Aiming at the problem of energy waste in the operation and management of the building, the energy consumption forecast and the abnormal diagnosis method based on the support vector machine are put forward, which provide the theoretical support and realization path for the large-scale public building energy saving. As a large unit of energy consumption per unit area, large public building has been widely concerned. Based on the historical energy consumption data, climatic factors and time-cycle factors, 11 input parameters were selected as the sample characteristics, and the large-scale public building energy consumption forecasting model based on support vector machine was constructed to forecast the daily energy consumption of buildings. Based on the forecast of energy consumption, the average relative error and the maximum error of the test set are taken as the criterion to diagnose the energy consumption abnormality. The method is applied to the abnormal diagnosis of energy consumption in the summer air conditioning system. Through the comparison of the energy consumption forecast value and the actual value, it is found that the operation of the air conditioning system in the unreasonable use of the phenomenon, for the management of buildings to provide a reference.%针对建筑运行中管理粗放、使用中能源浪费的问题,提出了基于支持向量机的能耗预测与异常诊断方法,为大型公共建筑节能提供理论支撑与实现路径.由于大型公共建筑具有极大的单位面积耗能量而得到广泛的关注.本文针对大型公共建筑能耗特点,从历史能耗数据、气候因素、时间周期因素三个方面选取11个输入参数作为样本特征,构建基于支持向量机的大型公共建筑能耗预测模型,对建筑逐日能耗展开预测.在能耗预测基础上,以测试集平均相对误差与最大误差作为判定标准进行能耗异常诊断,将该方法应用于夏季空调系统能耗异常诊断中,通过能耗预测值与实际值的对比,发现了空调系统运行中存在的不合理使用现象,为建筑节能管理运行提供参考.
展开▼
