본문 바로가기

A novel hybrid of auto-associative kernel regression and dynamic independent component analysis for fault detection in nonlinear multimode processes

문서 유형
연구출판물 · 학술지 논문
등재
SCIEScopus
저널 순위
JCR Q2Scopus Q1
저널
JOURNAL OF PROCESS CONTROL68 · pp.129 · 2018
피인용
Web of Science 45Scopus 49
FWCI (Scopus)
2.02
JCR IF
JCR 2017 2.787
ISSN
0959-1524

저자

  1. 유정원제1저자Department of Electrical and Computer Engineering, Pusan National University, Busan, South Korea
  2. Yoo, JaeyeongCTO, XEONET Co., Ltd, Seongnam, South Korea
  3. Jang, JaeyelTechnology & Information Department, Technical Solution Center, Korea East-West Power Co., Ltd., Dangjin, South Korea
  4. 박준호Department of Electrical and Computer Engineering, Pusan National University, Busan, South Korea
  5. 김성신교신저자Department of Electrical and Computer Engineering, Pusan National University, Busan, South Korea

초록

With modern industrial processes becoming larger and more complex, we should consider their nonlinear and multimode characteristics carefully for accurate process monitoring and fault detection. In this paper, a novel hybrid of two data-driven techniques-auto-associative kernel regression (AAKR) and dynamic independent component analysis (DICA)-is proposed for fault detection of nonlinear multimode processes. AAKR is a nonparametric multivariate technique; it can effectively deal with nonlinearity and multimodality of target systems by real-time local modeling in accordance with query vectors. Residuals obtained from AAKR usually deviate from Gaussian distribution (i.e., they are non-Gaussian), and there exist auto- and cross-correlations between them. The proposed method detects process faults by applying DICA to the residuals; DICA can capture useful statistical information hidden in the residuals. The validity and effectiveness of the proposed method are illustrated through three popular benchmark problems such as a three-variable multimodal process, a three-variable nonlinear process, and Tennessee Eastman process; the proposed method is also compared with several comparison methods The experimental results demonstrate the superiority of the proposed method, which achieves the best detection rates with reasonable false alarm rates. (C) 2018 Elsevier Ltd. All rights reserved.

키워드

Auto-associative kernel regressionDynamic independent component analysisFault detectionNonlinear multimode processesNEURAL-NETWORKSALGORITHMSDIAGNOSIS

식별자

Scopus EID
2-s2.0-85048229127
WoS UID
000442706100012