http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Yang Xu,Jin Zhao,Fangqiao Hu,Weidong Qiao,Weida Zhai,Yuequan Bao,Hui Li 국제구조공학회 2022 Smart Structures and Systems, An International Jou Vol.29 No.1
Despite recent breakthroughs in deep learning and computer vision fields, the pixel-wise identification of tiny objects in high-resolution images with complex disturbances remains challenging. This study proposes a modified U-net for tiny crack segmentation in real-world steel-box-girder bridges. The modified U-net adopts the common U-net framework and a novel Self-Attention-Self-Adaption (SASA) neuron as the fundamental computing element. The Self-Attention module applies softmax and gate operations to obtain the attention vector. It enables the neuron to focus on the most significant receptive fields when processing large-scale feature maps. The Self-Adaption module consists of a multiplayer perceptron subnet and achieves deeper feature extraction inside a single neuron. For data augmentation, a grid-based crack random elastic deformation (CRED) algorithm is designed to enrich the diversities and irregular shapes of distributed cracks. Grid-based uniform control nodes are first set on both input images and binary labels, random offsets are then employed on these control nodes, and bilinear interpolation is performed for the rest pixels. The proposed SASA neuron and CRED algorithm are simultaneously deployed to train the modified U-net. 200 raw images with a high resolution of 4928 × 3264 are collected, 160 for training and the rest 40 for the test. 512 × 512 patches are generated from the original images by a sliding window with an overlap of 256 as inputs. Results show that the average IoU between the recognized and ground-truth cracks reaches 0.409, which is 29.8% higher than the regular U-net. A five-fold cross-validation study is performed to verify that the proposed method is robust to different training and test images. Ablation experiments further demonstrate the effectiveness of the proposed SASA neuron and CRED algorithm. Promotions of the average IoU individually utilizing the SASA and CRED module add up to the final promotion of the full model, indicating that the SASA and CRED modules contribute to the different stages of model and data in the training process.
Chunbao Xiong,Sida Lian,Wen Chen 대한토목학회 2023 KSCE Journal of Civil Engineering Vol.27 No.3
Because the steel structure trestle has been in service under heavy load for a long time, the steel structure trestle is prone to cracks around the welds or bolt holes, which can lead to structural collapse in severe cases. Aiming at the characteristics of stable and high-quality images obtained by the unmanned consumer-grade camera monitoring system, this paper proposed structure health monitoring (SHM) system which is based on consumer-grade camera. The SHM system can identify crack damage and locate steadily in long term, which provides the technical support of practical application in intelligent SHM system. The method first performed edge detection on the trestle structure, followed by pixel-level semantic segmentation and crack localization. Canny edge detection algorithm was used to identify trestle structures in the camera image. The panorama trestle structure was divided into areas of suitable size, and the camera focused on each divided area one by one. Then the improved DeepLab V3+ model was trained by constructing global and local datasets. Then the improved DeepLab V3+ model was used to perform pixel-level semantic segmentation on the trestle images of the divided regions. Finally, based on the Speeded Up Robust Features and combined with the image, a panorama crack location output method was proposed. The system was used to test a section of a trestle in a coal mining industrial park, and the system showed that the method could efficiently and accurately identify and locate the crack damage.
Ta, Quoc-Bao,Pham, Quang-Quang,Kim, Yoon-Chul,Kam, Hyeon-Dong,Kim, Jeong-Tae Techno-Press 2022 Structural monitoring and maintenance Vol.9 No.3
In this study, the impact of assigned pixel labels on the accuracy of crack image identification of steel structures is examined by using an atrous separable convolution neural network (ASCNN). Firstly, images containing fatigue cracks collected from steel structures are classified into four datasets by assigning different pixel labels based on image features. Secondly, the DeepLab v3+ algorithm is used to determine optimal parameters of the ASCNN model by maximizing the average mean-intersection-over-union (mIoU) metric of the datasets. Thirdly, the ASCNN model is trained for various image sizes and hyper-parameters, such as the learning rule, learning rate, and epoch. The optimal parameters of the ASCNN model are determined based on the average mIoU metric. Finally, the trained ASCNN model is evaluated by using 10% untrained images. The result shows that the ASCNN model can segment cracks and other objects in the captured images with an average mIoU of 0.716.
손병직(Son Byung Jik),허용학(Huh Yong-Hak),박휘립(Park Philip),김동진(Kim dong Jin) 대한토목학회 2006 대한토목학회논문집 A Vol.26 No.4A
정적 손상 탐지방법은 동적 방법과 비교해서 실제 적용하기에 단순하고 효과적이다. 본 논문에서는 정적데이타를 이용하는 방법으로 변위, 처짐각, 곡률을 이용한 강박스 교량의 손상 탐지 방법에 대해서 연구하였다. 변위는 유한요소 해석에서 얻고, 처짐각과 곡률은 변위로부터 중앙차분법을 이용하여 구하였다. 손상되지 않은 경우와 손상된 경우의 응답차의 절대값으로 손상의 위치를 탐지하였다. 손상은 박스의 모서리 균열을 singular 요소를 사용하여 직접 모델링하여, 실질적인 거동을 분석하였다. 해석 결과 응답차의 절대값으로 손상의 위치를 탐지하기에 매우 효과적이었다. To detect and evaluate the damage present in bridge, static identification method is known to be simple and effective, compared to dynamic method. In this study, the damage detection method in steel box girder bridge using static responses including displacement, slope and curvature is examined. The static displacement is calculated using finite element analysis and the slope and curvature are determined from the displacement using central difference method. The location of damage is detected using the absolute differences of these responses in intact and damaged bridge. Steel box girder bridge with comer crack is modeled using singular element in finite element method. The results show that these responses were significantly useful in detecting and predicting the location of damage present in bridge.