To improve the accuracy of thermal response estimation and overcome the limitations of the linear regression model and Artificial Neural Network(ANN)model,this study introduces a deep learning estimation method specif...To improve the accuracy of thermal response estimation and overcome the limitations of the linear regression model and Artificial Neural Network(ANN)model,this study introduces a deep learning estimation method specifically based on the Long Short-Term Memory(LSTM)network,to predict temperature-induced girder end displacements of the Dasha Waterway Bridge,a suspension bridge in China.First,to enhance data quality and select target sensors,preprocessing based on the sigma rule and nearest neighbor interpolation is applied to the raw data.Furthermore,to eliminate the high-frequency components from the displacement signal,the wavelet transform is conducted.Subsequently,the linear regression model and ANN model are established,whose results do not meet the requirements and fail to address the time lag effect between temperature and displacements.The study proceeds to develop the LSTM network model and determine the optimal parameters through hyperparameter sensitivity analysis.Finally,the results of the LSTM network model are discussed by a comparative analysis against the linear regression model and ANN model,which indicates a higher accuracy in predicting temperatureinduced girder end displacements and the ability to mitigate the time-lag effect.To be more specific,in comparison between the linear regression model and LSTM network,the mean square error decreases from 6.5937 to 1.6808 and R^(2) increases from 0.683 to 0.930,which corresponds to a 74.51%decrease in MSE and a 36.14%improvement in R^(2).Compared to ANN,with an MSE of 4.6371 and an R^(2) of 0.807,LSTM shows a decrease in MSE of 63.75%and an increase in R^(2) of 13.23%,demonstrating a significant enhancement in predictive performance.展开更多
This study examines the temperature field distribution characteristics and temperature effects during the prefabrication of composite box girders with corrugated steel webs(CBGCSWs),aiming to provide practical recomme...This study examines the temperature field distribution characteristics and temperature effects during the prefabrication of composite box girders with corrugated steel webs(CBGCSWs),aiming to provide practical recommendations for controlling temperature-induced cracking and technical guidance for concrete mix proportions and placement processes.Based on field measurement data,a three-dimensional finite element model was developed to simulate the temperature effects at critical locations during the prefabrication phase.By varying the concrete mix proportions,initial casting temperature,and ambient temperature,the study elucidates the variation patterns of the temperature field during precast placement.The results show that the temperature rise caused by hydration heat increases with higher cement and fly ash content,whereas reducing cement and using minimal fly ash effectively lower the hydration temperature.However,the influence of fly ash on prestress losses should be carefully evaluated during the design phase.Higher initial casting temperatures accelerate hydration rates,leading to a rapid temperature rise.Significant differences between the initial casting and ambient temperatures result in larger residual temperature stresses.Based on concrete mix proportions,curing conditions,and ambient temperatures,three recommended casting temperature ranges were identified:5℃–10℃,10℃–25℃,and 25℃–30℃.Variations in the average ambient temperature affect the peak temperature of the hydration reaction and indirectly influence the final temperature distribution of the concrete structure.Optimizing the demolding time and applying geotextiles and water curing effectively reduces the peak temperature,maximum internal-to-surface temperature gradients,and surface tensile stresses,thereby mitigating the risk of temperature-induced cracking.展开更多
A ground girder is laid on the preprocessed subgrade by gravity compaction and integrally uniformly supported by subgrade in maglev transit.The settlement of the maglev subgrade inevitably affects the vibration state ...A ground girder is laid on the preprocessed subgrade by gravity compaction and integrally uniformly supported by subgrade in maglev transit.The settlement of the maglev subgrade inevitably affects the vibration state of the medium and low speed maglev coupled system by the additional deformation of the maglev track.This study investigated the dynamic properties of the coupled vibration system affected by the subgrade settlement.First,a theoretical coupled vibration model of a maglev train-track-ground girder system with uneven subgrade settlement was proposed and verified.Then,the effect mechanism of the coupled system caused by the uneven subgrade settlement was explored.Finally,settlement types and subgrade support voiding were examined.The analysis showed that the uneven subgrade settlement considerably increased the dynamic responses of the levitation control system and maglev vehicle while having a minor influence on those of the track-ground girder.The influence of a single ground girder settling was the strongest,and adjacent sides’settling of two ground girders was the weakest for the vibration of a maglev train.An extremely large uneven settlement exceeding 6 mm led to active levitation control system instability.The subgrade support voiding enlarged the vehicle-induced vibration of the track ground girder.展开更多
