共查询到20条相似文献,搜索用时 0 毫秒
1.
Keunyoung Jang Yun‐Kyu An Byunghyun Kim Soojin Cho 《Computer-Aided Civil and Infrastructure Engineering》2021,36(1):14-29
This article proposes a deep learning‐based automated crack evaluation technique for a high‐rise bridge pier using a ring‐type climbing robot. First, a ring‐type climbing robot system composed of multiple vision cameras, climbing robot, and control computer is developed. By spatially moving the climbing robot system along a target bridge pier with close‐up scanning condition, high‐quality raw vision images are continuously obtained. The raw vision images are then processed through feature control‐based image stitching, deep learning‐based semantic segmentation, and Euclidean distance transform–based crack quantification algorithms. Finally, a digital crack map on the region of interest (ROI) of the target bridge pier can be automatically established. The proposed technique is experimentally validated using in situ test data obtained from Jang–Duck bridge in South Korea. The test results reveal that the proposed technique successfully evaluates cracks on the entire ROI of the bridge pier with precision of 90.92% and recall of 97.47%. 相似文献
2.
3.
4.
通过对四个DeJong典型函数最小值问题的数值分析,系统地研究了差异进化算法中变异因子和交叉因子两个关键参数对整个进化过程的影响,为运用差异进化算法进行优化运算时的参数定值提供了参考。 相似文献
5.
6.
7.
This paper deals with the weight minimization of planar steel trusses by adopting a differential evolution-based algorithm. Square hollow sections are considered. The design optimization refers to size, shape and topology. The design variables are represented by the geometrical dimensions of the cross sections of the different components of the truss, directly involving the size of the structure, and by some geometrical parameters affecting the outer shape of the truss. The topology is included in the optimization search in a particular way, since the designer at different runs of the algorithm can change the number of bays keeping constant the total length of the truss, to successively choose the best optimal solution. The minimum weight optimum design is posed as a single-objective optimization problem subject to constraints formulated in accordance with the current Eurocode 3. The optimal solution is obtained by a Differential Evolutionary (DE) algorithm. In the DE algorithm, a particular combination of mutation and crossover operators is adopted in order to achieve the best solutions and a specific way for dealing with constraints is introduced. The effectiveness of the proposed approach is shown with reference to two case-studies. The analysis results prove the versatility of the optimizer algorithm with regard to the three optimization categories of sizing, shape, topology as well as its high computational performances and its efficacy for practical applications. In particular useful practical indications concerning the geometrical dimensions of the various involved structural elements can be deduced by the optimal solutions: in a truss girder the cross section of the top chord should be bigger than the one of the bottom chord as well as diagonals should be characterized by smaller cross sections with respect to the top and bottom chords in order to simultaneously optimize the weight and ensure an optimal structural behaviour. 相似文献
8.
9.
当前桥梁建设施工的建筑材料质量逐渐下降,桥梁建筑施工的程序逐步简化,同时受到监督不利等因素的影响,导致目前桥梁建设事业遭受到了发展瓶颈,为此,笔者结合多年的桥梁理论经验和实际数据考察,对桥梁结构的检测和加固处理问题进行了深入的分析。 相似文献
10.
11.
12.
Emad Elbeltagi Tarek Hegazy Abdel Hady Hosny Adel Eldosouky 《Construction Management & Economics》2013,31(7):689-697
The appropriate layout of temporary facilities on a construction site has a large impact on construction safety and productivity. For the duration of a project the site layout may need to be efficiently re-organized at various intervals to satisfy the schedule requirements and to maintain site efficiency. This paper presents a practical model for schedule-dependent site layout planning in construction. The proposed model uses a combination of artificial intelligence tools (knowledge-based systems, fuzzy logic, and genetic algorithms) to generate, optimize, and re-organize the site layout plan at frequent intervals during the project. The model incorporates flexible representation of irregular site shapes and several options for placing facilities. Based on the proposed model, an automated system is developed, fully integrated with widely used scheduling software. At each schedule interval, the system recalculates the space requirements and, for the convenience of congested sites, can utilize parts of the constructed space to accommodate temporary facilities. Details of the schedule-dependent model are described, and its application in an actual case study project is presented to demonstrate its capabilities. 相似文献
13.
Chaobo Zhang Chih‐chen Chang Maziar Jamshidi 《Computer-Aided Civil and Infrastructure Engineering》2020,35(4):389-409
Early and timely detection of surface damages is important for maintaining the functionality, reliability, and safety of concrete bridges. Recent advancement in convolution neural network has enabled the development of deep learning‐based visual inspection techniques for detecting multiple structural damages. However, most deep learning‐based techniques are built on two‐stage, proposal‐driven detectors using less complex image data, which could be restricted for practical applications and possible integration within intelligent autonomous inspection systems. In this study, a faster, simpler single‐stage detector is proposed based on a real‐time object detection technique, You Only Look Once (YOLOv3), for detecting multiple concrete bridge damages. A field inspection images dataset labeled with four types of concrete damages (crack, pop‐out, spalling, and exposed rebar) is used for training and testing of YOLOv3. To enhance the detection accuracy, the original YOLOv3 is further improved by introducing a novel transfer learning method with fully pretrained weights from a geometrically similar dataset. Batch renormalization and focal loss are also incorporated to increase the accuracy. Testing results show that the improved YOLOv3 has a detection accuracy of up to 80% and 47% at the Intersection‐over‐Union (IoU) metrics of 0.5 and 0.75, respectively. It outperforms the original YOLOv3 and the two‐stage detector Faster Region‐based Convolutional Neural Network (Faster R‐CNN) with ResNet‐101, especially for the IoU metric of 0.75. 相似文献
14.
通过对某斜腿刚架拱桥的详细检测,对桥梁运营的技术性能进行了准确评估;在此基础上经结构验算,拟定了以更换微弯板构件、加强桥面铺装、封闭裂缝等针对性的加固措施,提高了桥梁运营安全性,延长了桥梁使用寿命。 相似文献
15.
16.
17.
随着桥梁崩塌事故的增多,针对桥梁的结构进行科学的检测与及时的加固处理已经成了绝大多数劣质桥梁不出现坍塌事故的唯一解决之道。此外,年久失修的桥梁也必须进行适时的结构检测与加固处理。 相似文献
18.