基于混沌遗传算法的主汽温系统RBF-PID控制

A Novel RBF-PID Control Strategy for Fresh Steam Temperature Based on Chaotic and Genetic Algorithm

针对火电厂主汽温控制系统具有大惯性、大迟延等特性,提出一种基于混沌遗传算法的径向基函数神经网络整定PID参数的控制策略。利用遗传算法优化神经网络权系数,同时利用混沌优化方法的局部快速搜索能力,实现全局最优化。该控制策略不仅具有常规PID串级控制的特性,而且具有智能控制器的自学习能力,增强了系统对不确定因素的适应性。仿真研究结果表明,这种方法具有全局优化的能力,对PID控制的参数优化设计是成功和有效的,系统动态品质明显优于通常的PID串级控制,系统控制性能得到了较大提高。

Aiming at the large inertial time-delay characteristic of the fresh steam temperature variations in thermal power plants, a novel PID control strategy with radial basis function network tuning based on chaotic and genetic algorithm was proposed. In this method, Genetic algorithm was presented for tuning weight parameters of the neural network, and chaos algorithm was used to realize optimal control with its good local search capability. The intelligent PID controller not only has the characteristics of the conventional cascade PID control, but also has the self-learning ability of intelligent controller, which can strengthen the system of uncertainties adaptability. Simulation results showed that the control system performance is obviously better than the conventional cascade control.