基于深度学习的隧道衬砌裂缝智能检测分析系统OA
An automatic system for detecting and analyzing tunnel lining cracks based on deep learning
针对隧道衬砌裂缝检测效率低、微裂缝识别困难等问题,构建了一套闭环隧道衬砌裂缝自动检测系统.采集国内5省份21条隧道衬砌数据,利用优化标注方法,建立了隧道裂缝专用数据集T_crack.对语义分割网络进行改进,提出多通道并行混合注意力机制(MPMA),以提高微裂纹的识别精度.开发了裂缝检测应用,以实现裂缝识别、量化、定位及全景图像生成功能.试验结果表明,改进网络在T_crack数据集上的平均Dice系数为84.06%,平均准确率为82.94%,平均交并比为75.68%.相比传统标注方法,优化标注方法使标注效率平均提升90.23%.系统检测平均绝对误差为0.076 mm,低于工程检测精度要求,将其应用于隧道长期运维中,可以显著提升检测工作效率.
To address the low detection efficiency and diffi-cult identification of microcracks in tunnel lining cracks,a closed-loop automatic detection system for tunnel lining cracks was proposed.Lining data were collected from 21 tunnels across five provinces of China,and an optimized an-notation method was adopted to construct a dedicated tunnel crack dataset(T_Crack).The semantic segmentation net-work was improved by introducing a multichannel parallel mixed attention mechanism(MPMA)to enhance micro-crack recognition accuracy.A tunnel crack detection appli-cation was developed to enable crack identification,quanti-fication,localization,and panoramic image generation.The results show that the improved network achieves a mean Dice coefficient of 84.06%,a mean accuracy of 82.94%,and a mean intersection over union of 75.68%on T_Crack.Compared with the traditional annotation method,the opti-mized annotation method improves the labeling efficiency by 90.23%on average.The mean absolute error of the sys-tem is 0.076 mm,which is lower than the engineering de-tection accuracy requirement.The application of this system to long-term tunnel operation and maintenance can signifi-cantly improve the efficiency of tunnel inspection.
王萌;杨燕泽;刘诚;徐慧通;张小月
北京交通大学土木建筑工程学院,北京 100044北京交通大学土木建筑工程学院,北京 100044||中国能源建设集团云南省电力设计院有限公司,昆明 650051中路高科交通检测检验认证有限公司,北京 100088北京交通大学土木建筑工程学院,北京 100044北京交通大学土木建筑工程学院,北京 100044
交通工程
隧道裂缝检测隧道裂缝数据集语义分割系统开发裂缝量化
tunnel crack detectiontunnel crack datasetse-mantic segmentationsystem developmentcrack quantifi-cation
《东南大学学报(英文版)》 2026 (3)
337-350,14
Beijing Natural Science Foundation(No.26JL009),the National Natural Science Foundation of China(No.52478491).
评论