基于改进PSO-BP的模糊PID烧结炉温度控制

Fuzzy PID Sintering Furnace Temperature Control Based on Improved PSO-BP

采用改进粒子群算法整定优化PID参数,并在反馈回路中加入BP神经网络预测下一时刻温度,将超前温度信息作为改进粒子群算法适应度函数参数,提前调整PID控制器参数,从而给出超前的控制,以此来减弱烧结炉温度变化的滞后性。通过模糊推理在温度控制过程中在线调整PID控制器参数,加强温度控制的跟随性。试验结果表明,与传统PID控制模型相比,基于改进粒子群算法和BP神经网络的模糊PID参数模型的响应速度和稳态精度均得到有效提高,并且超调量更小。该方法适用于磨块烧结炉温度控制,有助于提高生产效率和磨块质量、增加经济效益。

This paper presents a sintering furnace temperature control method based on improved particle swarm optimization algorithm,BP neural network and fuzzy reasoning to optimize PID parameters.The improved particle swarm optimization algorithm is used to optimize the PID parameters,and the BP neural network is added to the feedback loop to predict the next temperature.The advanced temperature information is used as the fitness function parameter of the improved PSO algorithm,and the PID controller parameters are adjusted ahead of time.This method adjusts the parameters of PID controller online in the process of temperature control through fuzzy reasoning,so as to strengthen the follow-up of temperature control.The experimental results show that compared with the traditional PID control model,the response speed and steady-state accuracy of the model are effectively improved,and the overshoot is smaller.This method is suitable for temperature control of grinding block sintering furnace,which is helpful to improve production efficiency,grinding block quality and economic benefit.