Pub Date : 2024-06-06DOI: 10.1177/13694332241260140
Chenxi Xing, Zidong Xu, Hao Wang
To rapidly and effectively assess the bridge seismic-resistant capability, it is essential to conduct efficient predictions of bridge seismic responses. Recently, physics informed neural network (PINN) has made great progress and utilized to solve differential equations in different fields. However, how to increase its accuracy and efficiency still remains an open challenge. In this work, a novel gradient-enhanced Fourth-Order Runge-Kutta PINN (gRK4-PINN), as a powerful hybrid PINN, is utilized to achieve this goal. As for gRK4-PINN, the physical information is not simply embedded into the loss function; instead, the RK4 method and the physical model is intricately integrated with the neural network. In addition, to improve the predictive performance, additional gradient equation is directly embedded in loss function. A large-span continuous girder high speed railway (CGHSR) bridge is adopted as numerical experiment to validate the fidelity of the proposed method. Results reveal that the Mean Absolute Error (MAE) of the predicting seismic responses is relatively small, whose value is below 0.014 in most of the time. These small MAE values indicate that the proposed gRK4-PINN performs well in predicting the seismic responses of the CGHSR bridge.
{"title":"Structural seismic responses prediction using the gradient-enhanced hybrid PINN","authors":"Chenxi Xing, Zidong Xu, Hao Wang","doi":"10.1177/13694332241260140","DOIUrl":"https://doi.org/10.1177/13694332241260140","url":null,"abstract":"To rapidly and effectively assess the bridge seismic-resistant capability, it is essential to conduct efficient predictions of bridge seismic responses. Recently, physics informed neural network (PINN) has made great progress and utilized to solve differential equations in different fields. However, how to increase its accuracy and efficiency still remains an open challenge. In this work, a novel gradient-enhanced Fourth-Order Runge-Kutta PINN (gRK4-PINN), as a powerful hybrid PINN, is utilized to achieve this goal. As for gRK4-PINN, the physical information is not simply embedded into the loss function; instead, the RK4 method and the physical model is intricately integrated with the neural network. In addition, to improve the predictive performance, additional gradient equation is directly embedded in loss function. A large-span continuous girder high speed railway (CGHSR) bridge is adopted as numerical experiment to validate the fidelity of the proposed method. Results reveal that the Mean Absolute Error (MAE) of the predicting seismic responses is relatively small, whose value is below 0.014 in most of the time. These small MAE values indicate that the proposed gRK4-PINN performs well in predicting the seismic responses of the CGHSR bridge.","PeriodicalId":505409,"journal":{"name":"Advances in Structural Engineering","volume":"326 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141380989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-16DOI: 10.1177/13694332241254597
Dan Wang, Yi Tao, Jinben Gu, Zhiheng Chen, Qingxuan Shi
A novel composite column was introduced by integrating a concrete-filled steel tube column encasing a Fiber Reinforced Polymer (FRP) confined ultra high performance concrete (UHPC) core. In this paper, the seismic performance of four SCF-UHPC composite column-to-steel beam connections using external diaphragm joints was experimentally investigated under the quasi-static test. All specimens failed due to the formation of plastic hinges at the beams and the tearing failure on the beam flanges at the plastic hinge zone. The local buckling at the column end and the panel zone was observed for the specimens receiving the higher axial compression ratio. The increase of FRP tube thickness is more effective in improving the ductility and energy dissipation capacity of the joints than increasing the UHPC core diameter. On the contrary, increasing the UHPC core diameter led to better resistance to the shear deformation of the panel zone. The proportion of shear deformation to the total deformation of the panel zone and the strain distributions were investigated to determine the effect of each component. The composite column in the panel zone mainly carried the compression-bending effort, and the external diaphragm mainly took the shear effort. All joints were eventually classified as semi-rigid type joints, according to the initial rotational stiffness.
