Fault diagnosis of nonlinear process based on KCPLS reconstruction

被引：44

作者：

Zhang, Yingwei ^{[1
]}

Sun, Rongrong ^{[1
]}

Fan, Yunpeng ^{[1
]}

机构：

[1] Northeastern Univ, State Key Lab Synthet Automat Proc Ind, Shenyang 110819, Liaoning, Peoples R China

来源：

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS | 2015年 / 140卷

关键词：

Kernel concurrent projection to latent structure (KCPLS); Fault reconstruction; Fault diagnosis; Fault-relevant direction; PARTIAL LEAST-SQUARES; LATENT STRUCTURES; TOTAL PROJECTION; MULTISCALE KPLS; IDENTIFICATION; RELEVANT; MODEL;

D O I：

10.1016/j.chemolab.2014.10.002

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, a new kernel concurrent projection to latent structure (KCPLS) reconstruction method for process monitoring is proposed. The main contributions of the proposed approach are as follows: (1) the KCPLS method provides a complete monitoring of faults that happen in the predictable output subspace and the unpredictable output-residual subspace; (2) after the fault reconstruction approach is proposed, the fault-relevant direction is determined; (3) the fault is effectively diagnosed compared to the conventional KPLS method. The proposed method is applied to penicillin fermentation process and is compared to the KPLS method. Experiment results show that the KCPLS can more accurately detect the fault compared to the KPLS method. In addition, the fault-relevant direction is identified more effectively by using the KCPLS reconstruction algorithm compared to the KPLS reconstruction approach. (C) 2014 Elsevier B.V. All rights reserved.

引用

页码：49 / 60

页数：12

共 50 条

[21] Comment on "Fault Diagnosis for a Multiblock Batch Process Based on Intermediate Block Dependency Analysis Reconstruction"
Lin, Peter
INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2019, 58 (40) : 18901 - 18901
[22] Sensor Fault Diagnosis and Data Reconstruction Based on MSPCA
Tao, Xu
PROCEEDINGS OF THE 27TH CHINESE CONTROL CONFERENCE, VOL 6, 2008, : 30 - 33
[23] On the the use of reconstruction-based contribution for fault diagnosis
Ji, Hongquan
He, Xiao
Zhou, Donghua
JOURNAL OF PROCESS CONTROL, 2016, 40 : 24 - 34
[24] A new reconstruction-based auto-associative neural network for fault diagnosis in nonlinear systems
Ren, Shaojun
Si, Fengqi
Zhou, Jianxin
Qiao, Zongliang
Cheng, Yuanlin
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2018, 172 : 118 - 128
[25] Incipient fault diagnosis method of nonlinear chemical process based on weighted statistical local KPCA
Deng J.
Deng X.
Cao Y.
Zhang X.
Huagong Xuebao/CIESC Journal, 2019, 70 (07): : 2594 - 2605
[26] Partial Derivate Contribution Plot Based on KPLS-KSER for Nonlinear Process Fault Diagnosis
Zhu, Wenxiang
Zhen, Weiting
Jiao, Jianfang
2019 34RD YOUTH ACADEMIC ANNUAL CONFERENCE OF CHINESE ASSOCIATION OF AUTOMATION (YAC), 2019, : 735 - 740
[27] Data-driven nonlinear chemical process fault diagnosis based on hierarchical representation learning
Wang, Yang
Jiang, Qingchao
CANADIAN JOURNAL OF CHEMICAL ENGINEERING, 2020, 98 (10): : 2150 - 2165
[28] Twofold Weighted-Based Statistical Feature KECA for Nonlinear Industrial Process Fault Diagnosis
Li, Tao
Han, Yongming
Hu, Xuan
Ma, Bo
Geng, Zhiqiang
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2024, : 1 - 10
[29] Closed loop fault diagnosis based on a nonlinear process model and automatic fuzzy rule generation
Füssel, D
Ballé, P
Isermann, R
(SAFEPROCESS'97): FAULT DETECTION, SUPERVISION AND SAFETY FOR TECHNICAL PROCESSES 1997, VOLS 1-3, 1998, : 349 - 354
[30] Process Fault Diagnosis Based on Bayesian Inference
Liu, Jialin
Liu, Shu Jie
Wong, David Shan Hill
23 EUROPEAN SYMPOSIUM ON COMPUTER AIDED PROCESS ENGINEERING, 2013, 32 : 751 - 756

← 1 2 3 4 5 →