基于BP神经网络的过渡环境热舒适评判模型  

Evaluation Model for Thermal Comfort of Transitional Environment based on BP Neural Network

作　　者：许红波[1] 端木琳[1] 金权[1] 舒海文[1] 李祥立[1] 王宗山[1] 

机构地区：[1]大连理工大学建筑环境与设备工程研究所

出　　处：《建筑热能通风空调》2011年第4期28-31,共4页Building Energy & Environment

基　　金：国家自然科学基金(No.50678030);国家自然科学基金(No.51078052)

摘　　要：突变环境下的人体热反应是由许多主客观因素所决定的,利用神经网络具有通过学习最佳逼近非线性映射的能力,将其应用于突变环境下人体热反应的研究,具有一定的可行性。本文通过局部非均匀环境与背景均匀环境之间的过渡实验,利用Matlab工具,分别建立了向热环境过渡和向冷环境过渡的整体热感觉以及头部执感觉的BP(Back Propagation)神经网络热舒适评判模型。经验证,该模型对不同工况过渡后的逐时热感觉预测较为准确,从而为非均匀环境与均匀环境之间过渡的热舒适模型的建立提供了一种可借鉴的方法。Human thermal response under sudden change environment is determined by many subjective and objective factors,utilize neural network has the ability of best approximating nonlinear mapping through learning.It is feasible to make it apply to the study of human thermal response under sudden change environment.In this paper,through transitional experiment between the local non-environment and ambient uniform environment,make Use of Matlab tool,established respectively evaluation model of thermal comfort overall thermal sensation and head thermal sensation when transition to the hot environment and the cold environment.It is proved that the model can make a more accurate prediction to the thermal sensation under different conditions after the transition,to provide a reference method for transitional thermal comfort model between non-uniform environment and uniform environment.

关 键 词：突变环境 热舒适 MATLAB BP神经网络 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TU111[自动化与计算机技术—控制科学与工程]