Data-Driven Fault Detection of Three-Tank System Applying MWAT-ICA

doi:10.1007/s12204-020-2227-7

J Shanghai Jiaotong Univ Sci ›› 2020, Vol. 25 ›› Issue (5): 659-664.doi: 10.1007/s12204-020-2227-7

Data-Driven Fault Detection of Three-Tank System Applying MWAT-ICA

LIU Mingguang (刘明光), LIAO Yaxuan (廖雅璇), LI Xiangshun (李向舜))

(School of Automation, Wuhan University of Technology, Wuhan 430070, China)

出版日期:2020-10-28 发布日期:2020-09-11
通讯作者: LI Xiangshun (李向舜) E-mail:lixiangshun@whut.edu.cn

Data-Driven Fault Detection of Three-Tank System Applying MWAT-ICA

LIU Mingguang (刘明光), LIAO Yaxuan (廖雅璇), LI Xiangshun (李向舜)

(School of Automation, Wuhan University of Technology, Wuhan 430070, China)

Online:2020-10-28 Published:2020-09-11
Contact: LI Xiangshun (李向舜) E-mail:lixiangshun@whut.edu.cn

摘要/Abstract

摘要： In order to improve monitoring performance of dynamic process, a moving window independent component
analysis method with adaptive threshold (MWAT-ICA) is proposed. On-line fault detection can be realized
by applying moving windows technique, as well as false alarm caused by fluctuation of data can be effectively
avoided by adaptive threshold. The efficiency of the proposed approach is demonstrated with a three-tank system.
The results show that the MWAT-ICA can not only detect the fault quickly, but also has a high fault detection
rate and no false alarm rate under the transient behaviors of the three-water tank and the normal operation
process. These results demonstrate the effectiveness of the method for fault detection on the three-tank system.

关键词: moving window, adaptive threshold, three-tank system, fault detection

Abstract: In order to improve monitoring performance of dynamic process, a moving window independent component
analysis method with adaptive threshold (MWAT-ICA) is proposed. On-line fault detection can be realized
by applying moving windows technique, as well as false alarm caused by fluctuation of data can be effectively
avoided by adaptive threshold. The efficiency of the proposed approach is demonstrated with a three-tank system.
The results show that the MWAT-ICA can not only detect the fault quickly, but also has a high fault detection
rate and no false alarm rate under the transient behaviors of the three-water tank and the normal operation
process. These results demonstrate the effectiveness of the method for fault detection on the three-tank system.

Key words: moving window, adaptive threshold, three-tank system, fault detection

中图分类号:

TP 181

LIU Mingguang, LIAO Yaxuan, LI Xiangshun . Data-Driven Fault Detection of Three-Tank System Applying MWAT-ICA[J]. J Shanghai Jiaotong Univ Sci, 2020, 25(5): 659-664.

参考文献 11

[1]	DING S X, JEINSCH T, DING E L, et al. Application of observer based FDI schemes to the three tank system [C]//European Control Conference. Karlsruhe,Germany: IEEE, 1999: 4438-4443.
[2]	LEI Y, JIA F, LIN J, et al. An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data [J]. IEEE Transactions on Industrial Electronics, 2016, 63(5): 3137-3147.
[3]	KRESTA J V, MACGREGOR J F, MARLIN T E.Multivariate statistical monitoring of process operating performance [J]. The Canadian Journal of Chemical Engineering, 1991, 69(1): 35-47.
[4]	MELLIT A, BENGHANEM M, ARAB A H, et al. A simplified model for generating sequences of global solar radiation data for isolated sites: Using artificial neural network and a library of Markov transition matrices approach [J]. Solar Energy, 2005, 79(5): 469-482.
[5]	MA Y, ZHANG Z B, FENG F, et al. Optimized algorithm for feature extraction based on higher-order statistical moments [J]. Computer Technology and Development,2008, 18(12): 123-126 (in Chinese).
[6]	HYVRINEN A, HURRI J, HOYER P O. Independent component analysis [M]//Natural image statistics.London, UK: Springer, 2009.
[7]	HYV¨ARINEN A, OJA E. Independent component analysis: Algorithms and applications [J]. Neural Networks,2000, 13(4/5): 411-430.
[8]	ZHANG Y W, QIN S J. Fault detection of nonlinear processes using multiway kernel independent component analysis [J]. Industrial & Engineering Chemistry Research, 2007, 46(23): 7780-7787.
[9]	ZHANG Q, HUANG X Q, LIU W B. An effective image retrieval method based on fractal dimension using kernel density estimation [M]//Advanced computer and communication engineering technology.Cham, Switzerland: Springer, 2014: 987-999.
[10]	PONSART J C, THEILLIOL D, NOURA H. Faulttolerant control of a nonlinear system application to a three-tank-system [C]//European Control Conference.Karlsruhe, Germany: IEEE, 1999: 1592-1597.
[11]	HE X, WANG Z D, LIU Y, et al. Fault-tolerant control for an Internet-based three-tank system: Accommodation to sensor bias faults [J]. IEEE Transactions on Industrial Electronics, 2017, 64(3): 2266-2275.

编辑推荐 0

Metrics

阅读次数

全文

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	0	0	0	30

来源	本网站	其他网站

次数	20	10
比例	67%	33%

摘要

574

最新录用	在线预览	正式出版

0	0	574

来源	本网站	其他网站

次数	359	215
比例	63%	37%

Data-Driven Fault Detection of Three-Tank System Applying MWAT-ICA

Data-Driven Fault Detection of Three-Tank System Applying MWAT-ICA

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 11

相关文章 5

编辑推荐 0

Metrics

本文评价

[1]	LIU Ziwen (刘子文), XIAO Lei (肖雷), BAO Jinsong (鲍劲松), TAO Qingbao (陶清宝) . Bearing Incipient Fault Detection Method Based on Stochastic Resonance with Triple-Well Potential System[J]. J Shanghai Jiaotong Univ Sci, 2021, 26(4): 482-487.
[2]	PENG Rui (彭锐), MA Xiaoyang *(马晓洋), ZHAI Qingqing (翟庆庆), GAO Kaiye (高凯烨). Software Reliability Growth Model Considering First-Step and Second-Step Fault Dependency[J]. Journal of Shanghai Jiao Tong University (Science), 2019, 24(4): 477-479.
[3]	LIU Jinhai* (刘金海), MA Yanjuan (马艳娟), WU Zhenning (吴振宁), WANG Gang (汪刚). Real-Time Pressure Based Diagnosis Method for Oil Pipeline Leakage[J]. 上海交通大学学报（英文版）, 2017, 22(2): 233-239.
[4]	SU Xian-li1,2 (苏先礼), ZHAN Xing-qun1* (战兴群), NIU Man-cang1 (牛满仓), ZHANG Yan-hua1 . Receiver Autonomous Integrity Monitoring Availability and Fault Detection Capability Comparison Between BeiDou and GPS[J]. 上海交通大学学报（英文版）, 2014, 19(3): 313-324.
[5]	LI Bin (李斌), WAN Yi-ming (万一鸣), YE Hao (叶昊). Fault Detection of Networked Control Systems with Uncertain#br# Time-Varying Delay and Quantization Error[J]. J Shanghai Jiaotong Univ Sci, 2011, 16(5): 513-518.