STUDY ON GENETIC-NEURAL NETWORK METHODOF DISPLACEMENT BACK ANALYSIS

Anevolutionary neural network method for displaceme nt back analysis is proposed bycombining the neural network and genetic algorit hm. The samples produced in orthogonalexperiment are used to train the neural n etwork whose architecture is determined inglobal optimum by genetic algorithm. Thus, the neural network with optimal architecturetrained by optimal prediction algorithm is used to describe the relationship between therock mechanical para meters and displacements produced due to excavation. Then geneticalgorithm is a dopted again to search the optimal rock mechanical parameters in theirgloba l ranges. As an example, a back analysis for elastic problem is introduced. Theresults are satisfactory.