| 1. | The hourly meteorological parameters are the basic inputs in the determination of the hourly cooling load of the building
室外逐时气象参数是确定建筑物逐时冷负荷的基本输入参数。 |
| 2. | Develop the artificial neural network ( ann ) program to predict the hourly cooling load of the building under arbitrary meteorological conditions
开发了人工神经网络用于预测任意气象条件下建筑物的逐时冷负荷。 |
| 3. | Then , mre reaches 3 . 21 % for workday and 5 . 96 % for holiday . a unique next 24 hours hourly cooling load prediction ann model is established
对工作日负荷预测，其平均预测误差是3 . 21 ；对假日负荷，其平均预测误差是5 . 96 。 |
| 4. | In china and abroad , almost all of the dynamic load simulation software cannot calculate the hourly cooling load of the building , under random weather and building conditions
国内外，几乎所有动态负荷模拟软件都无法计算出任意气象和任意建筑条件下的建筑物逐时冷负荷。 |
| 5. | 1 . based on the meteorological parameters of test reference year ( try ) in xi ' an , the dynamic simulation program calculates the hourly cooling loads of an office building between april and september
采用动态负荷模拟软件计算了西安地区某办公楼参考年4 9月份的逐时冷负荷，其计算结果成为气象参数和冷负荷预测研究的基本数据。 |
| 6. | According to the research results from som model , 8 sub neural network is adopted in inner and mae of hourly cooling load prediction is reduced 80 . 64kwh . expected error percentage ( eep ) is reduced to 3 . 27 % . next 24 hours hourly cooling load prediction multi - output dynamic model is established and prediction accuracy is improved again
建立了一个统一的空调逐时负荷的24小时提前人工神经网络预测模型，并根据对日冷负荷类型的som分类结果，通过在内部一共采用8个子神经网络模型使得逐时负荷预测平均绝对误差降低到了80 . 64kwh ，期望相对误差降低到了3 . 27 。 |
