Semantic segmentation is a core task in computer vision that allows AI models to interact and understand their surrounding environment. Similarly to how humans subconsciously segment scenes, this ability is crucial fo...Semantic segmentation is a core task in computer vision that allows AI models to interact and understand their surrounding environment. Similarly to how humans subconsciously segment scenes, this ability is crucial for scene understanding. However, a challenge many semantic learning models face is the lack of data. Existing video datasets are limited to short, low-resolution videos that are not representative of real-world examples. Thus, one of our key contributions is a customized semantic segmentation version of the Walking Tours Dataset that features hour-long, high-resolution, real-world data from tours of different cities. Additionally, we evaluate the performance of open-vocabulary, semantic model OpenSeeD on our own custom dataset and discuss future implications.展开更多
高墩大跨连续刚构桥因主墩与上部结构固结,其减震控制设计存在一定的局限性,且主梁因地震作用会存在截面开裂及预应力束应力损失等现象。惯容系统是近年发展的结构减震控制新方式,特别是将惯容器与传统调谐质量阻尼器(tuned mass damper...高墩大跨连续刚构桥因主墩与上部结构固结,其减震控制设计存在一定的局限性,且主梁因地震作用会存在截面开裂及预应力束应力损失等现象。惯容系统是近年发展的结构减震控制新方式,特别是将惯容器与传统调谐质量阻尼器(tuned mass damper,TMD)结合,形成的调谐质量惯容阻尼器(tuned mass-damper-inerter,TMDI)。文中以某高墩大跨连续刚构桥为例,考虑施工过程结合Midas Civil与OpenSees软件建立非线性地震反应分析模型,以10条近断层脉冲波为输入,研究了分布式设置(多个)TMDI对其地震反应的控制效果。研究结果表明:地震动沿纵桥向输入时,TMDI可有效避免主梁顶板、底板开裂,但主梁腹板受力略有增大;沿横桥向输入时,TMDI则会明显降低主跨腹板受力;当地震动双向水平输入时,TMDI无论对主梁顶板、底板,还是主跨腹板的应力都有很好的减轻作用。在桥墩反应方面,墩顶最大位移平均减震率为52%(纵桥向)和21%(横桥向),纵桥向最大弯矩减震率是31%,在横桥向TMDI虽然会放大约10%的墩底弯矩,但它可控制桥墩的(弹塑性)残余位移反应。展开更多
This paper proposed a RIME-VMD-BiLSTM surrogate model to rapidly and precisely predict the seismic response of a nonlinear vehicle-track-bridge(VTB)system.The surrogate model employs the RIME algorithm to optimize the...This paper proposed a RIME-VMD-BiLSTM surrogate model to rapidly and precisely predict the seismic response of a nonlinear vehicle-track-bridge(VTB)system.The surrogate model employs the RIME algorithm to optimize the variational mode decomposition(VMD)parameters(k andα)and the architecture and hyperparameter of the bidirectional long-and short-term memory network(BiLSTM).After comparing different combinations and optimization algorithms,the surrogate model was trained and used to analyze a typical 9-span 32-m high-speed railway simply supported bridge system.A series of numerical examples considering the vehicle speed,bridge damping,seismic intensity,and training strategy on the prediction effect of the surrogate model were conducted on the extended OpenSees platform.The results show that the BiLSTM model performed better than the LSTM model,whereas the prediction effects of the single-LSTM and BiLSTM models were relatively poor.With the introduction of the VMD and RIME optimization techniques,the prediction effect of the proposed RIME-VMD-BiLSTM model was excellent.The abovementioned factors had a significant influence on the seismic response of a VTB system but little impact on the prediction effect of the surrogate model.The proposed surrogate model exhibits notable transferability and robustness for predicting the VTB’s nonlinear seismic response.展开更多
This study presents a numerical simulation of large-scale shaking table tests on a superstructure supported by a pile group installed in an inclined liquefiable site,fo-cusing on nonlinear interactions between piles a...This study presents a numerical simulation of large-scale shaking table tests on a superstructure supported by a pile group installed in an inclined liquefiable site,fo-cusing on nonlinear interactions between piles and the soil.A three-dimensional finite element model of a soil-pile superstructure system is developed using OpenSeesMP.The temporal and spatial evolution of the radial soil pressure around the pile is evaluated in both liquefied and nonlique-fied sites.Results show that the soil pressure around the pile is significantly influenced by site inclination and soil lateral spreading.In liquefied sites,the soil pressure in the ex-truded zone of the upstream pile is significantly higher than that in the diffused zone.However,higher pressure occurs in the diffused zone for nonliquefied sites.Correspond-ingly,the liquefaction state significantly influences the force characteristics of the pile group system.Additionally,the group effect is more pronounced in liquefied sites.The results also indicate that the soil pressure distribution around the piles is closely related to the relative pile-soil displace-ment and reveals different on-pile force mechanisms under varying site conditions.These findings offer valuable in-sights into the seismic design of pile foundations in inclined liquefied sites.展开更多
文摘Semantic segmentation is a core task in computer vision that allows AI models to interact and understand their surrounding environment. Similarly to how humans subconsciously segment scenes, this ability is crucial for scene understanding. However, a challenge many semantic learning models face is the lack of data. Existing video datasets are limited to short, low-resolution videos that are not representative of real-world examples. Thus, one of our key contributions is a customized semantic segmentation version of the Walking Tours Dataset that features hour-long, high-resolution, real-world data from tours of different cities. Additionally, we evaluate the performance of open-vocabulary, semantic model OpenSeeD on our own custom dataset and discuss future implications.
