【摘要】 对农村地区民居建筑温度调节能耗的准确预测,可以进一步实现生态宜居新农村的建设。对建筑整体温度调节过程的能耗预测,需要根据建筑进程能耗输入变量的维数,计算出温度调节能耗的影响因素集合,完成建筑整体温度调节的能耗预测。传统方法给出建筑月能耗呈现周期性震荡的特点,对原始数据进行一次累加变换,但忽略了计算能耗影响因素集合,导致能耗预测效果不理想。提出基于深度CRBM的农村地区民居建筑整体温度调节能耗预测方法。将温度调节能耗预测定义为一个时间序列,给出历史建筑能耗实例数据样本,确定能耗输入变量的维数,计算出能耗的影响因素集合,对BP网络的权重和初始值进行优化,得到不同时期的建筑能耗变化趋势的最优预测阈值,由此进行农村地区民居建筑整体温度调节能耗预测。实验证明,所提方法预测精度较高,为建设生态宜居的新农村提供了科学的依据。更多还原

【Abstract】 Traditional prediction method for energy consumption during regulation progress of bulk temperature of residential building in rural area always ignores calculation of influence factor set of the energy consumption,which leads to poor prediction effect. In order to solve the problem,based on depth CRBM,a new prediction method is proposed in this article. Energy consumption prediction of temperature regulation is defined as a time series and historical data sample of the energy consumption is provided. Dimensionality of input variable of the energy consumption is confirmed and the influence factor set is calculated. Weight and initial value of BP network is optimized to obtain optimal prediction threshold of variation trend of the energy consumption in different periods. Thus,the prediction is completed. Experimental results prove that the method has high prediction precision. It provides scientific gist for building ecological livable new countryside.更多还原