Near-field underwater explosions can cause substantial damage to offshore ship structures,presenting considerable risks to their integrity.This study focused on rapidly predicting girder structure deformation in ship ...Near-field underwater explosions can cause substantial damage to offshore ship structures,presenting considerable risks to their integrity.This study focused on rapidly predicting girder structure deformation in ship hulls subjected to near-field explosions from small equivalent-weight spherical charges underwater.The Runge-Kutta discontinuous Galerkin method(RKDG)was employed to calculate the explosive load generated by the spherical charge.This load was then applied to the nonlinear finite element solver software,ABAQUS,to determine the maximum deformation of the ship hull girder structure under the impulse load.By comparing the results with experimental data,the accuracy of the proposed model was validated,confirming that the RKDG finite element coupling calculation effectively simulates the response characteristics of spherical charges in near-field explosion scenarios.Subsequently,two machine learning algorithms driven by data,namely extreme gradient boosting(XGBoost)and random forest(RF),were employed to dynamically predict the maximum girder structure deformation in ship hulls.The analysis demonstrated that both models successfully predicted the maximum deformation.The root mean square error for the XGBoost model(27.67)was lower than that of the RF model(50.31).The XGBoost model also fitted 96%of the training data,compared to 94%for the RF model.Moreover,the relative error of the XGBoost model(6.25%)was lower than that of the RF model(10.38%).Overall,XGBoost is highly suitable for predicting girder structure deformation in ship hulls subjected to underwater explosions.展开更多
Streamlined box girders serve as a prevalent choice for the primary structural elements in large-span suspension bridge designs.With the increase in traffic demands,the design of such girders is evolving towards wider...Streamlined box girders serve as a prevalent choice for the primary structural elements in large-span suspension bridge designs.With the increase in traffic demands,the design of such girders is evolving towards wider bridge decks and larger aspect ratios(B/D).To obtain more effective and aerodynamic design shapes for streamlined box girders,it is essential to investigate the impact of B/D on their aerodynamic performance.Accordingly,in this study we investigate the buffeting responses of large-span suspension bridges using girders of varying aspect ratios(B/D of 7.5,9.3,and 12.7).First,the aerodynamic coefficients of these girders are estimated using computational fluid dynamics(CFD)simulations.Subsequently,spatial finite element(FE)models of three long-span suspension bridges with different girders(B/D of 7.5,9.3,and 12.7)are established in Ansys software,and the dynamic characteristics of these bridges are obtained.Then,the time-domain buffeting analysis is performed by simulating the fluctuating wind fields acting on the bridge through the spectral representation method.Ultimately,the buffeting responses are computed using Ansys software,and the impact of B/D on these responses is assessed.The results reveal that the root mean square(RMS)values of the main girder’s buffeting displacement are highest at the midspan position and are lowest at the ends of the bridge.A decrease in B/D of the main girder leads to a more severe buffeting response because both the range and the effective value of the displacement increase with the decreasing B/D.Comparing the buffeting displacements in three directions,B/D plays a significant role in the vertical buffeting displacement,moderately impacts the torsional displacement,and has the least effect on the lateral displacement.The findings of this study may help wind resistance analysis and design optimization for bridges.展开更多
To investigate the influence of the shear lag effect on the bending shear stress of single-box multicell box gird-ers(MCBG),the shear lag warping additional deflection is selected as the generalized displacement.The g...To investigate the influence of the shear lag effect on the bending shear stress of single-box multicell box gird-ers(MCBG),the shear lag warping additional deflection is selected as the generalized displacement.The governing dif-ferential equations and boundary conditions for the shear lag of the MCBG are derived using the energy variational method.Based on the shear lag warping deformation state of the MCBG and by employing the microelement equilib-rium differential equation and the coordination conditions for shear lag warping deformation,the calculation method for the bending-warping shear stress of the MCBG is de-rived,and the influence of the width-to-span and height-to span ratios on bending-warping shear stress is analyzed.Ex-ample analysis shows that the bending-warping shear stress of the MCBG calculated by the proposed calculation method coincides with the finite element solution,and the warping shear stress satisfies the self-balancing condition of shear warping,thus verifying the accuracy of the proposed method.The warping shear stress exhibits an antisymmetric distribution about the vertical axis of symmetry and has a weakening effect on the shear stress of the elementary beam(EB).The larger the width-to-span ratio is,the larger the proportion of the warping shear stress of the EB.The larger the height-to-span ratio is,the smaller the proportion of the warping shear stress and the more significant the influence of the width-to-span ratio.The more the number of cells is,the smaller the influence of the warping shear stress on the total bending shear stress.The influence of the shear lag ef-fect can be ignored in the calculation of the bending shear stress of three or more cells in the MCBG.展开更多
基金The National Key Research and Development Program of China grant No.2022YFB3706704 received by Yuan Renthe National Natural and Science Foundation of China grant No.52308150 received by Xiang Xu.
