ArticlesNo Access

EVOLVING RBF NEURAL NETWORKS FOR ADAPTIVE SOFT-SENSOR DESIGN

ALEX ALEXANDRIDIS

Department of Electronics, Technological Educational Institute of Athens, Agiou Spiridonos Aigaleo 12210, Greece

https://doi.org/10.1142/S0129065713500299Cited by:38

Abstract

This work presents an adaptive framework for building soft-sensors based on radial basis function (RBF) neural network models. The adaptive fuzzy means algorithm is utilized in order to evolve an RBF network, which approximates the unknown system based on input–output data from it. The methodology gradually builds the RBF network model, based on two separate levels of adaptation: On the first level, the structure of the hidden layer is modified by adding or deleting RBF centers, while on the second level, the synaptic weights are adjusted with the recursive least squares with exponential forgetting algorithm. The proposed approach is tested on two different systems, namely a simulated nonlinear DC Motor and a real industrial reactor. The results show that the produced soft-sensors can be successfully applied to model the two nonlinear systems. A comparison with two different adaptive modeling techniques, namely a dynamic evolving neural-fuzzy inference system (DENFIS) and neural networks trained with online backpropagation, highlights the advantages of the proposed methodology.

Keywords:

References

P. Kadlec and B. Gabrys , Adaptive local learning soft sensor for inferential control support , IEEE Int. Conf. Computational Intelligence for Modelling Control & Automation ( 2008 ) . Google Scholar
A. Jiménezet al., Sens. Actuators B Chem. 129, 985 (2008). Crossref, Google Scholar
L. Fortuna, S. Graziani and M. G. Xibilia, IEEE Trans. Instrum. Meas. 58, 2444 (2009), DOI: 10.1109/TIM.2009.2016386. Crossref, ISI, Google Scholar
G. Melagrakiet al., Mol. Divers. 10, 213 (2006), DOI: 10.1007/s11030-005-9008-y. Crossref, Medline, ISI, Google Scholar
A. P. Singh, T. S. Kamal and S. Kumar, Int. J. Neural Syst. 14, 237 (2004), DOI: 10.1142/S0129065704001991. Link, Google Scholar
C. Zanchettin and T. B. Ludermir, Int. J. Neural Syst. 15, 137 (2005), DOI: 10.1142/S0129065705000141. Link, ISI, Google Scholar
V. Kodogiannis and E. Wadge, Int. J. Neural Syst. 15, 363 (2005), DOI: 10.1142/S0129065705000347. Link, ISI, Google Scholar
M. A. González-Olveraet al., Int. J. Neural Syst. 20, 149 (2010). Link, Google Scholar
A. Y. Alaniset al., Int. J. Neural Syst. 21, 491 (2011), DOI: 10.1142/S0129065711003000. Link, ISI, Google Scholar
R. J. Martiset al., Int. J. Neural Syst. (2013), DOI: 10.1142/S0129065713500147. Google Scholar
R. A. Osornio-Rioset al., Comput.-Aided Civil Infrastruct. Eng. 27, 687 (2012), DOI: 10.1111/j.1467-8667.2012.00777.x. Crossref, ISI, Google Scholar
S. Arangio and F. Bontempi, Comput.-Aided Civil Infrastruct. Eng. 25, 348 (2010), DOI: 10.1111/j.1467-8667.2009.00644.x. Crossref, ISI, Google Scholar
D. H. Tran, B. J. C. Perera and A. W. M. Ng, Comput.-Aided Civil Infrastruct. Eng. 24, 145 (2009), DOI: 10.1111/j.1467-8667.2008.00577.x. Crossref, ISI, Google Scholar
H. Xu and J. Humar, Comput.-Aided Civil Infrastruct. Eng. 21, 450 (2006), DOI: 10.1111/j.1467-8667.2006.00449.x. Crossref, ISI, Google Scholar
H. Adeli and X. Jiang, J. Struct. Eng. 132, 102 (2006), DOI: 10.1061/(ASCE)0733-9445(2006)132:1(102). Crossref, ISI, Google Scholar