文摘高墩大跨连续刚构桥因主墩与上部结构固结,其减震控制设计存在一定的局限性,且主梁因地震作用会存在截面开裂及预应力束应力损失等现象。惯容系统是近年发展的结构减震控制新方式,特别是将惯容器与传统调谐质量阻尼器(tuned mass damper,TMD)结合,形成的调谐质量惯容阻尼器(tuned mass-damper-inerter,TMDI)。文中以某高墩大跨连续刚构桥为例,考虑施工过程结合Midas Civil与OpenSees软件建立非线性地震反应分析模型,以10条近断层脉冲波为输入,研究了分布式设置(多个)TMDI对其地震反应的控制效果。研究结果表明:地震动沿纵桥向输入时,TMDI可有效避免主梁顶板、底板开裂,但主梁腹板受力略有增大;沿横桥向输入时,TMDI则会明显降低主跨腹板受力;当地震动双向水平输入时,TMDI无论对主梁顶板、底板,还是主跨腹板的应力都有很好的减轻作用。在桥墩反应方面,墩顶最大位移平均减震率为52%(纵桥向)和21%(横桥向),纵桥向最大弯矩减震率是31%,在横桥向TMDI虽然会放大约10%的墩底弯矩,但它可控制桥墩的(弹塑性)残余位移反应。
基金Project(52108433)supported by the National Natural Science Foundation of ChinaProject(HSR202004)supported by the Open Foundation of National Engineering Research Center of High-Speed Railway Construction Technology(CSU),China+3 种基金Projects(2024RC3170,2021RC4031)supported by the Science and Technology Innovation Program of Hunan Province,ChinaProjects(2024JJ5018,2024JJ5427)supported by the Hunan Provincial Natural Science Foundation,ChinaProject(KQ2402027)supported by the Changsha City Natural Science Foundation,ChinaProjects(2021-Special-08,2022-Special-09)supported by the Science and Technology Research and Development Program Project of China Railway Group Limited。
文摘This paper proposed a RIME-VMD-BiLSTM surrogate model to rapidly and precisely predict the seismic response of a nonlinear vehicle-track-bridge(VTB)system.The surrogate model employs the RIME algorithm to optimize the variational mode decomposition(VMD)parameters(k andα)and the architecture and hyperparameter of the bidirectional long-and short-term memory network(BiLSTM).After comparing different combinations and optimization algorithms,the surrogate model was trained and used to analyze a typical 9-span 32-m high-speed railway simply supported bridge system.A series of numerical examples considering the vehicle speed,bridge damping,seismic intensity,and training strategy on the prediction effect of the surrogate model were conducted on the extended OpenSees platform.The results show that the BiLSTM model performed better than the LSTM model,whereas the prediction effects of the single-LSTM and BiLSTM models were relatively poor.With the introduction of the VMD and RIME optimization techniques,the prediction effect of the proposed RIME-VMD-BiLSTM model was excellent.The abovementioned factors had a significant influence on the seismic response of a VTB system but little impact on the prediction effect of the surrogate model.The proposed surrogate model exhibits notable transferability and robustness for predicting the VTB’s nonlinear seismic response.
基金The National Science Fund for Distinguished Young Scholars (No. 52225807)。
文摘This study presents a numerical simulation of large-scale shaking table tests on a superstructure supported by a pile group installed in an inclined liquefiable site,fo-cusing on nonlinear interactions between piles and the soil.A three-dimensional finite element model of a soil-pile superstructure system is developed using OpenSeesMP.The temporal and spatial evolution of the radial soil pressure around the pile is evaluated in both liquefied and nonlique-fied sites.Results show that the soil pressure around the pile is significantly influenced by site inclination and soil lateral spreading.In liquefied sites,the soil pressure in the ex-truded zone of the upstream pile is significantly higher than that in the diffused zone.However,higher pressure occurs in the diffused zone for nonliquefied sites.Correspond-ingly,the liquefaction state significantly influences the force characteristics of the pile group system.Additionally,the group effect is more pronounced in liquefied sites.The results also indicate that the soil pressure distribution around the piles is closely related to the relative pile-soil displace-ment and reveals different on-pile force mechanisms under varying site conditions.These findings offer valuable in-sights into the seismic design of pile foundations in inclined liquefied sites.
