摘要
在智能家居环境下,为满足用户对室内环境热舒适度的要求,对室内设备实施精准控制,对室内环境的热舒适度指标进行了预测分析。为提高数据质量,首先利用K-means聚类算法对实验数据进行处理;其次,为摆脱初始阈值与权值的随机性对模型预测精度带来的负面影响,而导致预测结果陷入局部最小,提出采用遗传算法优先寻找模型最优的初始阈值与权值,然后基于BP神经网络建立预测模型,对室内环境热舒适度进行预测,已有的实验数据证明预测效果良好。研究成果表明,系统能够根据当前热环境状况,自动改变控制策略,调整被控设备的运行状态,使得智能家居室内热环境保持在舒适、稳定且平衡的最佳状态。
In the smart home environment,the prediction analysis for thermal comfort index of indoor environment is carried out to meet the user’s requirements for thermal comfort of indoor environment and implement precise control of indoor devices.In order to improve the data quality,the experimental data are firstly processed by K-means clustering algorithm.Secondly,in order to get rid of the negative impact of the randomness of the initial threshold and weights on the prediction accuracy of the model,which leads to the prediction results into local minimum,the genetic algorithm is proposed to find the optimal initial threshold and weights of the model firstly,and then the prediction model is established based on BP neural network to predict the indoor environmental thermal comfort.The experimental data prove that the prediction effect is good.The research results show that the system can automatically change the control strategy and adjust the operation status of the controlled equipment according to the current thermal environment conditions,so that the indoor thermal environment of the smart home can be kept in the best state of comfort,stability and balance.
作者
王晓辉
刘静蕾
边会娟
王佳玏
WANG Xiao-hui;LIU Jing-lei;BIAN Hui-juan;WANG Jia-le(National Virtual Simulation Experimental Center for Smart City Education,School of Electrical and Information Engineering,Beijing University of Civil Engineering and Architecture,Beijing 100044,China)
出处
《控制工程》
CSCD
北大核心
2021年第7期1437-1445,共9页
Control Engineering of China
基金
2020年北京市大学生毕业设计(科研类)项目
北京建筑大学校基金项目(00331616040)。
关键词
室内环境热舒适度
K均值聚类
BP神经网络
遗传算法
联动控制
Indoor environment thermal comfort
K-means clustering
BP neural network
genetic algorithm
linkage control
