Flight load computations(FLC)are generally expensive and time-consuming.This paper studies deep learning(DL)-based surrogate models of FLC to provide a reliable basis for the strength design of aircraft structures.We ...Flight load computations(FLC)are generally expensive and time-consuming.This paper studies deep learning(DL)-based surrogate models of FLC to provide a reliable basis for the strength design of aircraft structures.We mainly analyze the influence of Mach number,overload,angle of attack,elevator deflection,altitude,and other factors on the loads of key monitoring components,based on which input and output variables are set.The data used to train and validate the DL surrogate models are derived using aircraft flight load simulation results based on wind tunnel test data.According to the FLC features,a deep neural network(DNN)and a random forest(RF)are proposed to establish the surrogate models.The DNN meets the FLC accuracy requirement using rich data sources in the FLC;the RF can alleviate overfitting and evaluate the importance of flight parameters.Numerical experiments show that both the DNN-and RF-based surrogate models achieve high accuracy.The input variables importance analysis demonstrates that vertical overload and elevator deflection have a significant influence on the FLC.We believe that synthetic applications of these DL-based surrogate methods show a great promise in the field of FLC.展开更多
A method for static aeroelastic trim analysis and flight loads computation of a flexible aircraft with large deformations has been presented in this paper,which considers the geometric nonlinearity of the structure an...A method for static aeroelastic trim analysis and flight loads computation of a flexible aircraft with large deformations has been presented in this paper,which considers the geometric nonlinearity of the structure and the nonplanar effects of aerodynamics.A nonplanar vortex lattice method is used to compute the nonplanar aerodynamics.The nonlinear finite element method is introduced to consider the structural geometric nonlinearity.Moreover,the surface spline method is used for structure/aerodynamics coupling.Finally,by combining the equilibrium equations of rigid motions of the deformed aircraft,the nonlinear trim problem of the flexible aircraft is solved by iterative method.For instance,the longitudinal trim analysis of a flexible aircraft with large-aspect-ratio wings is carried out by both the nonlinear method presented and the linear method of MSC Flightloads.Results obtained by these two methods are compared,and it is indicated that the results agree with each other when the deformation is small.However,because the linear method of static aeroelastic analysis does not consider the nonplanar aerodynamic effects or structural geometric nonlinearity,it is not applicable as the deformations increase.Whereas the nonlinear method presented could solve the trim problem accurately,even the deformations are large,which makes the nonlinear method suitable for rapid and efficient analysis in engineering practice.It could be used not only in the preliminary stage but also in the detail stage of aircraft design.展开更多
A study of piles is quit complex and the estimation of carrying capacity is calculated from theoretical formula and load test results. The design resistance may be calculated using conventional static pile design theo...A study of piles is quit complex and the estimation of carrying capacity is calculated from theoretical formula and load test results. The design resistance may be calculated using conventional static pile design theory. The pile founding depths should be predetermined before installation from a site geotechnical investigation. To ascertain the field performance and estimate load carrying capacities of piles, in-situ pile load tests should be conducted. In this study, field pile load test data is analyzed to estimate the ultimate load for end bearing piles. The investigated site is about 100 × 110 m located in Alexandria, Egypt. Geotechnical investigations at the site are carried out to a maximum depth of 45 m. Four borings have been done in field. The tests are conducted at the site for two skelton structure buildings to be constructed on raft foundation rested on piles executed by continuous flight auger. Four pile load tests are performed on 600 mmdiameters and 27 mlengths. Ultimate capacities of piles are determined according to different methods. It is concluded that the percentage of friction load carried by the shaft along the pile length is about 46% of total load while the percentage of load carried by the end bearing is 54% of total load. A new proposed method by the author is presented to calculate the ultimate capacity of pile from pile load test. The proposed method depends on the settlement of pile without taken into consideration the elastic deformation. An empirical formula is presented from the relationship between stress and settlement of pile due to friction and end bearing only after deducting the elastic deformation. However, the obtained results for the ultimate capacity of end bearing piles are considered to be more accurate than other methods. The proposed method appears to give bitter results that agrees well with the theoretical predictions. The proposed method is easier, quicker and more reliable.展开更多
基金This research was partially supported by the Natural Science Foundation of China under Grant 91730305Guangdong Provincial Natural Science Foundation of China under Grant 2017B030311001.
