Articles & Issues

Language: English

Conflict of Interest: In relation to this article, we declare that there is no conflict of interest.

Publication history: Received January 30, 2012
Accepted November 7, 2012

This is an Open-Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/bync/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

All issues

Adaptive neuro-fuzzy inference system based faulty sensor monitoring of indoor air quality in a subway station

Hongbin Liu Mingzhi Huang¹ Jeong Tai Kim² ChangKyoo Yoo^†

Department of Environmental Science and Engineering, Center for Environmental Studies, Kyung Hee University, Seocheon-dong 1, Giheung-gu, Yongin-si, Gyeonggi-do 446-701, Korea ¹College of Environmental Science and Engineering, South China University of Technology, Guangzhou 510640, P. R. China ²Department of Architectural Engineering, Kyung Hee University, Seocheon-dong 1, Giheung-gu, Yongin-si, Gyeonggi-do 446-701, Korea

Korean Journal of Chemical Engineering, March 2013, 30(3), 528-539(12), 10.1007/s11814-012-0197-7

Download PDF

Abstract

A new faulty sensor monitoring method based on an adaptive neuro-fuzzy inference system (ANFIS) is proposed to improve the monitoring performance of indoor air quality (IAQ) in subway stations. To enhance network performance, a data preprocessing step for detecting outliers and treating missing data is implemented before building the monitoring models. A squared prediction error (SPE) monitoring index based on the ANFIS prediction model is proposed to detect sensor faults, where the confidence limit for the SPE index is determined by using the kernel density_x000D_ estimation method. The proposed monitoring approach is applied to detect four typical kinds of sensor faults that may happen in the indoor space of a subway. The prediction results in the subway system indicate that the prediction accuracy of an ANFIS structure with 15 clusters is superior to that of an appropriate artificial neural network structure. Specifically, when detecting one kind of complete failure fault that happened within the normal range, the detection performance of ANFIS-based SPE outperforms that of a traditional principal component analysis method. The developed sensor monitoring technique could work well for other kinds of sensor faults resulting from a noxious underground environment.

Keywords

Adaptive Neuro-fuzzy Inference System (ANFIS) Indoor Air Quality Kernel Density Estimation Sensor Fault Detection Subway Systems

References

Park DU, Ha KC, Environ. Int., 34, 629 (2008)
Ye X, Lian Z, Jiang C, Zhou Z, Chen H, Environ. Monit.Assess., 167, 643 (2010)
Chan LY, Lau WL, Wang XM, Tang JH, Environ. Int., 29, 429 (2003)
Cho JH, Min KH, Paik NW, Int. J. Hyg. Environ. Heal., 209, 249 (2006)
Feng YL, Mu CC, Zhai JQ, Li JA, Zou T, J. Hazard. Mater., 183(1-3), 574 (2010)
Pandey JS, Kumar R, Devotta S, Atmos. Environ., 39, 6868 (2005)
Yoo CK, Villez K, Van Hulle SW, Vanrolleghem PA, Environmetrics., 19, 602 (2008)
Dunia R, Qin SJ, Edgar TF, Mcavoy TJ, AIChE J., 42(10), 2797 (1996)
Venkatasubramanian V, Rengaswamy R, Kavuri SN, Yin K, Comput. Chem. Eng., 27(3), 327 (2003)
Pires JCM, Sousa SIV, Pereira MC, Alvim-Ferraz MCM, Martins FG, Atmos. Environ., 42, 1249 (2008)
Lau J, Hung WT, Cheung CS, Atmos. Environ., 43, 769 (2009)
Kim Y, Kim JT, Kim I, Kim JC, Yoo C, Environ. Eng. Sci., 27, 721 (2010)
Liu H, Kim M, Kang O, Sankararao B, Kim JT, Kim JC, Yoo CK, Indoor Built Environ., 21, 205 (2012)
Chiang LH, Russell EL, Braatz RD, Fault detection and diagnosis in industrial systems, Springer-Verlag (2001)
Qin SJ, J. Chemometrics., 17, 480 (2003)
Ku W, Storer RH, Georgakis C, Chemometr. Intell. Lab., 30, 179 (1995)
Chen JH, Liu KC, Chem. Eng. Sci., 57(1), 63 (2002)
Haykin S, Neural networks, Prentice-Hall (1999)
Lee JM, Yoo CK, Choi SW, Vanrolleghem PA, Lee IB, Chem. Eng. Sci., 59(1), 223 (2004)
Ge ZQ, Yang CJ, Song ZH, Chem. Eng. Sci., 64(9), 2245 (2009)
Kramer MA, AIChE J., 37, 233 (1991)
Dong D, Mcavoy TJ, Comput. Chem. Eng., 20(1), 65 (1996)
Chen JH, Liao CM, J. Process Control, 12(2), 277 (2002)
Zhang J, Comput. Chem. Eng., 30(3), 558 (2006)
Jang JSR, IEEE Trans. Syst. Man Cybern., 23, 665 (1993)
Pai TY, Wan TJ, Hsu ST, Chang TC, Tsai YP, Lin CY, Su HC, Yu LF, Comput. Chem. Eng., 33(7), 1272 (2009)
Lau CK, Heng YS, Hussain MA, Nor MIM, ISA Trans., 49, 559 (2010)
Huang MZ, Wan JQ, Ma YW, Zhang HP, Wang Y, Wei CH, Liu HB, Yoo C, Ind. Eng. Chem. Res., 50(23), 13500 (2011)
Huang M, Wan J, Wang Y, Ma Y, Zhang H, Liu H, Hu Z, Yoo CK, Korean J. Chem. Eng., 29(5), 636 (2012)
Jang JSR, Sun CT, Mizutani E, Neuro-fuzzy and soft computing: A computational approach to learning and machine intelligence, Prentice Hall (1997)
Takagi T, Sugeno M, IEEE Trans. Syst. Man Cybern., 15, 116 (1985)
Sugeno M, Kang GT, Fuzzy Set. Syst., 28, 15 (1988)
Jackson J, A user’s guide to principal components, Wiley (1991)
Wise BM, Gallagher NB, J. Process Control, 6(6), 329 (1996)
Qin SJ, Dunia R, J. Process Control, 10(2-3), 245 (2000)
Chen Q, Wynne RJ, Goulding P, Sandoz D, Control Eng.Pract., 8, 531 (2000)
Martin EB, Morris AJ, J. Process Control, 6(6), 349 (1996)
Jolliffe I, Principal component analysis, Springer-Verlag (2002)
Nelson PRC, Taylor PA, MacGregor JF, Chemometr. Intell.Lab., 35, 45 (1996)
Stanimirova I, Daszykowski M, Walczak B, Talanta., 72, 172 (2007)
Chen T, Martin E, Montague G, Comput. Stat. Data. An., 53, 3706 (2009)
Nieuwenhuijsen MJ, Gomez-Perales JE, Colvile RN, Atmos.Environ., 41, 7995 (2007)
Yu JB, J. Process Control, 22(7), 1358 (2012)