Dam safety comprehensive evaluation method based on depth learning

The invention discloses a dam safety comprehensive evaluation method based on depth learning, and adopts a multi-level dam safety monitoring system for comprehensive safety evaluation. The method comprises the following steps: 1, in the step of dam safety monitoring measure point grading, according to dam engineering characteristics, the monitoring system is abstracted into a tree structure; 2, in the step of monitoring measure point data preprocessing, missing values are filled and obvious anomaly values are excluded for measure point data; 3, in the step of calculating and classifying measure point threshold, calculation is conducted on a measure point selection model, the measure point threshold is determined and measure points are classified; 4, in the step of constructing a convolution network for training and evaluation, the evaluation results of a dam and the monitoring system at all levels by professional monitors are obtained as a training set and a testing set, then the convolution neural network is trained based on the training set and the testing set, and finally the safety comprehensive evaluation for the dam is made.