optimization
process monitoring (PM)
Redundancy
Representations
sparsity-constrained optimization (SCO)
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This article proposes an efficient nonlinear process monitoring method (DCCA-SCO) by integrating canonical correlation analysis (CCA), deep autoencoder neural networks (DAENNs), and sparsity-constrained optimization (SCO). Specifically, DAENNs are first used to learn a nonlinear function automatically, which characterizes intrinsic features of the original process data. Then, the CCA is performed in that low-dimensional representation space to extract the most correlated variables. In addition, the SCO is imposed to reduce the redundancy of the hidden representation. Unlike other deep CCA methods, the DCCA-SCO provides a new nonlinear method that is able to learn a nonlinear mapping with a sparse prior. The validity of the proposed DCCA-SCO is extensively demonstrated on the benchmark Tennessee Eastman (TE) process and the diesel generator process. In particular, compared with the classical CCA, the fault detection rate is increased by 8.00% for the fault IDV(11) in the TE process.
ISSN:1551-3203
1941-0050
DOI:10.1109/TII.2021.3121770