Local scour threatens the safety of marine structures,necessitating the precise prediction of scour evo-lution around these structures.A visually oriented deep learning model,called Disentangled Physics-constrained Pr...Local scour threatens the safety of marine structures,necessitating the precise prediction of scour evo-lution around these structures.A visually oriented deep learning model,called Disentangled Physics-constrained Prediction(DPP),was proposed in this study to predict scour evolution at monopiles reliably.It integrates scouring physics with advanced video prediction techniques through a two-branch architec-ture.The Physics-constrained Recurrent Module(PRModule)branch leverages Recurrent Neural Networks(RNNs)for temporal differentiation,ensuring accurate prediction of scouring-related physical information.Meanwhile,the Convolutional Long-Short-Term Memory(ConvLSTM)branch captures spatial and tempo-ral dynamics in scouring videos,focusing on the prediction of residual features.DPP outperformed three baseline models in predicting the scour evolution at monopiles.Across three scouring scenarios,DPP achieved a 14.2%decrease in Root Mean Squared Error,a 14.7%reduction in Mean Absolute Error,and an 8.1%increase in Structural Similarity on average,compared to the best-performing baseline model.The predicted scouring frames are found to agree well with the true frames,demonstrating DPP’s potential as a valuable tool to protect marine infrastructures.展开更多
Local scour at a pile or pier in current or wave environments threats the safety of the upper structure all over the world.The application of a net-like matt as a scour protection cover at the pile or pier was propose...Local scour at a pile or pier in current or wave environments threats the safety of the upper structure all over the world.The application of a net-like matt as a scour protection cover at the pile or pier was proposed.The matt weakens and diffuses the flow in the local scour pit and thus reduces local scour while enhances sediment deposition.Numerical simulations were carried out to investigate the flow at the pile covered by the matt.The simulation results were used to optimize the thickness dt(2.6 d_(95)∼17.9 d_(95))and opening size dn(7.7 d_(95)∼28.2 d_(95))of the matt.It was found that the matt significantly reduced the local velocity and dissipated the vortex at the pile,substantially reduced the extent of local scour.The smaller the opening size of the matt,the more effective was the flow diffusion at the bed,and smaller bed shear stress was observed at the pile.For the flow conditions considered in this study,a matt with a relative thickness of T=7.7 and relative opening size of S=7.7 could be effective in scour protection.展开更多
基金supported by the National Natural Science Foundation of China(Grant No.52171268)Power China Zhongnan Engineering Corporation Limited(Grant No.100-2-01-2023-2483).
文摘Local scour threatens the safety of marine structures,necessitating the precise prediction of scour evo-lution around these structures.A visually oriented deep learning model,called Disentangled Physics-constrained Prediction(DPP),was proposed in this study to predict scour evolution at monopiles reliably.It integrates scouring physics with advanced video prediction techniques through a two-branch architec-ture.The Physics-constrained Recurrent Module(PRModule)branch leverages Recurrent Neural Networks(RNNs)for temporal differentiation,ensuring accurate prediction of scouring-related physical information.Meanwhile,the Convolutional Long-Short-Term Memory(ConvLSTM)branch captures spatial and tempo-ral dynamics in scouring videos,focusing on the prediction of residual features.DPP outperformed three baseline models in predicting the scour evolution at monopiles.Across three scouring scenarios,DPP achieved a 14.2%decrease in Root Mean Squared Error,a 14.7%reduction in Mean Absolute Error,and an 8.1%increase in Structural Similarity on average,compared to the best-performing baseline model.The predicted scouring frames are found to agree well with the true frames,demonstrating DPP’s potential as a valuable tool to protect marine infrastructures.
基金supported by National Natural Science Foundation of China(No.52171268)CCCC Road&Bridge Special Engineering Co.,Ltd.
文摘Local scour at a pile or pier in current or wave environments threats the safety of the upper structure all over the world.The application of a net-like matt as a scour protection cover at the pile or pier was proposed.The matt weakens and diffuses the flow in the local scour pit and thus reduces local scour while enhances sediment deposition.Numerical simulations were carried out to investigate the flow at the pile covered by the matt.The simulation results were used to optimize the thickness dt(2.6 d_(95)∼17.9 d_(95))and opening size dn(7.7 d_(95)∼28.2 d_(95))of the matt.It was found that the matt significantly reduced the local velocity and dissipated the vortex at the pile,substantially reduced the extent of local scour.The smaller the opening size of the matt,the more effective was the flow diffusion at the bed,and smaller bed shear stress was observed at the pile.For the flow conditions considered in this study,a matt with a relative thickness of T=7.7 and relative opening size of S=7.7 could be effective in scour protection.
