基于改进粒子群优化算法的预测控制

在实际工业过程中预测控制算法应用广泛,但是对于多变量预测控制算法其参数较多,且各个参数之间相互耦合,故整定其参数比较复杂,鉴于此提出一种基于改进粒子群算法的预测控制参数优化算法。该算法的基本思想是将生物寄生行为机制引入到粒子群优化算法中,形成双种群粒子群优化算法,使用该改进粒子群算法对多变量预测控制算法的参数进行离线优化,从而确定预测控制算法参数的最优取值。最后,将本文算法用于冷热水系统液位和温度的控制,并通过仿真将该算法与标准粒子群优化算法相比较,仿真结果表明使用该算法对多变量预测控制的参数进行优化整定时,系统的阶跃响应具有抗干扰性能好、超调量小、调节时间短等优点。

Predictive Control Based on Improved PSO Algorithm

In the actual industrial process, the predictive control algorithm is widely used, but the parameters of the multivariable predictive control algorithm are more and the parameters are coupled with each other, so tuning the parameters are complicated. In view of this, a predictive control parameters optimization algorithm based on improved particle swarm optimization is proposed. The basic idea of this algorithm is that the mechanism of parasitic behavior is introduced into the particle swarm optimization algorithm to form a two-population particle swarm optimization algorithm, the improved particle swarm algorithm is used to off-line optimization the parameters of the multivariable predictive control algorithm, so as to determine the optimal values of predictive control algorithm parameters. Finally, the algorithm is used to control the liquid level and temperature of a cold and hot water system, and the algorithm is compared with the standard particle swarm optimization algorithm through simulation. The simulation results show that the proposed algorithm is used to optimize the parameters of multivariable predictive control, the step response of system has advantages such as good anti-jamming performance, little overshoot, short adjusting time and so on.