{"title":"Seismic performance of external diaphragm joints of steel beam-to-CFST column encasing fiber reinforced polymer confined UHPC core","authors":"Dan Wang, Yi Tao, Jinben Gu, Zhiheng Chen, Qingxuan Shi","doi":"10.1177/13694332241254597","DOIUrl":"https://doi.org/10.1177/13694332241254597","url":null,"abstract":"A novel composite column was introduced by integrating a concrete-filled steel tube column encasing a Fiber Reinforced Polymer (FRP) confined ultra high performance concrete (UHPC) core. In this paper, the seismic performance of four SCF-UHPC composite column-to-steel beam connections using external diaphragm joints was experimentally investigated under the quasi-static test. All specimens failed due to the formation of plastic hinges at the beams and the tearing failure on the beam flanges at the plastic hinge zone. The local buckling at the column end and the panel zone was observed for the specimens receiving the higher axial compression ratio. The increase of FRP tube thickness is more effective in improving the ductility and energy dissipation capacity of the joints than increasing the UHPC core diameter. On the contrary, increasing the UHPC core diameter led to better resistance to the shear deformation of the panel zone. The proportion of shear deformation to the total deformation of the panel zone and the strain distributions were investigated to determine the effect of each component. The composite column in the panel zone mainly carried the compression-bending effort, and the external diaphragm mainly took the shear effort. All joints were eventually classified as semi-rigid type joints, according to the initial rotational stiffness.","PeriodicalId":505409,"journal":{"name":"Advances in Structural Engineering","volume":"41 24","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140971240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-15DOI: 10.1177/13694332241252282
E. Cho, Sang Whan Han
High-strength steel (HSS) can effectively and economically design structural members that withstand large forces induced by extreme events such as earthquakes. To evaluate the seismic performance of HSS members and structures using nonlinear finite element (FE) analyses, using an accurate material model is important, which can simulate the inelastic cyclic behavior of the HSS. The peculiar material behavior of HSS needs to be considered in the model. This study used a combined hardening model to construct the material model. The configuration of the model and the constituent model parameter values are determined to precisely simulate the low-cycle fatigue (LCF) behavior of HSS. An efficient particle swarm optimization (PSO) algorithm is used to determine parameter values with LCF test data of 54 individual HSS coupons. In additions, to conveniently determine the model parameter values with only monotonic tensile test data instead of conducting expensive LCT tests, empirical equations are proposed. It is shown that the LCF curves of HSS can be accurately simulated using the constructed material model with the proposed equations.
{"title":"A numerical model simulating cyclic behavior of high-strength steel","authors":"E. Cho, Sang Whan Han","doi":"10.1177/13694332241252282","DOIUrl":"https://doi.org/10.1177/13694332241252282","url":null,"abstract":"High-strength steel (HSS) can effectively and economically design structural members that withstand large forces induced by extreme events such as earthquakes. To evaluate the seismic performance of HSS members and structures using nonlinear finite element (FE) analyses, using an accurate material model is important, which can simulate the inelastic cyclic behavior of the HSS. The peculiar material behavior of HSS needs to be considered in the model. This study used a combined hardening model to construct the material model. The configuration of the model and the constituent model parameter values are determined to precisely simulate the low-cycle fatigue (LCF) behavior of HSS. An efficient particle swarm optimization (PSO) algorithm is used to determine parameter values with LCF test data of 54 individual HSS coupons. In additions, to conveniently determine the model parameter values with only monotonic tensile test data instead of conducting expensive LCT tests, empirical equations are proposed. It is shown that the LCF curves of HSS can be accurately simulated using the constructed material model with the proposed equations.","PeriodicalId":505409,"journal":{"name":"Advances in Structural Engineering","volume":"12 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140971994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-15DOI: 10.1177/13694332241254606
Haylim Chha, Yongbo Peng
Conventional active controllers generally adopt initial dynamic properties of intact structures to calculate optimal control force for magnetorheological damper, which eventually leads to ideal damping force of the device. Also, they cannot assure trade-off between damping force and response reduction under non-stationary excitations. To this end, an adaptive semiactive control algorithm for magnetorheological damper is proposed. Using wavelet packet transform, an improved control law determines optimal control forces in terms of resonant and non-resonant frequency bands in time interval. Both frequency bands are established based on natural frequency(ies) of structures, making damping force rely on actual structural properties and achieving trade-off under non-stationary disturbances. A refined clipped-optimal control algorithm is then deployed to convert optimal control force to the device’s voltage. A numerical study of a six-degree-of-freedom structure under four near- and far-fault ground accelerations reveals that the scheme outperforms existing controllers while attaining cost-effectiveness of damping force versus response alleviations.