文摘To improve the accuracy of thermal response estimation and overcome the limitations of the linear regression model and Artificial Neural Network(ANN)model,this study introduces a deep learning estimation method specifically based on the Long Short-Term Memory(LSTM)network,to predict temperature-induced girder end displacements of the Dasha Waterway Bridge,a suspension bridge in China.First,to enhance data quality and select target sensors,preprocessing based on the sigma rule and nearest neighbor interpolation is applied to the raw data.Furthermore,to eliminate the high-frequency components from the displacement signal,the wavelet transform is conducted.Subsequently,the linear regression model and ANN model are established,whose results do not meet the requirements and fail to address the time lag effect between temperature and displacements.The study proceeds to develop the LSTM network model and determine the optimal parameters through hyperparameter sensitivity analysis.Finally,the results of the LSTM network model are discussed by a comparative analysis against the linear regression model and ANN model,which indicates a higher accuracy in predicting temperatureinduced girder end displacements and the ability to mitigate the time-lag effect.To be more specific,in comparison between the linear regression model and LSTM network,the mean square error decreases from 6.5937 to 1.6808 and R^(2) increases from 0.683 to 0.930,which corresponds to a 74.51%decrease in MSE and a 36.14%improvement in R^(2).Compared to ANN,with an MSE of 4.6371 and an R^(2) of 0.807,LSTM shows a decrease in MSE of 63.75%and an increase in R^(2) of 13.23%,demonstrating a significant enhancement in predictive performance.
基金supported by the National Natural Science Foundation of China(U22A20598,52279113)Key Research and Development Special Program of Henan Province(241111322500)Support Plan for University Science and Technology Innovation Team of Henan Province(24IRTSTHN009).
文摘This study examines the temperature field distribution characteristics and temperature effects during the prefabrication of composite box girders with corrugated steel webs(CBGCSWs),aiming to provide practical recommendations for controlling temperature-induced cracking and technical guidance for concrete mix proportions and placement processes.Based on field measurement data,a three-dimensional finite element model was developed to simulate the temperature effects at critical locations during the prefabrication phase.By varying the concrete mix proportions,initial casting temperature,and ambient temperature,the study elucidates the variation patterns of the temperature field during precast placement.The results show that the temperature rise caused by hydration heat increases with higher cement and fly ash content,whereas reducing cement and using minimal fly ash effectively lower the hydration temperature.However,the influence of fly ash on prestress losses should be carefully evaluated during the design phase.Higher initial casting temperatures accelerate hydration rates,leading to a rapid temperature rise.Significant differences between the initial casting and ambient temperatures result in larger residual temperature stresses.Based on concrete mix proportions,curing conditions,and ambient temperatures,three recommended casting temperature ranges were identified:5℃–10℃,10℃–25℃,and 25℃–30℃.Variations in the average ambient temperature affect the peak temperature of the hydration reaction and indirectly influence the final temperature distribution of the concrete structure.Optimizing the demolding time and applying geotextiles and water curing effectively reduces the peak temperature,maximum internal-to-surface temperature gradients,and surface tensile stresses,thereby mitigating the risk of temperature-induced cracking.
基金National Natural Science Foundation of China under Grant Nos.52478467and 52108417Guangdong Basic and Applied Basic Research Foundation under Grant No.2024A1515012569the Natural Science Basic Research Program of Shaanxi under Grant No.2021JQ-101。
文摘A ground girder is laid on the preprocessed subgrade by gravity compaction and integrally uniformly supported by subgrade in maglev transit.The settlement of the maglev subgrade inevitably affects the vibration state of the medium and low speed maglev coupled system by the additional deformation of the maglev track.This study investigated the dynamic properties of the coupled vibration system affected by the subgrade settlement.First,a theoretical coupled vibration model of a maglev train-track-ground girder system with uneven subgrade settlement was proposed and verified.Then,the effect mechanism of the coupled system caused by the uneven subgrade settlement was explored.Finally,settlement types and subgrade support voiding were examined.The analysis showed that the uneven subgrade settlement considerably increased the dynamic responses of the levitation control system and maglev vehicle while having a minor influence on those of the track-ground girder.The influence of a single ground girder settling was the strongest,and adjacent sides’settling of two ground girders was the weakest for the vibration of a maglev train.An extremely large uneven settlement exceeding 6 mm led to active levitation control system instability.The subgrade support voiding enlarged the vehicle-induced vibration of the track ground girder.
基金Supported by the Heilongjiang Provincial Excellent Youth Fund under Grant No.YQ2021E009the Heilongjiang Provincial Key R&D Program under Grant No.GZ20210210the National Major Program under Grant No.J2019-I-0017-0016.
