Fault Diagnosis of Industrial Process Based on FDKICA-PCA

ZHANG Jing; ZHU Fei-fei; LIU Jia-xing; WANG Jiang-tao

doi:10.15938/j.jhust.2018.06.016

Chinese

您当前的位置：

首页 >

文章列表页 >

Fault Diagnosis of Industrial Process Based on FDKICA-PCA

更新时间：2026-08-31

- Fault Diagnosis of Industrial Process Based on FDKICA-PCA
- Vol. 23, Issue 6, Pages: 88-93(2018)
- 作者机构：
  
  1. 哈尔滨理工大学自动化学院,黑龙江,哈尔滨,150080
  2. 华东师范大学计算机科学与软件工程学院,上海,200062
- 作者简介：
- 基金信息：
- DOI：10.15938/j.jhust.2018.06.016
  CLC： TP273
- Published：2018
- 稿件说明：
移动端阅览
ZHANG Jing, ZHU Fei-fei, LIU Jia-xing, et al. Fault Diagnosis of Industrial Process Based on FDKICA-PCA[J]. 2018, 23(6): 88-93.
DOI：

ZHANG Jing, ZHU Fei-fei, LIU Jia-xing, et al. Fault Diagnosis of Industrial Process Based on FDKICA-PCA[J]. 2018, 23(6): 88-93. DOI： 10.15938/j.jhust.2018.06.016.

摘要

摘要:由于故障诊断中忽略生产过程中自相关与滞后相关的动态特性

核独立成分分析主成分分析（KICA-PCA）方法缺少可用的变量贡献分析，对微小故障和渐变故障检测效果很差，因此提出基于小波包滤波的动态核独立成分分析主成分分析（FDKICA-PCA）的故障诊断方法。该方法将小波包滤波理论与AR模型预测数据特性融入到KICA-PCA中，进而提取过程变量自相关、滞后相关的特征信息。文中采用KICA-PCA算法提取过程变量的独立成分与主成分以确定3个监控指标T.2、SPE、I.2的控制限，利用非线性贡献图进行故障诊断，并通过田纳西过程仿真结果验证了FDKICA-PCA方法的优越性。

Abstract

Abstract:Because the dynamic characteristics of autocorrelation and lag correlation in production process are neglected in fault diagnosis

Kernel Independent Component AnalysisPrincipal Component Analysis (KICAPCA) is very poor in detecting small and gradual faults because of lacking available variable contribution analysis.In this paper

a dynamic kernel independent component analysis (KICAPCA) fault diagnosis method based on wavelet packet filtering is proposed.This method integrates wavelet packet filtering theory and AR model prediction data characteristics into KICAPCA to extract the feature information of process variable autocorrelation and lagrelated .In this paper

KICAPCA algorithm is used to extract the independent components and principal components of process variables to determine the control limits of three monitoring indicators T2

SPE

I2.Nonlinear contribution graph is used for fault diagnosis

and the advantage of FDKICAPCA method is verified by simulation results of Tennessee process.

关键词

Keywords

references

Views

345

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Short Term Load Forecasting Based on Improved Neural Network Algorithm

Damage Analysis and Optimal Design of Micro-structure Milling Cutter Based on Peridynamics

Data Center Server Energy Consumption Prediction Based on xLSTM

Localization of Geometric Tolerance Fault Points on the Inner Surface of Compressor Casing

New Constant of Von Neumann-Jordan Constant Type in Banach Space

Related Author

WEI Qi

YANG Ming

Related Institution

Harbin University of Science and Engineering Electricity and Electronic Engineering Academy

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