空调负荷混沌特性分析与预测  

Analysis of chaos characteristic and forecasting on air conditioning load

作　　者：刘慧卿[1] 周国峰[1] 张先起[1] 

机构地区：[1]华北水利水电学院,河南郑州450011

出　　处：《四川建筑科学研究》2009年第5期299-302,共4页Sichuan Building Science

基　　金：河南省2008年软科学研究计划项目(082400451900);华北水利水电学院青年基金项目(hsqj2008014);河南省基础与前沿技术研究项目(082300460030)

摘　　要：影响空调负荷因素比较多,且难于确定和提取,这就造成空调负荷的拟合和预测精度较低。在对空调负荷时间序列混沌特性分析的基础上,利用嵌入相空间来确定前期影响因子,建立了基于混沌相空间技术的BP神经网络模型。模型既能考虑到影响空调负荷时间序列的动力因子,又能解决网络输入单元数确定的困难,并能利用神经网络超强的非线性映射功能,结合空调负荷实例的拟合与预测,表明其结果合理,预测精度较高。There are lots of factors which influence evolvement law of air conditioning load, and it is very difficult to be known and gained, which results in low precision of simulation and forecast. Based on analysis on chaos characteristic of air conditioning load time series ,BP neural networks model based on chaos phase space is proposed to forecast air conditioning load through embedding dimension. Considering influence of dynamical factor of air conditioning load as well as difficulty of calculating number of input cell, the model is provided with strong nonlinear mapping capacity, is applied to simulate and forecast air conditioning load, the outcomes is reasonable and higher precision.

关 键 词：混沌 空调 负荷 神经网络 相空间 

分 类 号：TU71[建筑科学—建筑技术科学]