A dynamic-inner convolutional autoencoder for process monitoring

•A novel deep learning method named DiCAE is proposed for process monitoring from the dynamic perspective.•1-dimensional CNN is adopted as the layer structure of autoencoder for extracting temporal features of process variables.•A vector autoregressive model is innovatively incorporated into the aut...

Full description

Saved in:
Bibliographic Details
Published in:Computers & chemical engineering Vol. 158; p. 107654
Main Authors: Zhang, Shuyuan, Qiu, Tong
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.02.2022
Subjects:
1D convolutional neural network
Dynamic data modeling
Fault detection
Process monitoring
Vector autoregressive model
Process monitoring
Vector autoregressive model
1D convolutional neural network
Fault detection
Dynamic data modeling
ISSN:0098-1354
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•A novel deep learning method named DiCAE is proposed for process monitoring from the dynamic perspective.•1-dimensional CNN is adopted as the layer structure of autoencoder for extracting temporal features of process variables.•A vector autoregressive model is innovatively incorporated into the autoencoder latent space to capture process dynamics.•Comparing to other monitoring methods, DiCAE exhibits an outstanding performance on processing nonlinear data and detecting dynamic variations. Modern manufacturing industries are urgently demanding intelligent process monitoring systems for plant maintenance and accident prevention in the Industry 4.0 era. With the rapid development of deep learning, data-driven process monitoring methods are attracting wide attention and have been applied to many processes. However, most deep learning methods do not model process latent dynamics and are deficient to detect dynamic variations. In this work, a novel dynamic-inner convolutional autoencoder (DiCAE) is proposed. Unlike previous autoencoders that only focus on input reconstruction, DiCAE innovatively integrates a vector autoregressive model into a 1-dimensional convolutional autoencoder to monitor nonlinear processes, as well as capture process dynamics. When applied to a numerical simulation, DiCAE could detect the dynamic variation and distinguish different process data into separate clusters with an intuitive visualization, while other conventional methods cannot. The effectiveness of DiCAE is also demonstrated on the benchmark Tennessee Eastman process.
ISSN:0098-1354
DOI:10.1016/j.compchemeng.2021.107654