Abstract: A backward analysis of physical and mechanical parameters of surrounding rock was conducted based on finite element method, orthogonal design and artificial neural networks, in which different parameters were chosen according to orthogonal design.The related analytical samples for neural networks were given by ANSYS calculation results.With the samples trained, the structure and learning parameters of networks were optimized.The physical and mechanical parameters of surrounding rock of Luoping tunnel were analyzed backwards by trained results and the on-the-spot surveyed data.The results met the demand of precision.