Hong Guo, Xiaokai Niu and Zhitian Xie
The occurrence of segment cracks caused by load changes in shield tunnels would affect the safety of the tunnel structure. To this end, a three-dimensional fine shield tunnel…
Abstract
Purpose
The occurrence of segment cracks caused by load changes in shield tunnels would affect the safety of the tunnel structure. To this end, a three-dimensional fine shield tunnel segment model based on the extended finite element method (XFEM) is established.
Design/methodology/approach
The cracking law of shield segment cracks is studied in two forms: overloading and unloading. The relationship between crack length, width and depth and transverse convergence and deformation is analyzed.
Findings
The results show that the cracks in shield tunnels mainly occur on the outer side of the arch waist and the inner side of the crown and bottom. Under overloading and unloading conditions, the length, width and depth of cracks increase non-linearly as the transverse convergence deformation increases. Under the same convergent deformation, the deeper the buried depth, the smaller the crack length, width and depth. Meanwhile, under overloading conditions, the influence of buried depth on the width and depth of cracks is more significant. In terms of crack width and depth, unloading conditions are more dangerous than overloading conditions.
Originality/value
The findings have a guiding effect for the management of cracks in shield tunnels during operation.
Details
Keywords
Zhitian Zhang, Hongdong Zhao, Yazhou Zhao, Dan Chen, Ke Zhang and Yanqi Li
In autonomous driving, the inherent sparsity of point clouds often limits the performance of object detection, while existing multimodal architectures struggle to meet the…
Abstract
Purpose
In autonomous driving, the inherent sparsity of point clouds often limits the performance of object detection, while existing multimodal architectures struggle to meet the real-time requirements for 3D object detection. Therefore, the main purpose of this paper is to significantly enhance the detection performance of objects, especially the recognition capability for small-sized objects and to address the issue of slow inference speed. This will improve the safety of autonomous driving systems and provide feasibility for devices with limited computing power to achieve autonomous driving.
Design/methodology/approach
BRTPillar first adopts an element-based method to fuse image and point cloud features. Secondly, a local-global feature interaction method based on an efficient additive attention mechanism was designed to extract multi-scale contextual information. Finally, an enhanced multi-scale feature fusion method was proposed by introducing adaptive spatial and channel interaction attention mechanisms, thereby improving the learning of fine-grained features.
Findings
Extensive experiments were conducted on the KITTI dataset. The results showed that compared with the benchmark model, the accuracy of cars, pedestrians and cyclists on the 3D object box improved by 3.05, 9.01 and 22.65%, respectively; the accuracy in the bird’s-eye view has increased by 2.98, 10.77 and 21.14%, respectively. Meanwhile, the running speed of BRTPillar can reach 40.27 Hz, meeting the real-time detection needs of autonomous driving.
Originality/value
This paper proposes a boosting multimodal real-time 3D object detection method called BRTPillar, which achieves accurate location in many scenarios, especially for complex scenes with many small objects, while also achieving real-time inference speed.