混合差分和多种群粒子群算法的T-S模糊模型辨识  

T-S Fuzzy Model Identification of Hybrid Differential and Multi Particle Swarm Optimization

作　　者：林国汉[1] 陈壮[1] LIN Guohan;CHEN Zhuang(College of Electrical and Information Engineering,Hunan Institute of Engineering,Xiangtan 411104,China)

机构地区：[1]湖南工程学院电气与信息工程学院,湘潭411104

出　　处：《湖南工程学院学报（自然科学版）》2024年第2期1-6,30,共7页Journal of Hunan Institute of Engineering(Natural Science Edition)

基　　金：湖南省科技创新计划资助项目(2021GK1210)。

摘　　要：为提高T-S模型的辨识精度,针对基本粒子群优化(particle swarm optimization,PSO)算法T-S模型全局优化辨识问题,提出混合差分和多种群粒子群算法的T-S模糊模型辨识方法,将T-S模型前件参数和后件参数整体编码进行全局优化辨识.为避免基本粒子群的早熟收敛和后期收敛速度慢的缺陷对T-S模型辨识精度和速度的影响,算法将种群分为若干个子群,每个子群根据粒子适应度值自适应调整惯性权重,平衡了算法的开发和探索能力,对子群最优粒子,进行差分操作以增强算法的全局搜索能力,采用全局最优粒子替代随机子群的最优粒子以加强子群间的信息交流,维持粒子多样性.典型非线性系统和混沌系统的仿真结果表明,采用混合差分和多种群粒子群算法辨识的T-S模型具有更高的辨识精度.An hybrid differential evolution(DE)with multi particle swarm optimization(PSO)(HDEMPSO)is proposed for modeling T-S fuzzy system.The premise parameters and consequences parameters are encoded together and identified.To avoid the premature convergence and low convergence speed of the PSO that effect the accuracy and speed,the proposed algorithm partitions the swarm into several subswarms,Each subswarms evolves independently and adjusts the inertia weight adaptively according to the fitness value of particles.The best of each particle in subswarms is updated by DE to further enhance the global search ability.The strategy of randomly selection subswarm's best particle replaced by global particle is used to transfer the information among all the sub-swarms and accelerate the convergence speed.The simulation results for typical nonlinear and chaotic systems show that the T-S model with hybrid difference and multi particle swarm optimization has higher identification accuracy.

关 键 词：T-S模糊系统 粒子群优化 差分进化 多种群 

分 类 号：TP273.4[自动化与计算机技术—检测技术与自动化装置]