|本期目录/Table of Contents|

[1]孙丽萍,李元,张冬妍,等. 中央制冷空调冷冻水系统模糊RBF 控制研究[J].电机与控制学报,2017,21(05):110-116.[doi:10. 15938 /j. emc. 2017. 05. 015]
 SUN Li-ping,LI Yuan,ZHANG Dong-yan,et al.Fuzzy radial basis function control for central air conditioning system[J].,2017,21(05):110-116.[doi:10. 15938 /j. emc. 2017. 05. 015]
点击复制

 中央制冷空调冷冻水系统模糊RBF 控制研究(PDF)
分享到:

《电机与控制学报》[ISSN:1007-449X/CN:23-1 408/TM]

卷:
21
期数:
2017年05
页码:
110-116
栏目:
出版日期:
2018-04-20

文章信息/Info

Title:
Fuzzy radial basis function control for central air conditioning system
作者:
 孙丽萍 李元 张冬妍 刘亚秋
 ( 东北林业大学机电工程学院,黑龙江哈尔滨150040)
Author(s):
SUN Li-ping LI Yuan ZHANG Dong-yan LIU Ya-qiu
 ( College of Mechanical and Electrical Engineering,Northeast Forestry University,Harbin 150040,China)
关键词:
中央空调 冷冻水系统 径向基函数 模糊控制 反向传播神经网络
Keywords:
central air-conditioning chilled water system radial basis function fuzzy control back propagation neural network
分类号:
TU 83
DOI:
10. 15938 /j. emc. 2017. 05. 015
文献标志码:
A
摘要:
针对中央空调冷冻水系统回水温度快速准确调节问题,提出基于模糊径向基函数( radial basis function,RBF) 网络的变流量回水温度智能控制方法。首先,对冷冻水系统旁通阀门的水量开度、泵组转速等输入量,按照模糊控制理论,进行模糊化与反模糊化处理,获得归一化的输入信息向量; 然后,利用能够全局寻优的RBF 网络进行温度预测,不断迭代预测产生理想的预测温度; 最后,当期望温度与预测迭代的温度残差小于门限值时,停止迭代,输出并记录温度,完成冷冻水系统的非线性温度控制。仿真实验表明,相比于传统反向神经( back propagation,BP) 网络控制,RBF 控制方法迭代次数更少且精度更高,能够提高系统的整体性能。
Abstract:
Aiming at the problem of rapid and accurate adjustment of chilled water system on central airconditioning backwater temperature,an intelligent control method based on fuzzy RBF network was proposed. Firstly, the fuzzy control theory was used to deal with the amount of water and the rotational speed of the bypass valve of the chilled water system. Then,RBF network was used to complete the global optimization of temperature prediction,and then the ideal iterative prediction temperature was produced by proposed method; finally, the iteration was stopped when the desired temperature and residual temperature prediction iterative was less than the threshold value,output and record the temperature,nonlinear temperature control of chilled water system was been completed. The simulation experiments show that the RBF control method is better than the traditional BP neural network control method, the iteration number is less and precision is higher,and improved proposed control method can improve system performance.

参考文献/References:

相似文献/References:

备注/Memo

备注/Memo:
收稿日期: 2016 - 09 - 23
基金项目: 国家自然科学基金( 31370565)
作者简介: 孙丽萍( 1958—) ,女,博士,教授,博士生导师,研究方向为智能控制与检测;
李元( 1991—) ,男,硕士研究生,研究方向为复杂系统建模仿真与智能控制;
张冬妍( 1976—) ,女,博士,副教授,研究方向为控制工程;
刘亚秋( 1971—) ,男,博士,教授,博士生导师,研究方向为计算机控制与应用。
更新日期/Last Update: 2017-08-24