Detection method of tunnel lining voids based on guided anchoring mechanism. (October 2021)

• Record Type: Journal Article
• Authors: Xu, Fei; Li, He; Yao, Hongge; An, MingShou
• Is Part Of: Computers & electrical engineering. Volume 95(2021)
• Publication Date: 2021-10
• Subjects: Tunnel void disease -- Neural network -- Guide anchoring -- GIoU; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2021.107462
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: The interpretation of GPR images depends heavily on the personal experience of the engineer. Deep learning neural network can effectively extract tunnel disease features. Data augmentation can be used to improve the training performance of deep learning methods. The generalized intersection over union optimizes the regression evaluation standard. The guide anchoring mechanism is added to optimize the regional recommendation network. Abstract: In tunnel construction engineering, the form of tunnel void diseases are complex and easily affected by the geographical environment. The traditional manual interpretation of image data has the characteristics of heavy workload, high probability of missing, and misjudgment. This paper constructs a convolution neural network that integrates the mechanism of guiding anchoring to detect tunnel voids. The network is composed of four parts: Feature extraction network extracts disease features from the enriched samples; Region proposal by guided anchoring join the generalized intersection over union (GIoU) evaluation criteria, and predict the shape of the anchor point through learning; The obtained feature maps are fixed in the region of interest pooling; Finally, the disease features are classified and bounding box regression. Compared with the existing target detection algorithm, the experimental results show that the improved network achieves an average classification accuracy of 92.74%, and the trained model has good generalization ability and robustness. Graphical abstract: Image, graphical abstract