Fault detect algorithm of chemical process based on kernel T-PLS

ZHAO Xiaoqiang; XUE Yongfei

doi:10.3969/j.issn.0438-1157.2013.12.050

您当前的位置：

首页 >

文章列表页 >

Fault detect algorithm of chemical process based on kernel T-PLS

更新时间：2025-12-10

- Fault detect algorithm of chemical process based on kernel T-PLS
- CIESC Journal Issue 12, Pages: 4608-4614(2013)
- 作者机构：
  
  1. 兰州理工大学电气工程与信息工程学院,甘肃,兰州,730050
  2. 甘肃省制造业信息化工程技术研究中心,甘肃,兰州,730050
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0438-1157.2013.12.050
  CLC： P277
- Online First：05 December 2013，
  
  Published：05 December 2013
- 稿件说明：
移动端阅览
ZHAO Xiaoqiang, XUE Yongfei. Fault detect algorithm of chemical process based on kernel T-PLS[J]. CIESC Journal, 2013, (12): 4608-4614.
DOI：

ZHAO Xiaoqiang, XUE Yongfei. Fault detect algorithm of chemical process based on kernel T-PLS[J]. CIESC Journal, 2013, (12): 4608-4614. DOI： 10.3969/j.issn.0438-1157.2013.12.050.

摘要

针对全潜结构投影法（T-PLS）在检测非线性过程故障时误报率和漏报率较高的缺点，提出了基于核函数的全潜结构投影法（KT-PLS）。该算法通过核函数将过程数据从低维输入空间非线性地映射到高维特征空间，实现非线性问题的线性化；然后在质量变量的引导下将特征空间分为与质量直接相关、与质量正交、与质量无关和残差四个子空间；最后分别构建D和Q统计量进行故障检测。将该算法应用到Tennessee Eastman process（TEP），多种故障模式下的仿真结果表明，KT-PLS比T-PLS更适合监控具有强非线性的生产过程。

Abstract

According to the shortcoming of total projection to latent structure (T-PLS) algorithm which has a higher false alarm rate and a higher missing report rate when it is used to detect fault in the nonlinear process

a new algorithm which is a combination of kernel function and T-PLS (KT-PLS) is proposed in this paper. Firstly

the low dimension process data is projected to the high dimension feature space through kernel function

which can resolve the nonlinear problem.Secondly

the feature space is divided into four subspaces by the guiding of quality variable.These four subspaces include the quality directly correlated subspace

the quality orthogonal subspace

the quality uncorrelated subspace and the residual subspace. Finally

statistics D and Q are used to detect fault respectively.Applying this algorithm to the Tennessee Eastman process (TEP)

the simulation results of various fault modes show that KT-PLS is better than T-PLS in monitoring strong nonlinear system.

关键词

Keywords

references

Views

482

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Analyzing time-lag effect of downcomer for control of ethylene column

Improved information flow diagram and its application in distillation column modeling and simulation process

Chemical process fault detection and risk early warning based on SlowFast-Transformer

ANN-GA integrated framework for intelligent screening of ORC mixture working fluids and performance optimization

Performance and application of specialized dry water material spraying agents

Related Author

HUANG Dong

ZHAO Minshuai

LUO Xionglin

SUN Jun

ZHANG Beike

MA Xin

WU Chongguang

WANG Ruiqi

Related Institution

Department of Automation, China University of Petroleum

College of Information Science & Technology, Beijing University of Chemical Technology

College of Chemistry and Chemical Engineering, Xi’an University of Science and Technology

Shaanxi Provincial Academy of Environmental Science

Institute of Chemical Process Systems Engineering, School of Chemical Engineering, Dalian University of Technology

⁰