摘要
数据挖掘技术与建筑工程之间的知识跨度较大,将两者完美融合起来存在一定难度,实际工程中也缺乏相关案例,因此在建筑工程中应用数据挖掘技术挖掘相关信息,为大型公共建筑用电能耗预测提供参考依据,是建筑领域一种新的发展趋势。基于对公共建筑用电能耗特性的分析,可利用Python构建BP神经网络建筑能耗预测模型,再将某公共建筑作为研究对象,确定影响建筑用电能耗的关键因素,并将其作为网络的输入参数进行学习训练得出预测值。研究结果表明:预测模型在不同参数下,当隐含层个数为8时,误差平方和最小,为0.000 139 6,此时BP神经网络能够较精确地预测公共建筑用电能耗值。
The knowledge span between data mining technology and construction engineering is large. It is difficult to integrate the two perfectly. There is no relevant case in actual engineering. Therefore,using data mining technology to mine relevant information in construction engineering is used for large public buildings. The reference for electric energy consumption prediction is a new development trend in the construction field. Based on the research and analysis of the energy consumption characteristics of public buildings,we use Python to construct the BP neural network building energy consumption prediction model,and then a public building is taken as the research object to determine the key factors affecting the building energy consumption,and learning training is performed as an input parameter to the network. The results show that under the different parameters,when the number of hidden layers is 8,the sum of squared errors is the smallest,which is 0.000 139 6. At this time,the BP neural network can accurately predict the energy consumption value of public buildings.
引文
[1]王艺斐,王宏愿.建筑能耗预测技术应用[J].山东工业技术,2017(12):113-114.
[2]宋蒙.大型公共建筑用电能耗预测模型及预测数据分析[D].西安:长安大学,2017.
[3]YALCINTAS M.An energy benchmarking model based on artificial neural network method with a case example for tropical climates[J].International Journal of Energy Research,2006(30):1158-1174.
[4]TSO G K F,YAU K K W.Predicting electricity energy consumptiona comparison of regression analysis,decision tree and neural network[J].Energy,2007(32):1761-1768.
[5]YANG J,RIVARD H,ZMEUREANU R.On-line building energy prediction using adaptive artificial neural networks[J].Energy and Buildings,2005,37(12):1250-1259.
[6]OLOFSON T,ANERSSON S.Long-term energy demand predictions based on short-term measured data[J].Energy and Buildings,2001,32(2):85-91.
[7]何磊.基于BP神经网络的建筑能耗预测[J].浙江建筑,2008(12):47-50.
[8]姚健,闫成文,叶晶晶,等.基于神经网络的建筑能耗预测[J].门窗,2007(10):31-33.
[9]肖丹.公共建筑能耗分析的数据挖掘方法研究与系统开发[D].重庆:重庆大学,2012.
[10]方涛涛,马小军,陈冲.基于BP-Adadoost算法的建筑能耗预测研究[J].科技通报,2017(7):162-166.
[11]季文娟,顾永松.基于POS-RBF建筑能耗预测模型研究[J].建筑节能,2015(11):109-112.
[12]高振祥.基于BP神经网络的电力负荷预测方法探析[J].科学与信息化,2017(2):54-55.
[13]张喆,吴知非,禹建丽.电力电量预测的神经网络方法[J].知识丛林,2008(4):156-157.
[14]李璐,于军琪,杨益.基于GA-BP神经网络的大型公共建筑能耗预测研究[J].中外建筑,2014(3):112-114.
[15]王雅楠,孟晓景.基于动量BP算法的神经网络房价预测研究[J].软件导刊,2015,14(2):59-61.
[16]胡程磊.数据驱动的建筑电能耗预测方法研究[D].江苏:江苏大学,2016.
[17]李然然,张永坚,刘畅,等.基于BP神经网络的建筑物用电能耗预测[J].山东建筑大学学报,2014(2):162-165.
[18]鄢涛.深圳市公共建筑能耗与节能分析[D].重庆:重庆大学,2005.
[19]胡伍生.神经网络理论及其工程应用[M].北京:测绘出版社,2006.
[20]崔冲.基于数据挖掘的公共建筑能耗预测与能效管理[D].山东:山东建筑大学,2017.
[21]许慧,黄世泽,郭其一,等.基于改进BP网络的建筑用电量预测[J].电器与能效管理技术,2014(18):54-58.