文摘Near-field underwater explosions can cause substantial damage to offshore ship structures,presenting considerable risks to their integrity.This study focused on rapidly predicting girder structure deformation in ship hulls subjected to near-field explosions from small equivalent-weight spherical charges underwater.The Runge-Kutta discontinuous Galerkin method(RKDG)was employed to calculate the explosive load generated by the spherical charge.This load was then applied to the nonlinear finite element solver software,ABAQUS,to determine the maximum deformation of the ship hull girder structure under the impulse load.By comparing the results with experimental data,the accuracy of the proposed model was validated,confirming that the RKDG finite element coupling calculation effectively simulates the response characteristics of spherical charges in near-field explosion scenarios.Subsequently,two machine learning algorithms driven by data,namely extreme gradient boosting(XGBoost)and random forest(RF),were employed to dynamically predict the maximum girder structure deformation in ship hulls.The analysis demonstrated that both models successfully predicted the maximum deformation.The root mean square error for the XGBoost model(27.67)was lower than that of the RF model(50.31).The XGBoost model also fitted 96%of the training data,compared to 94%for the RF model.Moreover,the relative error of the XGBoost model(6.25%)was lower than that of the RF model(10.38%).Overall,XGBoost is highly suitable for predicting girder structure deformation in ship hulls subjected to underwater explosions.
基金funded by the National Natural Science Foundation of China(Grant No.52108435)the Science and Technology Research Program of Chongqing Municipal Education Commission(Grant No.KJQN202404320)+1 种基金Chongqing Jiaotong University Postgraduate Research and Innovation Project(2024S0013)Chongqing Jiaotong University Undergraduate Innovation and Entrepreneurship Project(S202410618019).
文摘Streamlined box girders serve as a prevalent choice for the primary structural elements in large-span suspension bridge designs.With the increase in traffic demands,the design of such girders is evolving towards wider bridge decks and larger aspect ratios(B/D).To obtain more effective and aerodynamic design shapes for streamlined box girders,it is essential to investigate the impact of B/D on their aerodynamic performance.Accordingly,in this study we investigate the buffeting responses of large-span suspension bridges using girders of varying aspect ratios(B/D of 7.5,9.3,and 12.7).First,the aerodynamic coefficients of these girders are estimated using computational fluid dynamics(CFD)simulations.Subsequently,spatial finite element(FE)models of three long-span suspension bridges with different girders(B/D of 7.5,9.3,and 12.7)are established in Ansys software,and the dynamic characteristics of these bridges are obtained.Then,the time-domain buffeting analysis is performed by simulating the fluctuating wind fields acting on the bridge through the spectral representation method.Ultimately,the buffeting responses are computed using Ansys software,and the impact of B/D on these responses is assessed.The results reveal that the root mean square(RMS)values of the main girder’s buffeting displacement are highest at the midspan position and are lowest at the ends of the bridge.A decrease in B/D of the main girder leads to a more severe buffeting response because both the range and the effective value of the displacement increase with the decreasing B/D.Comparing the buffeting displacements in three directions,B/D plays a significant role in the vertical buffeting displacement,moderately impacts the torsional displacement,and has the least effect on the lateral displacement.The findings of this study may help wind resistance analysis and design optimization for bridges.
基金The National Natural Science Foundation of China (No. 52368020)Gansu Provincial Universities Young Doctor Support Project (No. 2024QB-047)Gansu Province postdoctoral Fund (No. 386824)。
文摘To investigate the influence of the shear lag effect on the bending shear stress of single-box multicell box gird-ers(MCBG),the shear lag warping additional deflection is selected as the generalized displacement.The governing dif-ferential equations and boundary conditions for the shear lag of the MCBG are derived using the energy variational method.Based on the shear lag warping deformation state of the MCBG and by employing the microelement equilib-rium differential equation and the coordination conditions for shear lag warping deformation,the calculation method for the bending-warping shear stress of the MCBG is de-rived,and the influence of the width-to-span and height-to span ratios on bending-warping shear stress is analyzed.Ex-ample analysis shows that the bending-warping shear stress of the MCBG calculated by the proposed calculation method coincides with the finite element solution,and the warping shear stress satisfies the self-balancing condition of shear warping,thus verifying the accuracy of the proposed method.The warping shear stress exhibits an antisymmetric distribution about the vertical axis of symmetry and has a weakening effect on the shear stress of the elementary beam(EB).The larger the width-to-span ratio is,the larger the proportion of the warping shear stress of the EB.The larger the height-to-span ratio is,the smaller the proportion of the warping shear stress and the more significant the influence of the width-to-span ratio.The more the number of cells is,the smaller the influence of the warping shear stress on the total bending shear stress.The influence of the shear lag ef-fect can be ignored in the calculation of the bending shear stress of three or more cells in the MCBG.
