摘要
针对中央空调系统具有非线性、时变、滞后等特性,提出一种基于PSO优化FNNPID(模糊神经网络PID)控制方法。该方法利用模糊控制、神经网络技术解决不确定性、非线性问题的优点,采用PID控制和模糊神经网络相结合的控制策略。同时针对模糊神经网络存在难以选取合理的学习参数的问题,提出一种混合协同优化的改进粒子群算法,通过改进算法对学习参数进行优化策略。试验结果表明,采用改进粒子群算法优化的模糊神经网络PID对空调系统控制具有更优的自适应能力,可提高空调系统的稳定性和可靠性。
In view of the nonlinear,time-varying,and lag characteristics of the central air-conditioning terminal system,a fuzzy neural network PID(FNN-PID)control method based on PSO is proposed.This method uses the advantages of fuzzy control and neural network technology to solve uncertain and nonlinear problems,and adopts a control strategy that combines PID control and fuzzy neural network.At the same time,in view of the problem that it is difficult to choose reasonable learning parameters for fuzzy neural networks,an improved particle swarm optimization algorithm for hybrid collaborative optimization is proposed,and the learning parameters are optimized through the improved algorithm.The experimental results show that the fuzzy neural network PID optimized by the improved particle swarm algorithm has better self-adaptive ability for the control of the airconditioning system,which can improve the stability and reliability of the air-conditioning system.
作者
刘宗瑶
邓勇
容慧
周笔锋
LIU Zong-yao;DENG Yong;RONG Hui;ZHOU Bi-feng(Wind Energy Engineering College,Hunan Electrical College of Technology,Xiangtan 411101,China;Hunan Zetian Zhihang Electronic Technology Co.,Ltd,Changsha 410000,China)
出处
《控制工程》
CSCD
北大核心
2020年第8期1474-1480,共7页
Control Engineering of China
基金
湖南省自然科学基金资助项目(2017JJ5011,2017JJ5012)。
关键词
PSO
模糊控制
神经网络
PID
控制策略
空调系统
Particle swarm optimization
fuzzy control
neural network
PID
control strategy
air-conditioning system
