Tunnel Lining Defect Identification Method Based on Small Sample Learning

Abstract

Aiming at the problem of insufficient number of samples due to the difficulty of data acquisition in the identification of tunnel lining defects, a generative adversarial network was introduced to expand the data, and the network was improved for the mode collapse problem of the traditional generative adversarial network and the problem that the generated image features were not obvious. On the basis of the WGAN-GP network, a deep convolutional network is selected as its backbone network, and the effectiveness of the deep convolutional network in feature extraction by Lv et al. (2022) is used to improve the quality of the images generated by the network. In addition, the residual module is introduced into the discriminator network, and the upsampling module is introduced into the generator network, which further solves the problem of gradient disappearance of the two networks during the update iteration process through the idea of cross-connection, while better retaining the underlying features, which effectively solves the problem of mode collapse and low quality of generated images in the generative adversarial network. Compared with the original network, the image quality of the generated adversarial network is improved, and the discriminator and generator losses converge faster. At the same time, the recognition accuracy of the YOLOv5 network is improved by 4.4% and the overfitting phenomenon is alleviated, which proves the effectiveness of the method under the limited training data set.

Prediction method of longitudinal surface settlement caused by double shield tunnelling based on deep learning

“…Table 1 demonstrates the common research methods currently used to tackle the problem of inadequate database data. These methods involve employing effective feature extraction techniques 35 – 37 , enhancing the database through the inclusion of outcomes derived from physical formulas 38 , 39 , numerical simulation results 40 , and results obtained using deep learning algorithms 41 . However, these methods do not contribute to the enrichment of high-fidelity data within their own database.…”

Lightweight Tunnel Defect Detection Algorithm Based on Knowledge Distillation

“…Three-dimensional ground-penetrating radar data and the Yolo model were merged by Liu et al [7] to quickly identify road problems and accomplish automated defect detection. The project team enhanced the SGD network [8] to increase model accuracy and added an adversarial network [9] to increase the dataset. Researchers' attention is now focused on finding ways to ensure lightweight deployment in the context of the development of edgeenabled devices.…”

MFF-YOLO: An Accurate Model for Detecting Tunnel Defects Based on Multi-Scale Feature Fusion

“…To increase the accuracy and usefulness of tunnel defect detection, as well as to better support and guarantee tunnel construction and maintenance operations, we will keep researching new methods and approaches. Previous studies by our group have included improvements to SGD networks and residual modules [ 15 ], the introduction of adversarial networks for data expansion problems [ 16 ], and the use of neural network fusion techniques to improve the generalization performance of the model.…”