{"title":"Adaptive semiactive control of structure with magnetorheological dampers using wavelet packet transform","authors":"Haylim Chha, Yongbo Peng","doi":"10.1177/13694332241254606","DOIUrl":"https://doi.org/10.1177/13694332241254606","url":null,"abstract":"Conventional active controllers generally adopt initial dynamic properties of intact structures to calculate optimal control force for magnetorheological damper, which eventually leads to ideal damping force of the device. Also, they cannot assure trade-off between damping force and response reduction under non-stationary excitations. To this end, an adaptive semiactive control algorithm for magnetorheological damper is proposed. Using wavelet packet transform, an improved control law determines optimal control forces in terms of resonant and non-resonant frequency bands in time interval. Both frequency bands are established based on natural frequency(ies) of structures, making damping force rely on actual structural properties and achieving trade-off under non-stationary disturbances. A refined clipped-optimal control algorithm is then deployed to convert optimal control force to the device’s voltage. A numerical study of a six-degree-of-freedom structure under four near- and far-fault ground accelerations reveals that the scheme outperforms existing controllers while attaining cost-effectiveness of damping force versus response alleviations.","PeriodicalId":505409,"journal":{"name":"Advances in Structural Engineering","volume":"58 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140975983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-15DOI: 10.1177/13694332241252283
Zhang Xue, Jinjie Men, Rong Qiang
Near-fault ground motions with high acceleration peaks and long-period velocity pulses pose a serious threat to the reliability of engineering structures. To reduce the displacement of isolation layer and improve the seismic performance of superstructure under the near-fault ground motions, a composite isolation system, which is composed of friction pendulum system (FPS) and inerter system, namely FPIS, was used in this paper. Based on D’Alembert’s principle, the nonlinear motion equations of a base-isolated structure with FPIS were established. The damping effect of two different mechanical layouts of FPIS subsystems, i.e, series-parallel inerter system-I-FPS(SPIS-I-FPS) or series-parallel inerter system-II-FPS(SPIS-II-FPS), were investigated in this study. The strong nonlinearity of FPIS was considered, and the inerter system parameters were designed based on the principle of maximum damping enhancement. The fourth-order Runge-Kutta approach was used to solve the dynamic response of a multi-degree-of-freedom system under seismic excitations. The effectiveness of FPIS was verified by comparing the isolation layer displacement and the acceleration of superstructure calculated by MATLAB with the friction pendulum system and viscous damper (FPS-VD). The nonlinear time history analysis results indicate that within a certain additional damping range, the SPIS-I-FPS subsystem performs effectively than SPIS-II-FPS in reducing the superstructure acceleration and isolation layer displacement. To increase the energy dissipation efficiency of structures, it is recommended to increase the design parameters of the inerter system and control the friction coefficient of FPS within the range of 0.05∼0.10.