X. Jiang and H. Adeli, Int. J. Numer. Meth. Eng. 74, 1045 (2008), DOI: 10.1002/nme.2195. Crossref, ISI, Google Scholar
A. Samant and H. Adeli, Comput.-Aided Civil Infrastruct. Eng. 16, 239 (2001), DOI: 10.1111/0885-9507.00229. Crossref, ISI, Google Scholar
W. Grafet al., Comput.-Aided Civil Infrastruct. Eng. 27, 640 (2012), DOI: 10.1111/j.1467-8667.2012.00779.x. Crossref, ISI, Google Scholar
F. Y. Hsiaoet al., Comput.-Aided Civil Infrastruct. Eng. 27, 764 (2012), DOI: 10.1111/j.1467-8667.2012.00786.x. Crossref, ISI, Google Scholar
S. Freitag, W. Graf and M. Kaliske, Integr. Comput.-Aided Eng. 18, 265 (2011). Crossref, ISI, Google Scholar
O. Uluyol, K. Kim and E. O. Nwadiogbu, IEEE Trans. Syst., Man, Cybern. C, Appl. Rev. 36, 476 (2006), DOI: 10.1109/TSMCC.2006.875415. Crossref, ISI, Google Scholar
E. D. Wandekokemet al., Integr. Comput.-Aided Eng. 18, 61 (2011). Crossref, ISI, Google Scholar
J. Sedanoet al., Integr. Comput.-Aided Eng. 17, 1 (2010). ISI, Google Scholar
G. A. P. Coronadoet al., Integr. Comput.-Aided Eng. 19, 285 (2012). Crossref, ISI, Google Scholar
X. Zeng and Y. Zhang, Comput.-Aided Civil Infrastruct. Eng. 28, 359 (2013), DOI: 10.1111/mice.12000. Crossref, ISI, Google Scholar
H. B. Celikoglu, Comput.-Aided Civil Infrastruct. Eng. 28, 273 (2013), DOI: 10.1111/j.1467-8667.2012.00792.x. Crossref, ISI, Google Scholar
H. Adeli and X. Jiang, J. Transport. Eng. 129, 484 (2003), DOI: 10.1061/(ASCE)0733-947X(2003)129:5(484). Crossref, ISI, Google Scholar
F. Badranet al., Int. J. Neural Syst. 6, 447 (1995), DOI: 10.1142/S0129065795000305. Link, ISI, Google Scholar
H. Adeli and A. Panakkat, Neural Netw. 22, 1018 (2009), DOI: 10.1016/j.neunet.2009.05.003. Crossref, Medline, ISI, Google Scholar
A. Panakkat and H. Adeli, Int. J. Neural Syst. 17, 13 (2007), DOI: 10.1142/S0129065707000890. Link, ISI, Google Scholar
A. Panakkat and H. Adeli, Comput.-Aided Civil Infrastruct. Eng. 24, 280 (2009), DOI: 10.1111/j.1467-8667.2009.00595.x. Crossref, ISI, Google Scholar
Q. D. Tran, P. Kantartzis and P. Liatsis, Integr. Comput.-Aided Eng. 19, 229 (2012). Crossref, ISI, Google Scholar
J. Mendeset al., Appl. Soft Comput. 12, 3237 (2012), DOI: 10.1016/j.asoc.2012.05.009. Crossref, ISI, Google Scholar
E. Zamprogna, M. Barolo and D. E. Seborg, J. Process Control. 15, 39 (2005), DOI: 10.1016/j.jprocont.2004.04.006. Crossref, ISI, Google Scholar
H. Adeli and S. L. Hung, Appl. Math. Comput. 62, 81 (1994), DOI: 10.1016/0096-3003(94)90134-1. Crossref, ISI, Google Scholar
N. Wanget al., Int. J. Neural Syst. 20, 389 (2010), DOI: 10.1142/S0129065710002486. Link, ISI, Google Scholar
F. Liu and M. J. Er, Int. J. Neural Syst. 22, 21 (2012), DOI: 10.1142/S0129065712003067. Link, ISI, Google Scholar
H. Wersinget al., Int. J. Neural Syst. 17, 219 (2007), DOI: 10.1142/S0129065707001081. Link, ISI, Google Scholar
O. Beyer and P. Cimiano, Int. J. Neural Syst. 22, 1250023 (2012), DOI: 10.1142/S0129065712500232. Link, ISI, Google Scholar
Z. Yanget al., Int. J. Neural Syst. 16, 151 (2006), DOI: 10.1142/S0129065706000573. Link, ISI, Google Scholar
J. Platt, Neural Comput. 3, 213 (1991), DOI: 10.1162/neco.1991.3.2.213. Crossref, Medline, ISI, Google Scholar
S. Toluet al., Int. J. Neural Syst. 23, 1350010 (2013), DOI: 10.1142/S012906571350010X. Link, ISI, Google Scholar
