Considering the variation of cohesion along the depth,the upper bound solution of active earth pressure for a rough inclined wall with sloped backfill is formulated based on a log-spiral failure mechanism.For a more a...Considering the variation of cohesion along the depth,the upper bound solution of active earth pressure for a rough inclined wall with sloped backfill is formulated based on a log-spiral failure mechanism.For a more accurate prediction,the influence of intermediate principal stress is taken into consideration using the unified strength theory.Converting the search for the active pressure to an optimization problem,the most critical failure surface can be located by a natural selection-based gravitational search algorithm(GSA).The proposed method is validated compared with existing methods for noncohesive and cohesive cases and proved to be more accordance with the limit equilibrium solution.The influences of the variation of soil cohesion and intermediate principal stress on active earth pressure coefficient are then fully studied.It can be concluded that both the variations of soil cohesion and intermediate principal stress have a significant influence on the active earth pressure coefficient.展开更多
Nonlinear resistivity inversion requires efficient artificial neural network(ANN)model for better inversion results.An evolutionary BP neural network(BPNN)approach based on differential evolution(DE)algorithm was pres...Nonlinear resistivity inversion requires efficient artificial neural network(ANN)model for better inversion results.An evolutionary BP neural network(BPNN)approach based on differential evolution(DE)algorithm was presented,which was able to improve global search ability for resistivity tomography 2-D nonlinear inversion.In the proposed method,Tent equation was applied to obtain automatic parameter settings in DE and the restricted parameter Fcrit was used to enhance the ability of converging to global optimum.An implementation of proposed DE-BPNN was given,the network had one hidden layer with 52 nodes and it was trained on 36 datasets and tested on another 4 synthetic datasets.Two abnormity models were used to verify the feasibility and effectiveness of the proposed method,the results show that the proposed DE-BP algorithm has better performance than BP,conventional DE-BP and other chaotic DE-BP methods in stability and accuracy,and higher imaging quality than least square inversion.展开更多
基金Project(2016YFC0800200)supported by the National Key Research Plan of China。
文摘Considering the variation of cohesion along the depth,the upper bound solution of active earth pressure for a rough inclined wall with sloped backfill is formulated based on a log-spiral failure mechanism.For a more accurate prediction,the influence of intermediate principal stress is taken into consideration using the unified strength theory.Converting the search for the active pressure to an optimization problem,the most critical failure surface can be located by a natural selection-based gravitational search algorithm(GSA).The proposed method is validated compared with existing methods for noncohesive and cohesive cases and proved to be more accordance with the limit equilibrium solution.The influences of the variation of soil cohesion and intermediate principal stress on active earth pressure coefficient are then fully studied.It can be concluded that both the variations of soil cohesion and intermediate principal stress have a significant influence on the active earth pressure coefficient.
基金Project(20120162110015)supported by the Research Fund for the Doctoral Program of Higher Education,ChinaProject(41004053)supported by the National Natural Science Foundation of ChinaProject(12c0241)supported by Scientific Research Fund of Hunan Provincial Education Department,China
文摘Nonlinear resistivity inversion requires efficient artificial neural network(ANN)model for better inversion results.An evolutionary BP neural network(BPNN)approach based on differential evolution(DE)algorithm was presented,which was able to improve global search ability for resistivity tomography 2-D nonlinear inversion.In the proposed method,Tent equation was applied to obtain automatic parameter settings in DE and the restricted parameter Fcrit was used to enhance the ability of converging to global optimum.An implementation of proposed DE-BPNN was given,the network had one hidden layer with 52 nodes and it was trained on 36 datasets and tested on another 4 synthetic datasets.Two abnormity models were used to verify the feasibility and effectiveness of the proposed method,the results show that the proposed DE-BP algorithm has better performance than BP,conventional DE-BP and other chaotic DE-BP methods in stability and accuracy,and higher imaging quality than least square inversion.