{"title":"Seismic response of structures with friction pendulum inerter system (FPIS) under near-fault earthquakes","authors":"Zhang Xue, Jinjie Men, Rong Qiang","doi":"10.1177/13694332241252283","DOIUrl":"https://doi.org/10.1177/13694332241252283","url":null,"abstract":"Near-fault ground motions with high acceleration peaks and long-period velocity pulses pose a serious threat to the reliability of engineering structures. To reduce the displacement of isolation layer and improve the seismic performance of superstructure under the near-fault ground motions, a composite isolation system, which is composed of friction pendulum system (FPS) and inerter system, namely FPIS, was used in this paper. Based on D’Alembert’s principle, the nonlinear motion equations of a base-isolated structure with FPIS were established. The damping effect of two different mechanical layouts of FPIS subsystems, i.e, series-parallel inerter system-I-FPS(SPIS-I-FPS) or series-parallel inerter system-II-FPS(SPIS-II-FPS), were investigated in this study. The strong nonlinearity of FPIS was considered, and the inerter system parameters were designed based on the principle of maximum damping enhancement. The fourth-order Runge-Kutta approach was used to solve the dynamic response of a multi-degree-of-freedom system under seismic excitations. The effectiveness of FPIS was verified by comparing the isolation layer displacement and the acceleration of superstructure calculated by MATLAB with the friction pendulum system and viscous damper (FPS-VD). The nonlinear time history analysis results indicate that within a certain additional damping range, the SPIS-I-FPS subsystem performs effectively than SPIS-II-FPS in reducing the superstructure acceleration and isolation layer displacement. To increase the energy dissipation efficiency of structures, it is recommended to increase the design parameters of the inerter system and control the friction coefficient of FPS within the range of 0.05∼0.10.","PeriodicalId":505409,"journal":{"name":"Advances in Structural Engineering","volume":"89 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140973182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-29DOI: 10.1177/13694332241242984
G. Zhang, Zhenwei Zhou, C. Wan, Zhenghao Ding, Zhishen Wu, Liyu Xie, Songtao Xue
The external excitations, interface forces and responses at the interface degrees-of-freedom are normally required in many existing substructural condition assessment methods, while they are difficult or even impossible to be accurately measured. To address this issue, a digital twin framework for output-only substructural damage identification with data fusion of muti-type responses is proposed in the present paper. First, heterogeneous responses including displacements, strains and accelerations from the target substructure are measured and divided into two sets. The multi-type responses in measurement set 2 are reconstructed with the first set of responses and transmissibility matrix in time domain. Then, a recovery method is introduced to obtain angular displacements from translational displacements and strains, to acquire angular accelerations from translational accelerations and the second order derivatives of strains by continuous wavelet transform. The recovered angular displacements and angular accelerations are involved into the evaluation of objective function. Besides, to avoid the single and monotonous search operation of traditional optimization algorithms, a reinforced learning-assisted Q-learning hybrid evolutionary algorithm (QHEA) by integrating Q-learning algorithm, differential evolution algorithm, Jaya algorithm, is developed as a search tool to solve the optimization-based inverse problem. The most suitable search strategy among DE/rand/1, DE/rand/2, DE/current-to-best/1, Jaya mutation in each iteration is selected and implemented under the guidance of Q-learning algorithm. Numerical studies on a three-span beam structure are performed to verify the effectiveness of the proposed approach. The results demonstrates that the proposed output-only substructural damage identification approach can accurately identify locations and severities of multiple damages even with high noise-polluted responses.
{"title":"Substructural damage identification in a digital twin framework using heterogeneous response reconstruction","authors":"G. Zhang, Zhenwei Zhou, C. Wan, Zhenghao Ding, Zhishen Wu, Liyu Xie, Songtao Xue","doi":"10.1177/13694332241242984","DOIUrl":"https://doi.org/10.1177/13694332241242984","url":null,"abstract":"The external excitations, interface forces and responses at the interface degrees-of-freedom are normally required in many existing substructural condition assessment methods, while they are difficult or even impossible to be accurately measured. To address this issue, a digital twin framework for output-only substructural damage identification with data fusion of muti-type responses is proposed in the present paper. First, heterogeneous responses including displacements, strains and accelerations from the target substructure are measured and divided into two sets. The multi-type responses in measurement set 2 are reconstructed with the first set of responses and transmissibility matrix in time domain. Then, a recovery method is introduced to obtain angular displacements from translational displacements and strains, to acquire angular accelerations from translational