Dam safety comprehensive evaluation method based on depth learning

Abstract

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.

Description

technical field [0001] The invention relates to a method for comprehensively evaluating dam safety based on deep learning, in particular to a method for comprehensively evaluating safety for dam automatic monitoring data, and belongs to the field of dam safety monitoring. . Background technique [0002] Deep learning is a method based on representation learning of data in machine learning. Observations (such as an image) can be represented in a variety of ways, such as a vector of intensity values ​​for each pixel, or more abstractly as a series of edges, regions of a specific shape, etc. Whereas it is easier to learn tasks from examples (e.g., face recognition or facial expression recognition) using some specific representations. Deep learning uses unsupervised or semi-supervised feature learning and hierarchical feature extraction efficient algorithms to replace manual feature acquisition. [0003] Dam safety monitoring is the measurement and observation of the main str...

AI Technical Summary

Problems solved by technology

[0006] Purpose of the invention: Aiming at the problems that the dam safety monitoring system has many monitoring points, huge amount of data, high difficulty and low efficiency in manual processing and evaluation, the present invention provides a comprehensive evaluation method for dam safety based on deep learning, which can analyze massive monitoring data Carry out feature learning, efficiently and accurately calculate and process and obtain evaluation results

Images