Data-driven optimal operation of the industrial methanol to olefin process based on relevance vector machine

Zhiquan Wang; Liang Wang; Zhihong Yuan; Bingzhen Chen

Your Location：

Home >

Browse articles >

Data-driven optimal operation of the industrial methanol to olefin process based on relevance vector machine

Process Systems Engineering and Process Safety | Updated：2026-01-06

- Data-driven optimal operation of the industrial methanol to olefin process based on relevance vector machine
- Chinese Journal of Chemical Engineering Vol. 34, Issue 6, Pages: 106-115(2021)
- Affiliations：
  
  1. Department of Chemical Engineering, Tsinghua University,Beijing,China,100084
  2. State Key Laboratory of Chemical Engineering, Department of Chemical Engineering, Tsinghua University,Beijing,China,100084
- Author bio：
- Funds：
- DOI：
  CLC：
- Published：2021
- Accepted：
Scan QR Code
Zhiquan Wang, Liang Wang, Zhihong Yuan, Bingzhen Chen. Data-driven optimal operation of the industrial methanol to olefin process based on relevance vector machine[J]. Chinese Journal of Chemical Engineering, 2021, 34(6): 106-115.
DOI：

Zhiquan Wang, Liang Wang, Zhihong Yuan, Bingzhen Chen. Data-driven optimal operation of the industrial methanol to olefin process based on relevance vector machine[J]. Chinese Journal of Chemical Engineering, 2021, 34(6): 106-115. DOI：

摘要

Abstract

Methanol to olefin (MTO) technology provides the opportunity to produce olefins from nonpetroleum sources such as coal

biomass and natural gas. More than 20 commercial MTO plants have been put into operation. Till now

contributions on optimal operation of industrial MTO plants from a process systems engineering perspective are rare. Based on relevance vector machine (RVM)

a data-driven framework for optimal operation of the industrial MTO process is established to fully utilize the plentiful industrial data sets. RVM correlates the yield distribution prediction of main products and the operation conditions. These correlations then serve as the constraints for the multi-objective optimization model to pursue the optimal operation of the plant. Nondominated sorting genetic algorithm II is used to solve the optimization problem. Comprehensive tests demonstrate that the ethylene yield is effectively improved based on the proposed framework. Since RVM does provide the distribution prediction instead of point estimation

the established model is expected to provide guidance for actual production operations under uncertainty.

关键词

Keywords

references

Views

326

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

Early identification of process deviation based on convolutional neural network

Multimodal process monitoring based on transition-constrained Gaussian mixture model

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

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

Scheduling and heat integration of multi-product plant based on genetic algorithm

Related Author

Fangyuan Ma

Cheng Ji

Jingde Wang

Wei Sun

Shutian Chen

Qingchao Jiang

Xuefeng Yan

Li Xinyu

Related Institution

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

College of Chemical Engineering, Beijing University of Chemical Technology

Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education, East China University of Science and Technology

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

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

⁰