基于神经网络分析的建筑物耗能仿真模型分析  

Analysis of Building Energy Consumption Simulation Model Based on Neural Network Analysis

作　　者：陈辉 CHEN Hui(School of Urban Construction and Transportation,Hefei University,Hefei 230000,China)

机构地区：[1]合肥学院城市建设与交通学院,安徽合肥230000

出　　处：《佳木斯大学学报（自然科学版）》2022年第1期13-15,138,共4页Journal of Jiamusi University：Natural Science Edition

摘　　要：以建筑物耗能特点为研究对象,在建筑节能标准中提取影响建筑能耗的主要因素,利用神经网络结构算法构建一种建筑物耗能评估仿真模型。仿真分析过程中,采用改进聚类分析方法确定神经网络结构仿真模型初始参数值,并采用混合学习算法对神经网络仿真模型进行训练。仿真模型评估应用实例表明基于神经网络结构算法建立的建筑物耗能仿真模型结构简单,仿真评估准确,学习过程具有较强的泛化能力。This paper takes the characteristics of building energy consumption as the research object,extracts the main factors affecting building energy consumption from building energy efficiency standards,and uses neural network structure algorithm to build a simulation model of building energy consumption evaluation.In the process of simulation analysis,the improved clustering analysis method is used to determine the initial parameters of the neural network structure simulation model,and the hybrid learning algorithm is used to train the neural network simulation model.The application example of simulation model evaluation shows that the structure of the building energy consumption simulation model based on neural network structure algorithm is simple,the simulation evaluation is accurate,and the learning process has strong generalization ability.

关 键 词：神经网络 聚类分析 建筑物能耗 仿真模型 

分 类 号：TU17[建筑科学—建筑理论]