基于粒子群算法优化的T-S型模糊神经网络控制器

粒子群优化(PSO)算法是一种新颖的演化算法,该算法通过粒子间的相互作用在复杂搜索空间中发现最优区域,其优势在于简单而功能强大。提出一种T-S型模糊神经网络控制器,采用PSO算法对模糊神经网络的前件参数和后件参数进行寻优,从而实现了模糊规则的自动调整、修改和完善。通过对非线性和时变被控对象的仿真研究,结果表明采用粒子群优化算法可以实现参数的全局快速寻优,而且优化后的T-S型模糊神经网络控制器能获得良好的控制性能。

A controller of T-S model fuzzy neural network based on particle swarm optimization

Particle Swarm Optimization (PSO) is a new evolutionary algorithm, which can find the optimal region in a complex search space through the interaction between particles. Its advantage is simple and powerful. A T-S type fuzzy neural network controller is presented, which adopt PSO algorithm for optimizing fuzzy neural network parame-ters in order to realize the fuzzy rules automatically adjusted, modified and improved. From the simulation research for non-linear and time-varying controlled objects, it is shown that the parameters can quickly achieve global opti-mization by using the PSO algorithm, and the optimized T-S fuzzy neural network controller can obtain a good con-trol performance.