ABSTRACT
BP neural network has strong nonlinear dynamic processing capability, enabling highly nonlinear mapping, with a strong learning, computing, storage and fault tolerance, can be used for particle flow analysis to determine the parameters of micromechanics. But there are some deficiencies, mainly in (Wang et al. 2013): (1) training time is longer; (2) training of instability (Gao et al. 2002);
1 INTRODUCTION
Rock areas of research and forecasting disasters depend on the kinematic behavior of the rock, usually by conventional macro analysis method for the study of rock as a whole, on the microscopic changes in the components of the rock particles, and the composition of cracks, etc. few studies. Particle flow method of non-continuous media theory, is the macroscopic mechanical parameters of the particles and micromechanics parameters linked to simulate the interaction among the particles (Miao et al. 2012).
