The present study aims to improve the efficiency of typical procedures used for post-processing flow field data by applying a neural-network technology.Assuming a problem of aircraft design as the workhorse,a regressi...The present study aims to improve the efficiency of typical procedures used for post-processing flow field data by applying a neural-network technology.Assuming a problem of aircraft design as the workhorse,a regression calculation model for processing the flow data of a FCN-VGG19 aircraft is elaborated based on VGGNet(Visual Geometry Group Net)and FCN(Fully Convolutional Network)techniques.As shown by the results,the model displays a strong fitting ability,and there is almost no over-fitting in training.Moreover,the model has good accuracy and convergence.For different input data and different grids,the model basically achieves convergence,showing good performances.It is shown that the proposed simulation regression model based on FCN has great potential in typical problems of computational fluid dynamics(CFD)and related data processing.展开更多
The surface deflection of asphalt pavement reflects the strength and stiffness of the entire structure, which can be used to evaluate the rutting life of asphalt pavements. However, it is influenced by various stochas...The surface deflection of asphalt pavement reflects the strength and stiffness of the entire structure, which can be used to evaluate the rutting life of asphalt pavements. However, it is influenced by various stochastic variables including traffic loads, material properties and structural thickness of each pavement course. The uncertainty of above stochastic variables is of significance for accurately predicting the rutting life of asphalt pavement. In this study, the statistical characteristics of stochastic variables of asphalt pavement were assessed based on the field data collected from asphalt pavement projects. A unique formula with a fairly good accuracy was found using multiple linear regression based on numerical simulation results to ease the calculation of pavement deflection during the reliability analysis. It is shown that the stochastic variables of asphalt pavement can be well characterized by normal distribution or logarithmic normal distribution. The regressed formula to calculate the surface deflection of pavement has a fairly good accuracy with an error of less than 6.0% compared to the numerical method. The proposed surface deflection-based reliability analysis can be used easily to evaluate the influence of input parameters on the rutting life and to guide the structure design of asphalt pavement with required reliability.展开更多
文摘The present study aims to improve the efficiency of typical procedures used for post-processing flow field data by applying a neural-network technology.Assuming a problem of aircraft design as the workhorse,a regression calculation model for processing the flow data of a FCN-VGG19 aircraft is elaborated based on VGGNet(Visual Geometry Group Net)and FCN(Fully Convolutional Network)techniques.As shown by the results,the model displays a strong fitting ability,and there is almost no over-fitting in training.Moreover,the model has good accuracy and convergence.For different input data and different grids,the model basically achieves convergence,showing good performances.It is shown that the proposed simulation regression model based on FCN has great potential in typical problems of computational fluid dynamics(CFD)and related data processing.
基金supported by the National Natural Science Foundation of China (Grant Nos. 51578316 and 51778331)。
文摘The surface deflection of asphalt pavement reflects the strength and stiffness of the entire structure, which can be used to evaluate the rutting life of asphalt pavements. However, it is influenced by various stochastic variables including traffic loads, material properties and structural thickness of each pavement course. The uncertainty of above stochastic variables is of significance for accurately predicting the rutting life of asphalt pavement. In this study, the statistical characteristics of stochastic variables of asphalt pavement were assessed based on the field data collected from asphalt pavement projects. A unique formula with a fairly good accuracy was found using multiple linear regression based on numerical simulation results to ease the calculation of pavement deflection during the reliability analysis. It is shown that the stochastic variables of asphalt pavement can be well characterized by normal distribution or logarithmic normal distribution. The regressed formula to calculate the surface deflection of pavement has a fairly good accuracy with an error of less than 6.0% compared to the numerical method. The proposed surface deflection-based reliability analysis can be used easily to evaluate the influence of input parameters on the rutting life and to guide the structure design of asphalt pavement with required reliability.