CNN-based crack recognition method and device and storage device

Abstract

The invention provides a CNN-based crack recognition method and device and a storage device. The method comprises the steps that sample pictures are collected and classified; the classified sample pictures are preprocessed; a CNN learning network is established to learn the sample pictures; a test link is established to test a trained CNN model; whether the test result meets a requirement is judged; if not, the step of establishing the CNN learning network is returned to and continues to be executed; and if yes, expected crack recognition information is acquired. The CNN-based crack recognition device and the storage device are used for implementing the method. Through the CNN-based crack recognition method and device and the storage device, the crack recognition information can be obtained efficiently in real time.

Description

technical field [0001] The invention relates to the field of pattern recognition, in particular to a CNN-based crack recognition method, device and storage device. Background technique [0002] In the field of underwater monitoring, such as monitoring whether there are cracks in the underwater dam body of a dam, due to the complex environment and too many unpredictable factors, it is extremely difficult to monitor the cracks in the underwater dam body. At the same time, the existing equipment does not support the collection and monitoring of crack samples underwater, and the method of manually entering the water for inspection is not only inefficient, but also expensive and impractical. Therefore, how to effectively monitor the cracks of the underwater dam body with the help of technical means has become an urgent problem to be solved. Contents of the invention [0003] The present invention provides a CNN-based crack identification method, device and storage device, whic...

AI Technical Summary

Problems solved by technology

[0002] In the field of underwater monitoring, such as monitoring whether there are cracks in the underwater dam body of the dam, due to the complex environment and too many unpredictable factors, it is extremely difficult to monitor the cracks in the underwater dam body

At the same time, the existing equipment does not support the collection and monitoring of crack samples underwater, and the method of manually entering the water for inspection is not only inefficient, but also expensive and impractical

Images