基于神经网络的哈尔滨高校教室热环境特征模型研究

Study on Characteristic Model for Thermal Environment of University Classrooms Based on Neural Network in Harbin

为了研究哈尔滨高校教室热环境特征模型和人体热舒适，笔者于2004年9月～2005年12月在哈尔滨进行了20次现场研究。在测量室内热舒适参数的同时，受试者填写对室内环境的热感觉和热舒适主观调查表。而后利用人工神经网络方法，建立了哈尔滨高校教室热环境特征和人体热舒适的BP神经网络评判模型，实现了对哈尔滨高校教室热环境内人体热感觉的智能化预测。现场研究结果验证表明，该模型预测的哈尔滨高校教室热环境内人体热感觉与实际主观调查吻合。

In order to study the characteristic model for thermal environment of university classrooms and human＇s thermal comfort, twenty field studies had been carried out from 2004 to 2005 in Harbin. When the parameters of thermal comfort were measured, students were asked to fill in the subjective questionnaires on their thermal perception/sensation and thermal comfort simultaneously. And then, a back- propagation neural network evaluation model was established to predict the thermal environment of university classrooms and human＇s thermal comfort. The results indicated that the forecast of the model was in agreement with the subjective investigation.