|Table of Contents|

 Fault Diagnosis of Industrial Process Based on FDKICAPCA(PDF)

《哈尔滨理工大学学报》[ISSN:1007-2683/CN:23-1404/N]

Issue:
2018年06期
Page:
88-93
Research Field:
计算机与控制工程
Publishing date:

Info

Title:
 Fault Diagnosis of Industrial Process Based on FDKICAPCA
Author(s):
 ZHANG Jing1ZHU Feifei1LIU Jiaxing1WANG Jiangtao2
 1.College of Automation,Harbin University of Science of Technology,Harbin 150080,China;2.School of Computer Science and Software Engineering,East China Normal University,Shanghai 200062,China)
Keywords:
 Keywords:fault diagnosis wavelet packets principal component analysis kernel independent component analysisAR model
PACS:
TP273
DOI:
10.15938/j.jhust.2018.06.016
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.

References:

[1]KOURTI T, MACGREGOR J F Process Analysis, Monitoring and Diagnosis, Using Multivariate Projection Methods[J] Chemometrics & Intelligent Laboratory Systems, 1995, 28(1):3-21
[2]PAUL Nomikos, JOHN F M Multivariate SPC Charts for Monitoring Batch Processes[J] Technometrics, 1995, 37(1):41-59
[3]NDEY C, TATARA E, NAR A Intelligent Realtime Performance Monitoring and Quality Prediction for Batch/fedbatch Cultivations[J] Journal of Biotechnology, 2004, 108(1):61-77
[4]李晗, 萧德云 基于数据驱动的故障诊断方法综述[J]控制与决策, 2011, 26(1):1-9
[5]吕宁, 付元健,白光远 间歇过程的KPCA恒值判定故障诊断模型[J] 哈尔滨理工大学学报, 2015, 20(6):88-92
[6]SCHLKOPF B, SMOLA A, MLLER K R Nonlinear Component Analysis as a Kernel Eigenvalue Problem[J] Neural Computation, 1998, 10(5):1299-1319
[7]CHEN J, LIAO C M Dynamic Process Fault Monitoring Based on Neural Network and PCA[J] Journal of Process Control, 2002, 12(2):277-289
[8]SANG W C, LEE I B Nonlinear Dynamic Process Monitoring Based Ondynamic Kernel PCA[J] Chemical Engineering Science, 2004, 59(24):5897-5908
[9]FAN J, WANG Y Fault Detection and Diagnosis of Nonlinear NonGaussian Dynamic Processes Using Kernel Dynamic Independent Component Analysis[J] Information Sciences, 2014, 259(3):369-379
[10]ZHAO C, GAO F, WANG F Nonlinear Batch Process Monitoring Using PhaseBased KernelIndependent Component AnalysisPrincipal Component Analysis (KICAPCA)[J]Industrial & Engineering Chemistry Research, 2009, 48(20):9163-9174
[11]王莉莉,沈月,陈德运,等PCA与小波变换的ECT图像融合方法[J] 哈尔滨理工大学学报, 2016, 21(4):30-35
[12]FAN J, QIN S J, WANG Y Online Monitoring of Nonlinear Multivariate Industrial Processes Using Filtering KICA–PCA[J] Control Engineering Practice, 2014, 22(1):205–216
[13]HYVRINEN A Fast and Robust Fixedpoint Algorithms for Independent Component Analysis[J] IEEE Transactions on Neural Networks, 1999, 10(3):626-634[14]LEE J M, YOO C K, LEE I B Statistical Process Monitoring with Independent Component Analysis[J] Journal of Process Control, 2004, 14(5):467-485
[15]赵景波,唐勇伟,张磊 基于改进小波变换的故障电弧检测方法的研究[J] 电机与控制学报, 2016, 20(2): 90-97
[16]丁锋,秦峰伟小波降噪及Hilbert变换在电机轴承故障诊断中的应用[J] 电机与控制学报, 2017, 21(6): 89-95
[17]KU W, STORER R H, GEORGAKIS C Disturbance Detection and Isolation by Dynamic Principal Component Analysis[J] Chemometrics & Intelligent Laboratory Systems, 1995, 30(1):179-196
[18]MARTIN E B, MORRIS A J Nonparametric Confidence Bounds for Process Performance Monitoring Charts[J] Journal of Process Control, 1996, 6(6):349-358
[19]ALCALA C F, QIN S J Analysis and Generalization of Fault Diagnosis Methods for Process Monitoring[J] Journal of Process Control, 2011, 21(3):322-330
[20]MS L H C, RUSSELL E L, BRAATZ R D Fault Detection and Diagnosis in Industrial Systems[J] Measurement Science & Technology, 2001, 12(10):1745

Memo

Memo:
-
Last Update: 2019-03-21