文摘Flight load computations(FLC)are generally expensive and time-consuming.This paper studies deep learning(DL)-based surrogate models of FLC to provide a reliable basis for the strength design of aircraft structures.We mainly analyze the influence of Mach number,overload,angle of attack,elevator deflection,altitude,and other factors on the loads of key monitoring components,based on which input and output variables are set.The data used to train and validate the DL surrogate models are derived using aircraft flight load simulation results based on wind tunnel test data.According to the FLC features,a deep neural network(DNN)and a random forest(RF)are proposed to establish the surrogate models.The DNN meets the FLC accuracy requirement using rich data sources in the FLC;the RF can alleviate overfitting and evaluate the importance of flight parameters.Numerical experiments show that both the DNN-and RF-based surrogate models achieve high accuracy.The input variables importance analysis demonstrates that vertical overload and elevator deflection have a significant influence on the FLC.We believe that synthetic applications of these DL-based surrogate methods show a great promise in the field of FLC.
基金supported by the National Natural Science Foundation of China (Grant Nos. 11172025,91116005)the Research Fund for the Doctoral Program of Higher Education of China (Grant No.20091102110015)
文摘A method for static aeroelastic trim analysis and flight loads computation of a flexible aircraft with large deformations has been presented in this paper,which considers the geometric nonlinearity of the structure and the nonplanar effects of aerodynamics.A nonplanar vortex lattice method is used to compute the nonplanar aerodynamics.The nonlinear finite element method is introduced to consider the structural geometric nonlinearity.Moreover,the surface spline method is used for structure/aerodynamics coupling.Finally,by combining the equilibrium equations of rigid motions of the deformed aircraft,the nonlinear trim problem of the flexible aircraft is solved by iterative method.For instance,the longitudinal trim analysis of a flexible aircraft with large-aspect-ratio wings is carried out by both the nonlinear method presented and the linear method of MSC Flightloads.Results obtained by these two methods are compared,and it is indicated that the results agree with each other when the deformation is small.However,because the linear method of static aeroelastic analysis does not consider the nonplanar aerodynamic effects or structural geometric nonlinearity,it is not applicable as the deformations increase.Whereas the nonlinear method presented could solve the trim problem accurately,even the deformations are large,which makes the nonlinear method suitable for rapid and efficient analysis in engineering practice.It could be used not only in the preliminary stage but also in the detail stage of aircraft design.
文摘A study of piles is quit complex and the estimation of carrying capacity is calculated from theoretical formula and load test results. The design resistance may be calculated using conventional static pile design theory. The pile founding depths should be predetermined before installation from a site geotechnical investigation. To ascertain the field performance and estimate load carrying capacities of piles, in-situ pile load tests should be conducted. In this study, field pile load test data is analyzed to estimate the ultimate load for end bearing piles. The investigated site is about 100 × 110 m located in Alexandria, Egypt. Geotechnical investigations at the site are carried out to a maximum depth of 45 m. Four borings have been done in field. The tests are conducted at the site for two skelton structure buildings to be constructed on raft foundation rested on piles executed by continuous flight auger. Four pile load tests are performed on 600 mmdiameters and 27 mlengths. Ultimate capacities of piles are determined according to different methods. It is concluded that the percentage of friction load carried by the shaft along the pile length is about 46% of total load while the percentage of load carried by the end bearing is 54% of total load. A new proposed method by the author is presented to calculate the ultimate capacity of pile from pile load test. The proposed method depends on the settlement of pile without taken into consideration the elastic deformation. An empirical formula is presented from the relationship between stress and settlement of pile due to friction and end bearing only after deducting the elastic deformation. However, the obtained results for the ultimate capacity of end bearing piles are considered to be more accurate than other methods. The proposed method appears to give bitter results that agrees well with the theoretical predictions. The proposed method is easier, quicker and more reliable.
