当前位置: X-MOL 学术Comput. Aided Civ. Infrastruct. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
An optimization strategy to improve the deep learning-based recognition model of leakage in shield tunnels
Computer-Aided Civil and Infrastructure Engineering ( IF 9.6 ) Pub Date : 2021-06-28 , DOI: 10.1111/mice.12731
Yadong Xue 1 , Fei Jia 1 , Xinyuan Cai 1 , Mahdi Shadabfar 1, 2 , Hongwei Huang 1
Affiliation  

Due to the interference problems of complex on-site installations attached to shield tunnel lining surface, deep learning models, developed for leakage datasets of shield tunnels, are not prepared to meet engineering requirements. Therefore, it is of utmost importance to optimize the original model based on the characteristics of leakage datasets. For this purpose, the present study adopted Mask R-CNN as the baseline and improved its performance from two aspects, including the properties of shield tunnel leakage datasets and detection errors of the original model in the testing set. With reference to the properties of leakage datasets, the model compression technique was implemented to remove the redundant parameters in the training stage and enhance the detection accuracy and speed of the original model. Besides, three error types were grouped to explore the optimization direction in practical application. Accordingly, four different optimization measurements were fulfilled step-by-step to improve the model performance. It was concluded that the compressed model with 62% sparsity reached average precision (AP) of 0.399 at the detection speed of 7 frames per second (FPS), which was 0.144 higher and 2 FPS faster than that of the original model, respectively. The improvements in the model concerned were also quite different with the three error types moderated, indicating that the optimization direction of the original model needed to be focused on the error types with higher AP promotion. In addition, the AP value of the original model significantly augmented from 25.5% to 51.1% upon minimizing the detection errors on shield tunnel leakage datasets.

中文翻译:

一种改进基于深度学习的盾构隧道渗漏识别模型的优化策略

由于附加在盾构隧道衬砌表面的复杂现场装置的干扰问题,为盾构隧道泄漏数据集开发的深度学习模型无法满足工程要求。因此,根据泄漏数据集的特点对原始模型进行优化至关重要。为此,本研究以Mask R-CNN为基准,从盾构隧道渗漏数据集的性质和测试集中原始模型的检测误差两个方面改进其性能。参考泄漏数据集的特性,实施模型压缩技术,去除训练阶段的冗余参数,提高原始模型的检测精度和速度。除了,对三种错误类型进行分组,探索实际应用中的优化方向。因此,逐步完成了四种不同的优化测量以提高模型性能。得出的结论是,稀疏度为 62% 的压缩模型在每秒 7 帧(FPS)的检测速度下达到了 0.399 的平均精度(AP),分别比原始模型高 0.144 和快 2 FPS。所关注的模型的改进也与缓和的三种错误类型有很大的不同,表明原模型的优化方向需要集中在AP提升较高的错误类型上。此外,在最小化盾构隧道泄漏数据集的检测误差后,原始模型的 AP 值从 25.5% 显着增加到 51.1%。
更新日期:2021-06-28
down
wechat
bug