Fuzzy Pattern Recognition Method of Flatness
Based on Particle Swarm Theory

LIU Jian  WANG Yiqun  SUN Fu  NING Shurong

(College of Mechanical Engineering, Yanshan University, Qinhuangdao 066004)

Abstract: Pattern recognition of strip flatness is the key to flatness close-loop control system. The result of pattern recognition of strip flatness has the direct effects on strip flatness control precision. With the development of strip flatness control methods, higher demands are presented for pattern recognition of strip flatness. To overcome the disadvantage of poor anti-interference ability and uncertain approaching ranks in traditional flatness pattern recognition, the fuzzy pattern recognition method of flatness is given according to the fuzzy classification theory, and the flatness pattern is classified by selecting nearness principle of Euclidean distance. On the basis of fuzzy pattern recognition, particle swarm theory, developed since 1990s, with global optimization capability is applied to optimize the result of pattern recognition. Compared with the simplex optimization method, validity of particle swarm theory applied in flatness pattern recognition is testified. The result after optimization can accurately control the flatness adjusting sets to meet the need of high precision flatness control.

Key words: Flatness  Fuzzy pattern recognition  Particle swarm  Euclidean distance

CLC No: TP391.4

国家自然科学基金(60474044、50675189)和河北省自然科学基金(E2004000221)资助项目. Received 20070212, received in revised form 20070810