To improve the accuracy and anti-noise ability of the structural damage identification method,a bridge damage identification method is proposed based on a deep belief network(DBN).The output vector is used to establis...To improve the accuracy and anti-noise ability of the structural damage identification method,a bridge damage identification method is proposed based on a deep belief network(DBN).The output vector is used to establish the nonlinear mapping relationship between the mode shape and structural damage.The hidden layer of the DBN is trained through a layer-by-layer pre-training.Finally,the backpropagation algorithm is used to fine-tune the entire network.The method is validated using a numerical model of a steel truss bridge.The results show that under the influence of noise and modeling uncertainty,the damage identification method based on the DBN can identify the accurate damage location and degree identification compared with the traditional damage identification method based on an artificial neural network.展开更多
To investigate long-term CO2 behavior in geological formations and quantification of possible CO2 leaks, it is crucial to inves- tigate the potential mobility of CO2 dissolved in brines over a wide range of spatial an...To investigate long-term CO2 behavior in geological formations and quantification of possible CO2 leaks, it is crucial to inves- tigate the potential mobility of CO2 dissolved in brines over a wide range of spatial and temporal scales and density distribu- tions in geological media. In this work, the mass transfer of aqueous CO2 in brines has been investigated by means of a chemi- cal potential gradient model based on non-equilibrium thermodynamics in which the statistical associating fluid theory equa- tion of state was used to calculate the fugacity coefficient of CO2 in brine. The investigation shows that the interracial concen- tration of aqueous CO2 and the corresponding density both increase with increasing pressure and decreasing temperature; the effective diffusion coefficients decrease initially and then increase with increasing pressure; and the density of the CO2-disolved brines increases with decreasing CO2 pressure in the CO2 dissolution process. The aqueous CO2 concentration profiles obtained by the chemical potential gradient model are considerably different from those obtained by the concentration gradient model, which shows the importance of considering non-ideality, especially when the pressure is high.展开更多
基金The National Natural Science Foundation of China(No.51378104)。
文摘To improve the accuracy and anti-noise ability of the structural damage identification method,a bridge damage identification method is proposed based on a deep belief network(DBN).The output vector is used to establish the nonlinear mapping relationship between the mode shape and structural damage.The hidden layer of the DBN is trained through a layer-by-layer pre-training.Finally,the backpropagation algorithm is used to fine-tune the entire network.The method is validated using a numerical model of a steel truss bridge.The results show that under the influence of noise and modeling uncertainty,the damage identification method based on the DBN can identify the accurate damage location and degree identification compared with the traditional damage identification method based on an artificial neural network.
基金Lule University of Technology for the financial support the financial support from the Swedish Research Council+2 种基金the National Basic Research Program of China (2009CB226103,2009CB623400)the National Natural Science Foundation of China(50808039)the Natural Science Foundation of Jiangsu Province,China (BK2009138)
文摘To investigate long-term CO2 behavior in geological formations and quantification of possible CO2 leaks, it is crucial to inves- tigate the potential mobility of CO2 dissolved in brines over a wide range of spatial and temporal scales and density distribu- tions in geological media. In this work, the mass transfer of aqueous CO2 in brines has been investigated by means of a chemi- cal potential gradient model based on non-equilibrium thermodynamics in which the statistical associating fluid theory equa- tion of state was used to calculate the fugacity coefficient of CO2 in brine. The investigation shows that the interracial concen- tration of aqueous CO2 and the corresponding density both increase with increasing pressure and decreasing temperature; the effective diffusion coefficients decrease initially and then increase with increasing pressure; and the density of the CO2-disolved brines increases with decreasing CO2 pressure in the CO2 dissolution process. The aqueous CO2 concentration profiles obtained by the chemical potential gradient model are considerably different from those obtained by the concentration gradient model, which shows the importance of considering non-ideality, especially when the pressure is high.
