论文部分内容阅读
利用2011年12月2012年3月张掖国家湿地公园水域结冰厚度观测资料和张掖观象台的气温、地温等资料,借助BP神经网络可以逼近任意非线性函数的能力和特点,构建了用于短期预报水域结冰厚度的模型,并验证该模型的预报效果。结果表明,BP神经网络预报模型能够对水域结冰厚度进行有效的短期预报,该结冰厚度的预报模型对结冰厚度的预报效果较理想。流动水域结冰厚度预报历史拟合率高达96.8%,模型试报准确率为85.7%;静止水域结冰厚度预测历史拟合率达87.8%,模型试报准确率为80.0%,其性能指标符合实际要求,具有实际应用价值。
Based on the observed data of ice thickness in Zhangye National Wetland Park in December 2011 and the temperature and ground temperature of Zhangye Observatory in December 2011, the capability and characteristics of any nonlinear function can be approximated by using BP neural network. The icing thickness of the water model, and verify the model of the forecast results. The results show that the BP neural network prediction model can effectively predict the icing thickness in the water area, and the prediction model of icing thickness is more effective in predicting the icing thickness. The historical fitting rate of prediction of ice thickness in flowing waters was as high as 96.8%, the accuracy rate of model test was 85.7%, that of frozen waters was 87.8%, and the accuracy of model test was 80.0% The actual requirements, with practical value.