The combination forecasting method gives bigger weight to the models, which better conform with the variation of power load, and improves the precision. The sample calculation shows the truth.
采用组合预测法对能很好反映负荷变化规律的模型赋予较大的权重，从而提高负荷预测精度，示例计算表明组合预测法的预测精度明显高于各单一模型的预测精度。
This method can be applied to designing sample components for fatigue test as well as to forecasting various fatigue life of component from stress fatigue to strain fatigue.
该方法不仅可用于构件从应力疲劳到应变疲劳的各类疲劳寿命预测，还可用于构件的疲劳试验模拟件设计。
Meanwhile, the length of time on training sample was determined as the recent complete economic cycle when using artificial neural network for railway freight volume forecasting.
并提出在利用人工神经网络进行铁路货运量预测时，训练样本的时间长度为最近的一个完整经济周期。
应用推荐