Abstract
Fault diagnostics is an important research area including different techniques. Principal component analysis (PCA) is a linear technique which has been widely used. For nonlinear processes, however, the nonlinear principal component analysis (NLPCA) should be applied. In this work, NLPCA based on auto-associative neural network (AANN) was applied to model a chemical process using historical data. First, the residuals generated by the AANN were used for fault detection and then a reconstruction based approach called enhanced AANN (E-AANN) was presented to isolate and reconstruct the faulty sensor simultaneously. The proposed method was implemented on a continuous stirred tank heater (CSTH) and used to detect and isolate two types of faults (drift and offset) for a sensor. The results show that the proposed method can detect, isolate and reconstruct the occurred fault properly.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
SUBRAMANIAN V, RENGASWAMY R, KAVURI N, YIN K. A review of process fault detection and diagnosis. Part III: Process history based methods [J]. Computers and Chemical Engineering, 2003, 27: 327–346.
THISSEN U, MELSSEN W J, BUYDENS L M C. Nonlinear process monitoring using bottle-neck neural networks [J]. Analytica Chimica Acta, 2001, 446: 371–383. (in Netherland)
KOURTI T. Process analysis and abnormal situation detection from theory to practice [J]. IEEE Control Systems Magazine, 2002: 400–405.
ZHU Qun-xiong, LI Cheng-fe. Dimensionality reduction with input training neural network and its application in chemical process modeling [J]. Chinese J Chem Eng, 2006, 145: 597–603. (in Chinese)
Diego Garcia-Alvarez. Fault detection using principal component analysis (PCA) in a waste water treatment (WWTP) [M]. Valladolid: University of Valladolid Press, 2010: 55–59. (in Spain)
Jonathon Shlens. A tutorial on principal component analysis [D]. San Diego La Jolla: Institute for Nonlinear Science, University of California, 2005
HE Xiang-yu, LUO Hui-ming, SHAO Yi-ming. Online fault detection of excavator’s hydraulic system [J]. International Journal of Digital Content Technology and its Applications. 2011, 5(7): 258–260.
YANG Qing-song. Model based and data driven fault diagnosis methods with applications to process monitoring [D]. Case Western Reserve University, 2008: 25–36.
MARK A K. Nonlinear principal component analysis using auto-associative neural networks [J]. Alche Journal, 1991, 37(2): 233–243.
Mahmoodreza Sharifi. Sensor fault diagnosis using principal component analysis [D]. America: University of Texas A & M, 2009:.
HE Qing-hua, HE Xiang-yu, ZHU Jian-xin. Fault detection of excavator’s hydraulic system based on dynamic principal component analysis [J]. Journal of Central South University: Science and Technology, 2008, 15: 700–705. (in Chinese)
NAJAFI M, CULP C, LANGARI R. Performance study of enhanced auto-associative neural networks for sensor fault detection [C]// IEEE Int Conference on Fuzzy Systems. Budapest, 2004: 453–456.
THORNHILL N F, SACHIN C, SIRISH L S. A continuous stirred tank heater simulation model with applications [J]. Journal of Process Control, 2008, 18: 347–360.
Author information
Authors and Affiliations
Corresponding author
Additional information
Foundation item: Project(1390/2) supported by Khuzestan Gas Company, Iran
Rights and permissions
About this article
Cite this article
Hamidreza, M., Mehdi, S., Hooshang, JR. et al. Reconstruction based approach to sensor fault diagnosis using auto-associative neural networks. J. Cent. South Univ. 21, 2273–2281 (2014). https://doi.org/10.1007/s11771-014-2178-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11771-014-2178-y