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

Yiming Bai; Shuaiyu Xiang; Feifan Cheng; Jinsong Zhao

Your Location：

Home >

Browse articles >

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

Full Length Article | Updated：2026-01-06

- A dynamic-inner LSTM prediction method for key alarm variables forecasting in chemical process
- Chinese Journal of Chemical Engineering Vol. 55, Issue 3, Pages: 266-276(2023)
- Affiliations：
  
  1. Department of Chemical Engineering, Tsinghua University,Beijing,China,100084
  2. Sinopec Engineering Incorporation,Beijing,China,100084
  3. Beijing Key Laboratory of Industrial Big Data System and Application, Tsinghua University,Beijing,China,100084
- Author bio：
- Funds：
- DOI：
  CLC：
- Published：2023
- Accepted：
Scan QR Code
Yiming Bai, Shuaiyu Xiang, Feifan Cheng, Jinsong Zhao. A dynamic-inner LSTM prediction method for key alarm variables forecasting in chemical process[J]. Chinese Journal of Chemical Engineering, 2023, 55(3): 266-276.
DOI：

Yiming Bai, Shuaiyu Xiang, Feifan Cheng, Jinsong Zhao. A dynamic-inner LSTM prediction method for key alarm variables forecasting in chemical process[J]. Chinese Journal of Chemical Engineering, 2023, 55(3): 266-276. DOI：

摘要

Abstract

With the increase in the complexity of industrial system

simply detecting and diagnosing a fault may be insufficient in some cases

and prognosing the fault ahead of time could have a certain necessity. Accurate prediction of key alarm variables in chemical process can indicate the possible change to reduce the probability of abnormal conditions. According to the characteristics of chemical process data

this work proposed a key alarm variables prediction model in chemical process based on dynamic-inner principal component analysis (DiPCA) and long short-term memory (LSTM). DiPCA is used to extract the most dynamic components for prediction. While LSTM is used to learn the relationship and predict the key alarm variables. This work used a simulation data set and a real hydrogenation process data set for applications and explained the model validity from the essential characteristics. Comparison of results with different models shows that our model has better prediction accuracy and performance

which can provide the basis for fault prognosis and health management.

关键词

Keywords

references

Views

411

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

Early identification of process deviation based on convolutional neural network

Attention-based long short-term memory fully convolutional network for chemical process fault diagnosis

Optimization of chemical looping hydrogen generation process via Aspen Plus—Machine learning integration

Research on composite scale inhibitors for inhibiting calcium carbonate scaling in high temperature geothermal fluid

Multi-dimensional key performance indicators construction methodology for the process safety management

Related Author

Fangyuan Ma

Cheng Ji

Jingde Wang

Wei Sun

Shanwei Xiong

Li Zhou

Yiyang Dai

Xu Ji

Related Institution

College of Chemical Engineering, Beijing University of Chemical Technology

Center of Process Monitoring and Data Analysis, Wuxi Research Institute of Applied Technologies, Tsinghua University

School of Chemical Engineering, Sichuan University

Key Laboratory of Energy Thermal Conversion and Control of Ministry of Education, School of Energy and Environment, Southeast University

State Key Laboratory of Low-carbon Smart Coal-fired Power Generation and Ultra-clean Emission, China Energy Science and Technology Research Institute Co.,Ltd.

⁰