One-step-ahead predictive control based on sparse kernel learning with polynomial kernel and its application to chemical processes

LIU Yi; WANG Haiqing; LI Ping

您当前的位置：

首页 >

文章列表页 >

One-step-ahead predictive control based on sparse kernel learning with polynomial kernel and its application to chemical processes

更新时间：2025-12-10

- One-step-ahead predictive control based on sparse kernel learning with polynomial kernel and its application to chemical processes
- CIESC Journal Issue 10, Pages: 2541-2545(2008)
- 作者机构：
  
  1. 工业控制技术国家重点实验室
  2. 浙江大学工业控制研究所
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Online First：05 October 2008，
  
  Published：05 October 2008
- 稿件说明：
移动端阅览
LIU Yi, WANG Haiqing, LI Ping. One-step-ahead predictive control based on sparse kernel learning with polynomial kernel and its application to chemical processes[J]. CIESC Journal, 2008, (10): 2541-2545.
DOI：

LIU Yi, WANG Haiqing, LI Ping. One-step-ahead predictive control based on sparse kernel learning with polynomial kernel and its application to chemical processes[J]. CIESC Journal, 2008, (10): 2541-2545. DOI：

摘要

提出一种基于稀疏核学习辨识模型的单步预测控制（sparse kernel learning one-step-ahead predictive control，SKL-OPC）框架，并推导了该框架下采用多项式核的一种控制算法。该算法在求取最优控制律时可将调节变量从目标函数分离出来，并最终转化为求解一奇数次代数方程根的问题。因此无需复杂的非线性优化技术，且克服了基于二次多项式核辨识模型不准确造成控制算法失效的缺点。在一非线性连续搅拌反应釜的控制研究表明了该方法的有效性和优越性。

Abstract

A novel control framework based on sparse kernel learning one-step-ahead predictive control (SKL-OPC) was presented for the general unknown nonlinear processesThe polynomial kernel function was adopted to derive a simple control strategy as a natural extension of SKLOPCThe manipulated input can be separated from the control performance index due to the special structure of polynomial kernelConsequently

the control problem was resolved by solving the roots of an odddegree polynomial equationThe proposed control strategy did not require the nonlinear optimization technique

which resulted in a small computation scale and made it very suitable for realtime controlApplication of the proposed approach to a highly nonlinear continuous stirred tank reactor indicated its validity and showed superior performance

compared to other methods.

关键词

Keywords

references

Views

240

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Physics-informed spatio-temporal graph convolutional network for fermentation processes

Research on the characterization of the molecular weight and its distribution of perfluoropolyether

Corrosion health status assessment method for refining unit pipeline based on GLAE-MLP

Methods of adaptive prediction and abnormal states traceability for sulphur content in flue gas desulfurization process

Recent advances in machine learning for modeling and control of crystallization processes

Related Author

No data

Related Institution

No data

⁰