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
Reducing the peak actuating force(PAF)and parasitic displacement is of high significance for improving the performance of compliant parallel mechanisms(CPMs).In this study,a 2-DOF 4-4R compliant parallel pointing mech...Reducing the peak actuating force(PAF)and parasitic displacement is of high significance for improving the performance of compliant parallel mechanisms(CPMs).In this study,a 2-DOF 4-4R compliant parallel pointing mechanism(4-4R CPPM)was used as the object,and the actuating force of the mechanism was optimized through redundant actuation.This was aimed at minimizing the PAF and parasitic displacement.First,a kinetostatic model of the redundantly actuated 4-4R CPPM was established to reveal the relationship between the input forces/displacements and the output displacements of the mobile platform.Subsequently,based on the established kinetostatic model,methods for optimizing the actuating force distribution with the aim of minimizing the PAF and parasitic displacement were introduced successively.Second,a simulated example of a mobile platform’s spatial pointing trajectory validated the accuracy of the kinetostatic model.The results show a less than 0.9%relative error between the analytical and finite element(FE)results,and the high consistency indicates the accuracy of the kinetostatic model.Then,the effectiveness of the method in minimizing the PAF and parasitic displacement was validated using two simulated examples.The results indicate that compared with the non-redundant actuation case,the PAF of the mechanism could be reduced by up to 50%,and the parasitic displacement was reduced by approximately three-four orders of magnitude by means of redundant actuation combined with the optimal distribution of the actuating force.As expected,with the reduction in parasitic displacement,the FE-results of the output angular displacements(θ_(x) andθ_(z))of the mobile platform were closer to the target oscillation trajectory.This further verified that the reduction in parasitic displacement is indeed effective in improving the motion accuracy of the mechanism.The advantage of this proposed method is that it reduces the PAF and parasitic displacement from the perspective of the actuating force control strategy,without the requirement of structural changes to the original mechanism.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 Key Project of Hubei Provincial Department of Education Research Program(Grant No.D20211401).
文摘Reducing the peak actuating force(PAF)and parasitic displacement is of high significance for improving the performance of compliant parallel mechanisms(CPMs).In this study,a 2-DOF 4-4R compliant parallel pointing mechanism(4-4R CPPM)was used as the object,and the actuating force of the mechanism was optimized through redundant actuation.This was aimed at minimizing the PAF and parasitic displacement.First,a kinetostatic model of the redundantly actuated 4-4R CPPM was established to reveal the relationship between the input forces/displacements and the output displacements of the mobile platform.Subsequently,based on the established kinetostatic model,methods for optimizing the actuating force distribution with the aim of minimizing the PAF and parasitic displacement were introduced successively.Second,a simulated example of a mobile platform’s spatial pointing trajectory validated the accuracy of the kinetostatic model.The results show a less than 0.9%relative error between the analytical and finite element(FE)results,and the high consistency indicates the accuracy of the kinetostatic model.Then,the effectiveness of the method in minimizing the PAF and parasitic displacement was validated using two simulated examples.The results indicate that compared with the non-redundant actuation case,the PAF of the mechanism could be reduced by up to 50%,and the parasitic displacement was reduced by approximately three-four orders of magnitude by means of redundant actuation combined with the optimal distribution of the actuating force.As expected,with the reduction in parasitic displacement,the FE-results of the output angular displacements(θ_(x) andθ_(z))of the mobile platform were closer to the target oscillation trajectory.This further verified that the reduction in parasitic displacement is indeed effective in improving the motion accuracy of the mechanism.The advantage of this proposed method is that it reduces the PAF and parasitic displacement from the perspective of the actuating force control strategy,without the requirement of structural changes to the original mechanism.
