基于PSO算法的HVAC系统LSSVM预测控制

来源期刊:中南大学学报(自然科学版)2012年第7期

论文作者:邹木春 龙文

文章页码:2642 - 2647

关键词:暖通空调系统;预测控制;最小二乘支持向量机;PSO算法

Key words:heating ventilating and air-conditioning (HVAC) system; predictive control; least square support vector machine (LSSVM); PSO algorithm

摘    要:针对暖通空调(HVAC)系统,提出一种基于粒子群优化(PSO)算法和最小二乘支持向量机(LSSVM)的预测控制方法。该方法利用LSSVM建立HVAC系统预测模型并预测系统的输出值,引入输出反馈和偏差校正以克服模型失配等因素引起的预测误差,以此构造加权预测控制性能指标。由PSO算法滚动优化得到系统的最优控制量。利用该控制方法对一个HVAC系统进行仿真实验,结果表明该方法具有较好的控制效果。

Abstract: For the system of heating, ventilating and air-conditioning (HVAC), a nonlinear predictive control algorithm based on particle swarm optimization (PSO) and least square support vector machine (LSSVM) was proposed. It utilizes LSSVM to estimate the HVAC system model and forecast the output value, reducing the error in output feedback and error correction. A new weighted predictive control performance index is formulated. The optimal control values of the nonlinear system are obtained by the rolling optimization of PSO algorithm. An optimal control system is designed to control a HVAC system; simulation results show that the proposed nonlinear predictive control algorithm is effective.

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号