A method for optimal decision of limit gradient of newly-built railway

The invention discloses a method for optimal decision of limit gradient of a newly-built railway. The method comprises the following steps: firstly, a depth convolution neural network model is constructed; secondly, a railway case database is established to represent the factors that influence the decision-making of the limited gradient of the newly-built railway as gray images, which are fused into multi-channel images to be used in the training network model. Finally, a sliding scanning technique is proposed to make the decision of railway limited gradient combining with the trained depth convolution neural network model. Compared with the prior art, the method has the advantages of high automation degree, strong practicability, high operation efficiency and good application prospect. 本发明公开了种新建铁路限制坡度优化决策方法，所述优化决策方法包括以下步骤：首先构建深度卷积神经网络模型；然后建立铁路案例数据库，将影响新建铁路限制坡度决策的各项因素表征成灰度图，并融合成多通道图像用于训练网络模型；最后提出种滑动扫描技术，结合训练完成的深度卷积神经网络模型进行铁路限制坡度决策。与现有技术相比，该方法具有自动化程度高、实用性强、运行效率高且应用前景好等优点。