G. Bello-Orgaz, H. D. Menéndez and D. Camacho, Int. J. Neural Syst. 22, 1250018 (2012), DOI: 10.1142/S0129065712500189. Link, ISI, Google Scholar
J. Lee and W. Pinheiro dos Santos, Integr. Comput.-Aided Eng. 18, 29 (2011). Crossref, ISI, Google Scholar
Z. M. Maet al., Integr. Comput.-Aided Eng. 18, 181 (2011). Crossref, ISI, Google Scholar
L. Yan and Z. M. Ma, Integr. Comput.-Aided Eng. 19, 199 (2012). Crossref, ISI, Google Scholar
L. Yan and Z. M. Ma, Integr. Comput.-Aided Eng. 19, 313 (2012). Crossref, ISI, Google Scholar
C. M. Bo et al. , The application of neural network soft sensor technology to an advanced control system of distillation operation , Int. Joint Conf. Neural Networks ( 2002 ) . Google Scholar
M.-D. Maet al., Control Eng. Pract. 17, 1026 (2009), DOI: 10.1016/j.conengprac.2009.03.004. Crossref, ISI, Google Scholar
A. Alexandridis et al. , An adaptive soft-sensor for non-destructive cement-based material testing, through the use of RBF networks , IEEE Conf. Evolving and Adaptive Intelligent Systems (EAIS) ( 2012 ) . Google Scholar
F. Petitjeanet al., Int. J. Neural Syst. 21, 475 (2011), DOI: 10.1142/S0129065711003024. Link, ISI, Google Scholar
E. Nichols, L. J. McDaid and N. Siddique, Int. J. Neural Syst. 20, 501 (2010), DOI: 10.1142/S0129065710002577. Link, ISI, Google Scholar
N. R. Luqueet al., Int. J. Neural Syst. 22, 1250013 (2012), DOI: 10.1142/S012906571250013X. Link, ISI, Google Scholar
P. Kadlec, R. Grbic and B. Gabrys, Comput. Chem. Eng. 25, 1 (2011). ISI, Google Scholar
J. Moody and C. Darken, Neural Comput. 2, 281 (1989). Google Scholar
P. Anand, B. V. N. Siva Prasad and C. Venkateswarlu, Int. J. Neural Syst. 19, 127 (2009), DOI: 10.1142/S0129065709001896. Link, ISI, Google Scholar
A. Karim and H. Adeli, J. Transport. Eng. 128, 21 (2002), DOI: 10.1061/(ASCE)0733-947X(2002)128:1(21). Crossref, ISI, Google Scholar
A. Karim and H. Adeli, J. Transport. Eng. 129, 494 (2003), DOI: 10.1061/(ASCE)0733-947X(2003)129:5(494). Crossref, ISI, Google Scholar
S. Ghosh-Dastidar, H. Adeli and N. Dadmehr, IEEE Trans. Biomed. Eng. 55, 512 (2008), DOI: 10.1109/TBME.2007.905490. Crossref, Medline, ISI, Google Scholar
Q. Junfei and H. Honggui, Int. J. Neural Syst. 20, 63 (2010). Medline, ISI, Google Scholar
D. Wuet al., Int. J. Neural Syst. 20, 109 (2010), DOI: 10.1142/S0129065710002292. Link, ISI, Google Scholar
H. Adeli and A. Karim, J. Transport. Eng. 126, 464 (2000), DOI: 10.1061/(ASCE)0733-947X(2000)126:6(464). Crossref, ISI, Google Scholar
J. F. Qiao and H. G. Han, Int. J. Neural Syst. 20, 63 (2010), DOI: 10.1142/S0129065710002243. Link, ISI, Google Scholar
S. Colic, O. C. Zalay and B. L. Bardakjian, Int. J. Neural Syst. 21, 367 (2011), DOI: 10.1142/S0129065711002894. Link, ISI, Google Scholar
U. R. Acharyaet al., Int. J. Neural Syst. 22, 1250011 (2012), DOI: 10.1142/S0129065712500116. Link, ISI, Google Scholar
U. R. Acharyaet al., Int. J. Neural Syst. 23, 1350009 (2013), DOI: 10.1142/S0129065713500093. Link, ISI, Google Scholar
L. Zhou, G. Yan and J. Ou, Comput.-Aided Civil Infrastruct. Eng. 28, 210 (2012), DOI: 10.1111/j.1467-8667.2012.00803.x. Crossref, ISI, Google Scholar
U. Reuter, Integr. Comput.-Aided Eng. 18, 281 (2011). Crossref, ISI, Google Scholar
H. Sarimveiset al., Ind. Eng. Chem. Res. 41, 751 (2002), DOI: 10.1021/ie010263h. Crossref, ISI, Google Scholar