accelerations and the second order derivatives of strains by continuous wavelet transform. The recovered angular displacements and angular accelerations are involved into the evaluation of objective function. Besides, to avoid the single and monotonous search operation of traditional optimization algorithms, a reinforced learning-assisted Q-learning hybrid evolutionary algorithm (QHEA) by integrating Q-learning algorithm, differential evolution algorithm, Jaya algorithm, is developed as a search tool to solve the optimization-based inverse problem. The most suitable search strategy among DE/rand/1, DE/rand/2, DE/current-to-best/1, Jaya mutation in each iteration is selected and implemented under the guidance of Q-learning algorithm. Numerical studies on a three-span beam structure are performed to verify the effectiveness of the proposed approach. The results demonstrates that the proposed output-only substructural damage identification approach can accurately identify locations and severities of multiple damages even with high noise-polluted responses.","PeriodicalId":505409,"journal":{"name":"Advances in Structural Engineering","volume":"21 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140366742","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-29DOI: 10.1177/13694332241242980
Souvick Sadhukhan, Arghyadip Das, Satadru Bhattacharya, S. Dalui
The study is on the variation of pressure in different faces of rectangular plan-shaped tall buildings with interference conditions due to the presence of another building with the same shape and dimension connected through a multipurpose bridge. The analysis is done on computational fluid dynamics (namely ANSYS CFX) for 0° to 90° wind incidence angle (WIA). The buildings are spaced 60 m from each other. Different cases have been taken and analyzed based on the different positions of the bridge (i.e., 0.33H, 0.5H, and 0.67H) and compared with the isolated case (i.e., buildings without the bridge). A comparison study has been done in the form of interference factor (IF), so we can clearly understand the effect of the bridge at different heights of the building and isolated conditions on rectangular plan-shaped buildings. The study shows that when the bridge is at 0.5H and 0.33H, the force coefficient along X and Y produces similar results to an isolated condition for WIA of 60° and 30°, respectively.
{"title":"Interference effects on two rectangular tall buildings with coupling bridge in close proximity","authors":"Souvick Sadhukhan, Arghyadip Das, Satadru Bhattacharya, S. Dalui","doi":"10.1177/13694332241242980","DOIUrl":"https://doi.org/10.1177/13694332241242980","url":null,"abstract":"The study is on the variation of pressure in different faces of rectangular plan-shaped tall buildings with interference conditions due to the presence of another building with the same shape and dimension connected through a multipurpose bridge. The analysis is done on computational fluid dynamics (namely ANSYS CFX) for 0° to 90° wind incidence angle (WIA). The buildings are spaced 60 m from each other. Different cases have been taken and analyzed based on the different positions of the bridge (i.e., 0.33H, 0.5H, and 0.67H) and compared with the isolated case (i.e., buildings without the bridge). A comparison study has been done in the form of interference factor (IF), so we can clearly understand the effect of the bridge at different heights of the building and isolated conditions on rectangular plan-shaped buildings. The study shows that when the bridge is at 0.5H and 0.33H, the force coefficient along X and Y produces similar results to an isolated condition for WIA of 60° and 30°, respectively.","PeriodicalId":505409,"journal":{"name":"Advances in Structural Engineering","volume":"55 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140365904","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-29DOI: 10.1177/13694332241242975
Weihao Sun, Shitong Hou, Gang Wu, Dongming Feng, Jian-hu Fan
In-service urban utility tunnels (UUT) suffer from cracks, corrosion, and leakage defects, which rises the chance of major accidents. However, prevailing detection methods for UUT remain reliant on manual inspection and subjective judgment, or traditional image processing technologies, such methods may not be able to obtain accurate defect information. This study proposes a novel and effective network called UUTNet based on the constructed UUT dataset for defects detection. Considering that the UUT defects has a certain distribution correlation, the attention module is introduced to the Pyramid Scene Parsing Network to capture the relation. By adding the hybrid dilated convolution after the feature extraction layer, the receptive field is expanded to further extract global and local features. The performance of UUTNet was evaluated based on the metrics MIoU, F1-score, Accuracy, and robustness. Comparative experiments were conducted, and the results showed the UUTNet achieved the best detection performance, achieving 0.7615 MIoU, 0.9806 Accuracy and 0.8012 F1-score. The MIoU was further improved to 0.7847 by utilizing the Bayesian optimization. Three extreme inspection scenes, including uneven illumination, high brightness, and obstacle interference, were applied to validate model robustness. The proposed method offers robust technical assistance for detecting defects in the UUT and precisely assessing the distribution and extent of these defects.
