Application of LDA and SVM method in fault diagnosis of chemical process

被引：0

作者：

Ji F.-C. ^{[1
,2
]}

Yu Y.-S. ^{[1
]}

Zhang Z.-X. ^{[1
,2
]}

机构：

[1] School of Chemical Engineering and Technology, Xi'an Jiaotong University, Xi'an

[2] State Key Laboratory of Multiphase Flow in Power Engineering, Xi'an Jiaotong University, Xi'an

来源：

Gao Xiao Hua Xue Gong Cheng Xue Bao/Journal of Chemical Engineering of Chinese Universities | 2020年 / 34卷 / 02期

关键词：

Fault diagnosis; Linear discriminant analysis; Support vector machine; Tennessee-Eastman;

D O I：

10.3969/j.issn.1003-9015.2020.02.025

中图分类号：

学科分类号：

摘要：

Based on the variety and high dimensionality of the data and also the characteristic of repetitive risks in complicated chemical processes, a fault diagnosis method based on linear discriminant analysis (LDA) and support vector machine (SVM) was proposed combined with the grid search (GS) and K-fold cross validation (K-CV) theory. In this method, LDA is used to map the normal operation and five types of fault data by vectorization, compressing the dimensions of the feature space, extracting and reconstructing the feature information. Subsequently, the optimal parameters of SVM model are established for the processed data by using GS and K-CV to diagnose faults. In this work, the introduced LDA_SVM mixed model is compared with SVM and PCA (principal component analysis)_SVM fault diagnosis models, where the new method proved to be superior with fast convergence, high recognition rates and robustness. In this work, it is also showed that accuracy of diagnosis results for the six types of running modes in chemical process has reached 93.9% for the proposed method. © 2020, Editorial Board of "Journal of Chemical Engineering of Chinese Universities". All right reserved.

引用

页码：487 / 494

页数：7

共 20 条

[1] QIAN F, DU W L, ZHONG W M, Et al., Problems and challenges of smart optimization manufacturing in petrochemical industries, Acta Automatica Sinica, 43, 6, pp. 893-901, (2017)
[2] XIE Y, ZHANG T., A fault diagnosis approach using SVM with data dimension reduction by PCA and LDA method, Chinese Automation Congress, (2016)
[3] XU Y, DENG X G, ZHONG N., A fault diagnosis method for multimode processes based on ICA mixture models, CIESC Journal, 67, 9, pp. 3793-3803, (2016)
[4] BO C M, QIAO X, ZHANG G M, Et al., ICA-SVM based fault diagnosis method for complex chemical process, CIESC Journal, 60, 9, pp. 2259-2264, (2009)
[5] LI G X, WANG L, LI J D, Et al., Modeling of hydrogen recovery membrane separation process based on PCA-LSSVM, Journal of Chemical Engineering of Chinese Universities, 27, 5, pp. 877-883, (2013)
[6] CHANG Y Q, WNAG S, WANG F L, Et al., Process monitoring method based on multiple PCA models, Chinese Journal of Scientific Instrument, 35, 4, pp. 901-908, (2014)
[7] GUO J Y, LIU Y C, LI Y., A fault detection method based on improved local entropy PCA for industrial processes, Journal of Chemical Engineering of Chinese Universities, 33, 4, pp. 922-932, (2019)
[8] HE F, DU W L, QIAN F., Multifaults classification method based on PCA_SVM and its application to the TE process, Computers and Applied Chemistry, 27, 10, pp. 1321-1324, (2010)
[9] HUANG D R, CHEN C S, SUN G X, Et al., Linear discriminant analysis and back propagation neural network cooperative diagnosis method for multiple faults of complex equipment bearings, Acta Armamentarii, 38, 8, pp. 1649-1657, (2017)
[10] CHENG Z, ZHU A S, CHEN D Z., Fault diagnosis of chemical process using isometric feature mapping and linear discriminant analysis, CIESC Journal, 60, 1, pp. 122-126, (2009)

← 1 2 →