量子遗传算法优化RBF神经网络及其在热工辨识中的应用.pdfVIP

第 28 卷 第 17 期 中 国 电 机 工 程 学 报 Vol.28 No.17 Jun. 15, 2008 2008 年 6 月 15 日 Proceedings of the CSEE ©2008 Chin.Soc.for Elec.Eng. 99 文章编号：0258-8013 (2008) 17-0099-06 中图分类号：TP 181 ；TK 229 文献标识码：A 学科分类号：470⋅20 量子遗传算法优化 RBF 神经网络及其在 热工辨识中的应用 董 泽，黄 宇，韩 璞 (华北电力大学控制科学与工程学院，河北省 保定市 071003) Thermal Process Identification With Radial Basis Function Network Based on Quantum Genetic Algorithm DONG Ze, HUANG Yu, HAN Pu (School of Control Science and Engineering, North China Electric Power University, Baoding 071003, Hebei Province, China) ABSTRACT: Quantum genetic algorithm is a probability 算法的计算精度和收敛速度。同时利用该方法设计了一种通 optimization method which is based on quantum compute 用的热工对象模型辨识神经网络算法，编制了专用的模型识 principle. The precision and the rate of convergence are 别软件，对某电厂循环流化床锅炉一次风对床温的动态特性 impacted by rotation angle. Aiming at the shortcoming of fuzzy 进行辨识，结果表明该方法是一种精度比较高的辨识算法。 quantum genetic algorithm (FQGA), quantum-inspired 关键词：热工过程；系统辨识；径向基函数神经网络；量子 crossover method was introduced to FQGA, and a novel 遗传算法 quantum genetic algorithm was put forward. Using this method, an identification algorithm of nonlinear systems was presented. 0 引言 This method is characterized by estimating parameters such as [1-5] 径向基函数神经网络 (radial basis function weight, width and central position of RBFNN using the new quantum genetic algorithm. High velocity and accuracy of the neural network，RBFNN)基于正则化理论导出，具 method enable nonlinear systems to be