Aiming at the problem that the performance of neural network PID controller in biogas dry fermentation temperature system is greatly influenced by the setting of initial weights, a design method of particle swarm optimization (PSO) algorithm to optimize the initial weights of neural network PID controller was presented.PSO algorithm optimized the initial weights of the neural network by using the mathematical model of fermentation temperature system.The optimized neural network was used to adjust PID parameters on-line.Multi-population competition mechanism was introduced into algorithm to improve the global optimization performance of PSO algorithm.Simulation results show that the proposed system can reach better control quality than the one using neural network PID controller, and it also can reduce the overshoot, shorten the stable time, and improve the control precision.%针对目前沼气干发酵温度控制中神经网络PID控制器性能受初始权值设置影响较大的问题,提出一种粒子群优化神经网络PID控制器的控制方法.粒子群算法利用发酵温度系统数学模型对神经网络的初始权值进行优化,用优化后的神经网络在线调整PID控制器参数.在优化过程中引入多种群竞争机制,提高粒子群全局寻优性能.仿真结果表明,该系统控制品质要优于神经网络PID控制,能够减小超调量、缩短稳定时间,提高控制精度.
展开▼