• Home
  • Search
  • Deep Discriminative Representation Learning for Nonlinear Process Fault Detection
  • Cite Icon41
  • https://doi.org/10.1109/tase.2019.2956087Copy DOI Icon

Deep Discriminative Representation Learning for Nonlinear Process Fault Detection

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Nonlinear process fault detection remains a challenge, with representation learning being a key step. In this article, a deep neural network (DNN)-based discriminative representation learning approach is proposed to achieve efficient fault detection for nonlinear plant-wide processes. An early-stage fault rarely affects several independent variables concurrently; hence, mutual information-based block division and randomized fault construction are performed to generate faulty validation data. By using the training data from the normal operation training data and the constructed validation data, a DNN with stacked autoencoders and a softmax classifier is trained to generate discriminative representations that maximize the capability of discriminating normal and abnormal statuses. Finally, on the basis of the learned deep discriminative representations, support vector data description is employed to discriminate the normal and abnormal process statuses. The proposed monitoring approach is tested on a numerical example and an industrial tail-gas treatment process, through which the efficiency is verified. Note to Practitioners —A modern process is generally characterized by a large scale and complex nonlinear correlation, and monitoring of such nonlinear plant-wide processes is imperative. Nowadays, a large amount of process data is generally available, and deep neural network-based monitoring is promising in dealing with such data on nonlinear processes. This article proposes a deep discriminative representation learning method for efficient nonlinear plant-wide process monitoring. The key idea is to first decompose a large-scale process into multiple units according to a variable relationship, and then generate faulty validation data based on randomized fault construction. Then, deep discriminative representations are learned by optimizing a stacked autoencoder-based deep neural network (DNN). This article provides guidelines for designing an efficient monitoring algorithm for plant-wide nonlinear processes in the industrial big data environment.

Similar Papers
  • Research Article
  • Citations7

Data‐driven nonlinear chemical process fault diagnosis based on hierarchical representation learning

  • May 04, 2020
  • The Canadian Journal of Chemical Engineering
  • Yang Wang +1
  • Conference Article

Incipient Fault Detection of Nonlinear Processes Based on Probablility Related SVDD in Local Variable Field

  • Nov 06, 2020
  • Xiaohui Wang +3
  • Research Article
  • Citations53

Machine learning technique for data-driven fault detection of nonlinear processes

  • Jul 17, 2019
  • Journal of Intelligent Manufacturing
  • Maroua Said +2
  • Conference Article
  • Citations4

Outlier detection of business process based on support vector data description

  • Aug 01, 2009
  • Liang Quan +1
  • Conference Article
  • Citations2

Nonlinear process monitoring using dynamic kernel slow feature analysis and support vector data description

  • May 01, 2013
  • Deng Xiaogang +1
  • Research Article
  • Citations3

Plantwide operability assessment for nonlinear processes using a microscopic level network analysis

  • Jul 23, 2011
  • Chemical Engineering Research and Design
  • Ridwan Setiawan +1
  • Research Article
  • Citations26

Mutual information-based sparse multiblock dissimilarity method for incipient fault detection and diagnosis in plant-wide process

  • Sep 27, 2019
  • Journal of Process Control
  • Jing Zeng +3
  • Research Article
  • Citations16

A Novel Distributed CVRAE-Based Spatio-Temporal Process Monitoring Method With Its Application

  • Nov 01, 2023
  • IEEE Transactions on Industrial Informatics
  • Peng Tang +3
  • Research Article
  • Citations13

Parity-based robust data-driven fault detection for nonlinear systems using just-in-time learning approach

  • Jan 08, 2020
  • Transactions of the Institute of Measurement and Control
  • Muhammad Asim Abbasi +6
  • Research Article
  • Citations2

Self-organised maps for online detection of faults in non-linear industrial processes

  • Jan 01, 2010
  • International Journal of Automation and Control
  • M Jeevan +2
  • Research Article

Learning discriminative representations from integrated features for DOA estimation

  • Nov 19, 2025
  • Journal of King Saud University Computer and Information Sciences
  • Qi You +1
  • Conference Article
  • Citations12

Deep Discriminative Representation Learning for Face Verification and Person Re-Identification on Unconstrained Condition

  • Oct 01, 2018
  • Jongmin Yu +3
  • Research Article
  • Citations41

Learning deep discriminative representations with pseudo supervision for image clustering

  • Apr 06, 2021
  • Information Sciences
  • Weibo Hu +4
  • Research Article
  • Citations22

Decentralized plant-wide monitoring based on mutual information-Louvain decomposition and support vector data description diagnosis

  • Jul 20, 2022
  • ISA Transactions
  • Jing Wang +4
  • Research Article
  • Citations4

Deep multi-sphere support vector data description based on disentangled representation learning

  • Jul 27, 2024
  • Pattern Recognition
  • Hong-Jie Xing +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.