使用中的城市公用事业隧道（UUT）存在裂缝、腐蚀和渗漏等缺陷，从而增加了发生重大事故的几率。然而，目前对 UUT 的检测方法仍然依赖于人工检测和主观判断，或者传统的图像处理技术，这些方法可能无法获得准确的缺陷信息。本研究基于构建的 UUT 数据集，提出了一种新颖有效的缺陷检测网络，即 UUTNet。考虑到 UUT 缺陷具有一定的分布相关性，在金字塔场景解析网络中引入了注意力模块来捕捉这种相关性。通过在特征提取层后添加混合扩张卷积，扩大感受野以进一步提取全局和局部特征。根据 MIoU、F1-score、准确性和鲁棒性等指标对 UUTNet 的性能进行了评估。对比实验结果表明，UUTNet 的检测性能最好，MIoU 达到 0.7615，准确率达到 0.9806，F1 分数达到 0.8012。通过贝叶斯优化，MIoU 进一步提高到 0.7847。为了验证模型的鲁棒性，应用了三个极端检测场景，包括光照不均、高亮度和障碍物干扰。所提出的方法为检测 UUT 中的缺陷以及精确评估这些缺陷的分布和程度提供了强大的技术帮助。
{"title":"Image-based automatic multiple-defect detection of urban utility tunnel using UUTNet","authors":"Weihao Sun, Shitong Hou, Gang Wu, Dongming Feng, Jian-hu Fan","doi":"10.1177/13694332241242975","DOIUrl":"https://doi.org/10.1177/13694332241242975","url":null,"abstract":"In-service urban utility tunnels (UUT) suffer from cracks, corrosion, and leakage defects, which rises the chance of major accidents. However, prevailing detection methods for UUT remain reliant on manual inspection and subjective judgment, or traditional image processing technologies, such methods may not be able to obtain accurate defect information. This study proposes a novel and effective network called UUTNet based on the constructed UUT dataset for defects detection. Considering that the UUT defects has a certain distribution correlation, the attention module is introduced to the Pyramid Scene Parsing Network to capture the relation. By adding the hybrid dilated convolution after the feature extraction layer, the receptive field is expanded to further extract global and local features. The performance of UUTNet was evaluated based on the metrics MIoU, F1-score, Accuracy, and robustness. Comparative experiments were conducted, and the results showed the UUTNet achieved the best detection performance, achieving 0.7615 MIoU, 0.9806 Accuracy and 0.8012 F1-score. The MIoU was further improved to 0.7847 by utilizing the Bayesian optimization. Three extreme inspection scenes, including uneven illumination, high brightness, and obstacle interference, were applied to validate model robustness. The proposed method offers robust technical assistance for detecting defects in the UUT and precisely assessing the distribution and extent of these defects.","PeriodicalId":505409,"journal":{"name":"Advances in Structural Engineering","volume":"87 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140366213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-28DOI: 10.1177/13694332241242981
Yang Huang, Shiming Chen, P. Gu
A new type composite dowel shear connector was proposed by introducing folded angles in the steel dowels. Four push-out specimens and two composite beam specimens were designed and experimentally studied. The structural behavior and failure mechanism of the composite folded dowel shear connection were investigated. The concrete failure was observed in both push-out and flexural tests, and the folded steel dowels were capable of yielding development. It is found that the bearing capacity and shear stiffness of the specimens with denser spacing dowels were higher than that of specimens with sparser dowels, but the ductility and deformation performance of the specimens with denser spacing dowels were lower than those with sparser dowels. By means of the finite element model simulation, the influence of strength and thickness of concrete slab, strength, thickness and folded angle of steel dowel on the mechanical properties of folded dowel shear connection were analysed. The folded angle could be determined as 20° because of the larger actual effective shear area and bearing capacity. Based on the bearing capacity analysis in terms of the three likely failure modes, such as steel failure, concrete shear failure and concrete pry-out, calculation formula of the shear bearing capacity of the folded dowel shear connection was put forward and verified. The calculated results by the proposed formula were in good agreement with the test results. For the composite beams, the calculated bending moments derived from the transformed section and the plasticity section methods were also in good agreement with the test values. It is suggested that the shear connection degree should be greater than 1 to enable a full composite beam.
