An Evolutionary Algorithm for Parameters Identification in Parabolic Systems^*

Zhijian Wu¹, Zhilong Tang¹, Jun Zou², Lishan Kang¹, and Mingbiao Li³

¹The State Key Lab. of Software Eng., Wuhan Uni., Wuhan, China
zjwu@public.wh.hb.cn

²Dept. of Math., The Chinese Univ. of Hong Kong, Hong Kang, China

³School of Computer Sci. and Eng., Wenzhou Normal College, Zhejiang, China

Abstract. In this paper we construct a novel evolutionary algorithm. It yields good performance on a collection of parabolic parameter identification problems. The algorithm has a good tolerability for the noise in the observed data. Even when the noise level is up to 10% we can also get such a good result.

^*This work was supported by Open Fund of State Key Laboratory of Software Engineering, Wuhan University, National Natural Science Foundation of China (Nos. 60133010, 60073043, 70071042)

LNCS 3103, p. 1336 f.

Full article in PDF

lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2004