Particle Flow method is widely applied in meso mechanical research field. Codes such as PFC3D program generate calculation model with particles. Meso-scale mechanical parameters can only be obtained by varying them until the macro mechanical parameters of the numerical sample match that of the laboratory rock-soil mass sample. The corresponding parameters may be then used in a simulation of problem containing the same solid material as the sample. Based on PFC3D program, a nonlinear network model linked macro mechanical parameters and meso-scale mechanical parameters is founded by adopting BP neural network, so meso-scale mechanical parameters can be inversed rapidly and accurately by inputting macro mechanical parameters. Some studying results are drawn as follows: (1) Precision of macro mechanical parameters calculated by inversed results is generally over 90%; (2) Inversion performance of BP neural network model is best when Resolution(RES) equals 10 and the hidden layer has six neurons.
展开▼
