Early identification of process deviation based on convolutional neural network

Fangyuan Ma; Cheng Ji; Jingde Wang; Wei Sun

Your Location：

Home >

Browse articles >

Early identification of process deviation based on convolutional neural network

Full Length Article | Updated：2026-01-06

- Early identification of process deviation based on convolutional neural network
- Early identification of process deviation based on convolutional neural network
- 中国化学工程学报（英文版） 2023年56卷第4期页码：104-118
- Affiliations：
  
  1. College of Chemical Engineering, Beijing University of Chemical Technology,Beijing,China,100029
  2. Center of Process Monitoring and Data Analysis, Wuxi Research Institute of Applied Technologies, Tsinghua University,Wuxi,China,214072
- Author bio：
- Funds：
- DOI：
  中图分类号：
- 纸质出版：2023
- Accepted：
Scan QR Code
Fangyuan Ma, Cheng Ji, Jingde Wang, 等. Early identification of process deviation based on convolutional neural network[J]. 中国化学工程学报（英文版）, 2023,56(4):104-118.

Fangyuan Ma, Cheng Ji, Jingde Wang, Wei Sun. Early identification of process deviation based on convolutional neural network[J]. Chinese Journal of Chemical Engineering, 2023, 56(4): 104-118.
Fangyuan Ma, Cheng Ji, Jingde Wang, 等. Early identification of process deviation based on convolutional neural network[J]. 中国化学工程学报（英文版）, 2023,56(4):104-118. DOI：

Fangyuan Ma, Cheng Ji, Jingde Wang, Wei Sun. Early identification of process deviation based on convolutional neural network[J]. Chinese Journal of Chemical Engineering, 2023, 56(4): 104-118. DOI：

摘要

Abstract

A novel process monitoring method based on convolutional neural network (CNN) is proposed and applied to detect faults in industrial process. By utilizing the CNN algorithm

cross-correlation and autocorrelation among variables are captured to establish a prediction model for each process variable to approximate the first-principle of physical/chemical relationships among different variables under normal operating conditions. When the process is operated under pre-set operating conditions

prediction residuals can be assumed as noise if a proper model is employed. Once process faults occur

the residuals will increase due to the changes of correlation among variables. A principal component analysis (PCA) model based on the residuals is established to realize process monitoring. By monitoring the changes in main feature of prediction residuals

the faults can be promptly detected. Case studies on a numerical nonlinear example and data from two industrial processes are presented to validate the performance of process monitoring based on CNN.

关键词

Keywords

references

浏览量

112

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

A blast furnace fault monitoring algorithm with low false alarm rate: Ensemble of greedy dynamic principal component analysis-Gaussian mixture model

A dynamic-inner LSTM prediction method for key alarm variables forecasting in chemical process

Improved process monitoring using the CUSUM and EWMA-based multiscale PCA fault detection framework

Multimodal process monitoring based on transition-constrained Gaussian mixture model

Local component based principal component analysis model for multimode process monitoring