Method for rapid detection and treatment of cracks in tunnel lining based on deep learning

The number and scale of tunnels around the world are continuously increasing, but various disease problems during the operation period have also followed, and they have become one of the important problems facing tunnels at present. Many detection methods have been proposed in the field of tunnel detection, such as traditional manual detection method, ultrasonic detection method, ground-penetrating radar method, laser scanning method and inspection method based on image processing technology. However, due to the high cost of equipment, single test content, strict test environment and other reasons, most of the current tunnel routine inspection is still manual inspection. In order to solve the existing problems in tunnel detection, a method for rapid detection and treatment analysis of cracks in tunnel linings based on deep learning is proposed. Firstly, lining cracks were selected as the main research objects, and their causes and treatment measures in different parts were analyzed. Secondly, the AlexNet convolutional neural network based on the Caffe framework was used to identify the cracks. The crack images were collected to establish a data set, and the network parameters were modified and trained. Then use MATLAB to extract the crack length and width, and design a human-machine interactive tunnel lining crack detection program in MATLAB GUI. Finally, the content and results of this paper are discussed.