基于粒子群优化的神经网络PID控制器在供热系统的研究  

Research on Neural Network PID Controller based on Particle Swarm Optimization in Heating System

作　　者：孟亚男[1] 黄迎旭 MENG Yanan;HUANG Yingxu(School of Information and Control Engineering,Jilin Institute of Chemical Technology,Jilin City 132022,China)

机构地区：[1]吉林化工学院信息与控制工程学院,吉林吉林132022

出　　处：《吉林化工学院学报》2023年第11期50-53,共4页Journal of Jilin Institute of Chemical Technology

摘　　要：集中供热系统是一个具有时滞性、非线性、大惯性等特点的复杂控制系统,传统PID控制无法达到令人满意的效果,还造成一定的资源浪费。BP神经网络PID控制器尽管在一定程度上改善了PID控制器的性能,但是BP神经网络自身仍有一些缺陷。为了能够提高供热系统的稳定性,进而实现合理用热,采用粒子群算法(PSO)优化BP神经网络PID控制器的权值。设计PSO-BP-PID控制器后,借助MATLAB仿真平台,获得传统PID控制、BP-PID控制以及PSO-BP-PID控制的仿真系统响应曲线图,根据曲线对比得出系统性能的改进情况。Central heating system is a complex control system with the characteristics of time delay,nonlinearity and large inertia,and the effect of traditional PID control can't achieve satisfactory results,and it also causes a certain waste of resources.Although the BP neural network PID controller improves the performance of the PID controller to a certain extent,the BP neural network itself still has some shortcomings.In order to improve the stability of the heating system and realize the rational use of heat,the particle swarm algorithm(PSO)was used to optimize the weights of the BP neural network PID controller.After designing the PSO-BP-PID controller,the simulation curve of the traditional PID control,BP-PID control and PSO-BP-PID controller was obtained by using MATLAB,and the improvement effect of system performance was obtained according to the comparison of curve effects.

关 键 词：集中供热 粒子群 BP神经网络 PID 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]