Improved Adaptive Genetic Algorithm and Its Application to Backward Analysis of Geotechnical Engineering

Abstract:

By niching, population migration and increasing Hamming distance between different populations,an improved adaptive genetic algorithm is proposed.It keeps populations diversity effectively and improves the performance of local convergence and premature convergence and enhances search speed and precision of genetic algorithm.High search speed and precision of the proposed method were further tested through back analysis of geotechnical engineering,and the influence of initial population yielding method, quantity of populations, maximum crossover probability and maximum mutation were discussed on search speed and precision.

Key words:backward analysis; adaptive genetic algorithm; niche; initial populations; crossover; mutation