{"title":"Experimental and numerical study on structural behavior of folded dowel shear connection","authors":"Yang Huang, Shiming Chen, P. Gu","doi":"10.1177/13694332241242981","DOIUrl":"https://doi.org/10.1177/13694332241242981","url":null,"abstract":"A new type composite dowel shear connector was proposed by introducing folded angles in the steel dowels. Four push-out specimens and two composite beam specimens were designed and experimentally studied. The structural behavior and failure mechanism of the composite folded dowel shear connection were investigated. The concrete failure was observed in both push-out and flexural tests, and the folded steel dowels were capable of yielding development. It is found that the bearing capacity and shear stiffness of the specimens with denser spacing dowels were higher than that of specimens with sparser dowels, but the ductility and deformation performance of the specimens with denser spacing dowels were lower than those with sparser dowels. By means of the finite element model simulation, the influence of strength and thickness of concrete slab, strength, thickness and folded angle of steel dowel on the mechanical properties of folded dowel shear connection were analysed. The folded angle could be determined as 20° because of the larger actual effective shear area and bearing capacity. Based on the bearing capacity analysis in terms of the three likely failure modes, such as steel failure, concrete shear failure and concrete pry-out, calculation formula of the shear bearing capacity of the folded dowel shear connection was put forward and verified. The calculated results by the proposed formula were in good agreement with the test results. For the composite beams, the calculated bending moments derived from the transformed section and the plasticity section methods were also in good agreement with the test values. It is suggested that the shear connection degree should be greater than 1 to enable a full composite beam.","PeriodicalId":505409,"journal":{"name":"Advances in Structural Engineering","volume":"44 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140368815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-10DOI: 10.1177/13694332241232049
Jiajing Li, Qiaoyun Wu, Shun Weng
Time history response derivatives with respect to the design variables are frequently used in optimization design, damage detection, structural control, etc. This paper proposes a substructuring method for efficient calculation of higher order time history response derivatives of large-scale structures. First, the global structure is disassembled into several small substructures and the substructural displacement is projected onto the range space of a few substructural master eigenvectors. Afterwards, the derivative of substructural master eigenvectors of a few substructures containing the design variables are assembled to form the reduced first, second, and higher order sensitivity equations with a size of the number of master eigenvectors. The equivalent eigenvector which relates the slave and master eigenvectors is derived to compensate for the inertial effect of discarded slave eigenvectors. Finally, the first, second, and higher order time history response derivatives of global large-scale structure are efficiently solved from the reduced sensitivity equations by using Newmark- β method. A numerical one-bay plane frame and a numerical highway bridge are applied to verify the accuracy and efficiency of proposed substructuring method.
{"title":"Efficient calculation of higher order time history response derivatives by substructuring method","authors":"Jiajing Li, Qiaoyun Wu, Shun Weng","doi":"10.1177/13694332241232049","DOIUrl":"https://doi.org/10.1177/13694332241232049","url":null,"abstract":"Time history response derivatives with respect to the design variables are frequently used in optimization design, damage detection, structural control, etc. This paper proposes a substructuring method for efficient calculation of higher order time history response derivatives of large-scale structures. First, the global structure is disassembled into several small substructures and the substructural displacement is projected onto the range space of a few substructural master eigenvectors. Afterwards, the derivative of substructural master eigenvectors of a few substructures containing the design variables are assembled to form the reduced first, second, and higher order sensitivity equations with a size of the number of master eigenvectors. The equivalent eigenvector which relates the slave and master eigenvectors is derived to compensate for the inertial effect of discarded slave eigenvectors. Finally, the first, second, and higher order time history response derivatives of global large-scale structure are efficiently solved from the reduced sensitivity equations by using Newmark- β method. A numerical one-bay plane frame and a numerical highway bridge are applied to verify the accuracy and efficiency of proposed substructuring method.","PeriodicalId":505409,"journal":{"name":"Advances in Structural Engineering","volume":"34 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139846645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：