Abstract
Permeability coefficients of dam foundation are inversed on the base of real water heads. Otherwise, simple genetic algorithm has the disadvantages in determining the optimal probability values of the crossover and mutation, computation quantity is great and premature phenomena easily appears. Adaptive genetic algorithm is proposed to overcome the disadvantages which simple genetic algorithm has. At same time, adaptive genetic algorithm is used to identify the permeability coefficients of Er Tan dam foundation. The result shows that the method is effective in improving the computational convergence and overcoming the premature phenomena. So adaptive genetic algorithm is efficient and feasible in back analysis for permeability coefficients of dam.