A. Alexandridiset al., Chemom. Intell. Lab. Syst. 75, 149 (2005), DOI: 10.1016/j.chemolab.2004.06.004. Crossref, ISI, Google Scholar
A. Alexandridiset al., J. Process Control. 23, 968 (2013), DOI: 10.1016/j.jprocont.2013.04.008. Crossref, ISI, Google Scholar
A. Alexandridis, E. Chondrodima and H. Sarimveis, IEEE Trans. Neural Netw. Learn. Syst. 24, 219 (2013), DOI: 10.1109/TNNLS.2012.2227794. Crossref, Medline, ISI, Google Scholar
G. C. Marano, G. Quaranta and G. Monti, Comput.-Aided Civil Infrastruct. Eng. 26, 92 (2011), DOI: 10.1111/j.1467-8667.2010.00659.x. Crossref, ISI, Google Scholar
R. Jafarkhani and S. F. Masri, Comput.-Aided Civil Infrastruct. Eng. 26, 207 (2011), DOI: 10.1111/j.1467-8667.2010.00687.x. Crossref, ISI, Google Scholar
V. Plevris and M. Papadrakakis, Comput.-Aided Civil Infrastruct. Eng. 26, 48 (2011). ISI, Google Scholar
L. Sgambi, K. Gkoumas and F. Bontempi, Comput.-Aided Civil Infrastruct. Eng. 27, 655 (2012), DOI: 10.1111/j.1467-8667.2012.00780.x. Crossref, ISI, Google Scholar
R. Putha, L. Quadrifoglio and E. Zechman, Comput.-Aided Civil Infrastruct. Eng. 27, 14 (2012), DOI: 10.1111/j.1467-8667.2010.00715.x. Crossref, ISI, Google Scholar
T. Chabuket al., Integr. Comput.-Aided Eng. 19, 111 (2012). Crossref, ISI, Google Scholar
C. F. Fung, S. A. Billings and W. Luo, Neural Netw. 9, 1597 (1996), DOI: 10.1016/S0893-6080(96)00024-X. Crossref, Medline, ISI, Google Scholar
G. P. Liu, V. Kadirkamanathan and S. A. Billings, Neural Netw. 11, 1645 (1998), DOI: 10.1016/S0893-6080(98)00100-2. Crossref, Medline, ISI, Google Scholar
G.-B. Huang, P. Saratchandran and N. Sundararajan, IEEE Trans. Syst., Man, Cybern. B, Cybern. 34, 2284 (2004), DOI: 10.1109/TSMCB.2004.834428. Crossref, Medline, ISI, Google Scholar
A. Alexandridis, H. Sarimveis and G. Bafas, Neural Netw. 16, 1003 (2003), DOI: 10.1016/S0893-6080(03)00052-2. Crossref, Medline, ISI, Google Scholar
J. Nie, IEEE Trans. Fuzzy Syst. 5, 304 (1997), DOI: 10.1109/91.580803. Crossref, ISI, Google Scholar
K. J. Astrom and B. Wittenmark , Adaptive Control ( Addison-Wesley , Reading, MA , 1995 ) . Google Scholar
N. Kasabov and Q. Song, IEEE Trans. Fuzzy Syst. 10, 144 (2002), DOI: 10.1109/91.995117. Crossref, ISI, Google Scholar
S. Haykin , Neural Networks and Learning Machines ( Prentice Hall , Upper Saddle River, NJ , 2009 ) . Google Scholar
P. C. Krause , Analysis of Electric Machinery ( MacGraw-Hill International Editions , Singapore , 1987 ) . Google Scholar
J. Gama , R. Sebastião and P. P. Rodrigues , Issues in evaluation of stream learning algorithms , Proc. 15th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining ( 2009 ) . Google Scholar
A. Alexandridis and H. Sarimveis, AIChE J. 51, 2495 (2005), DOI: 10.1002/aic.10505. Crossref, ISI, Google Scholar
H. Sarimveiset al., Comput. Chem. Eng. 28, 209 (2004), DOI: 10.1016/S0098-1354(03)00169-8. Crossref, ISI, Google Scholar

Published: 10 October 2013

Remember to check out the Most Cited Articles!
Check out our titles in neural networks today!

Vol. 23, No. 06

Metrics

Downloaded 112 times

History

Accepted 20 August 2013

Keywords

PDF download

System Upgrade on Mon, Jun 21st, 2021 at 1am (EDT)

EVOLVING RBF NEURAL NETWORKS FOR ADAPTIVE SOFT-SENSOR DESIGN

Abstract

References

Recommended