A fault diagnosis method based on improved kernel Fisher

MA Liling; XU Fafu; WANG Junzheng

doi:10.11949/j.issn.0438-1157.20161000

您当前的位置：

首页 >

文章列表页 >

A fault diagnosis method based on improved kernel Fisher

更新时间：2025-12-10

- A fault diagnosis method based on improved kernel Fisher
- CIESC Journal Issue 3, Pages: 1041-1048(2017)
- 作者机构：
  
  北京理工大学自动化学院,北京,100081
- 作者简介：
- 基金信息：
- DOI：10.11949/j.issn.0438-1157.20161000
  CLC： P277
- Online First：05 March 2017，
  
  Published：05 March 2017
- 稿件说明：
移动端阅览
MA Liling, XU Fafu, WANG Junzheng. A fault diagnosis method based on improved kernel Fisher[J]. CIESC Journal, 2017, (3): 1041-1048.
DOI：

MA Liling, XU Fafu, WANG Junzheng. A fault diagnosis method based on improved kernel Fisher[J]. CIESC Journal, 2017, (3): 1041-1048. DOI： 10.11949/j.issn.0438-1157.20161000.

摘要

针对化工过程故障数据呈非线性分布，数据类别复杂，难以进行故障诊断的问题，提出一种改进核Fisher的故障诊断方法。对于原始样本数据投影后，样本出现因类间距离存在很大差异性而导致部分类别样本存在混叠的现象，以及不同类别的边界数据归类模糊问题，给出了统一的解决办法。该方法首先采用改进类间距的方法来改变样本投影空间的分布，使得样本具有较好的投影效果，然后通过定义阈值参数来筛选出边界数据，对于边界数据，采用改进的K近邻（K-NN）算法来分类，对于非边界数据，采用马氏距离来分类。最后在TE过程中进行了仿真验证，结果表明方法在兼顾了故障诊断时间的同时，有效提高了故障诊断精度。

Abstract

A fault diagnosis method of kernel Fisher projection was proposed to solve issues of nonlinear data

complex classes

and difficult fault-diagnosing in chemical processes. The proposed method provided a uniform solution for partial sample mix-up induced by a large difference in category distances and nebulous classification of different category's boundary data after projection of the original data sample. First

an improved category distance was used to change sample distribution in the projection space so that the sample had a good projection. Then

boundary data was screened out by a defined threshold parameter and classified by improved K-Nearest Neighbor (K-NN) algorithm

which none-boundary data was classified by Mahalanobis distance. Simulation in a TE process showed that training accuracy was increased by 2.25% and testing accuracy was increased by 2.41% in the first experiment

whereas training accuracy was increased by 4.75% and testing accuracy was increased by 6.75% in the second experiment. Therefore

the method improved both fault diagnosis time and accuracy.

关键词

Keywords

references

Views

198

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Fault diagnosis of cathode material sintering based on temporal graph convolutional network

A two-stage dual-channel deep learning model for chemical fault classification

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

Research and comparison of throttling and venting characteristics of CO2 pipelines in different phase states

Soft sensor modeling based on MHSA-LSTM and its application in chemical process

Related Author

YANG Peng

CHEN Ning

LIU Yuepeng

XIE Muyan

LIU Xiuyue

ZHANG Jiaxin

SONG Chaoyang

DONG Lichun

Related Institution

School of Automation, Central South University

National Engineering Research Centre of Advanced Energy Storage Materials

School of Chemistry and Chemical Engineering, Chongqing University

College of Chemical Engineering, Hebei Normal University of Science and Technology

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

⁰