Research On Genetic Algorithm And Its Applications In Direct Rorque Control

Genetic algorithm is one of the optimal search algorithms that are most widely in use. Today, genetic algorithm has been used in many fields, such as function optimum, model optimum,structure optimum, and so on. Genetic algorithm apt fall into the local optimum, sometimes, its convergence speed can not meet for the demands also. How to overcome these limitations has been a hot study project of many scholars and engineers.The paper puts forward a series of methods on improving the simple genetic algorithm. Importing foreign species, first mutating the high quality species and reproducing the high quality species are used to realize the selection operation of the simple genetic algorithm. The improved genetic algorithm takes the hybrid crossover strategies into the crossover operation part. The hybrid crossover strategies include double-population crossover, inverted order crossover and adjacent crossover. First mutation probability, crossover probability and mutation probability tune with the fitness and the convergence speed. The amount of the foreign species being imported and high quality species of the first mutation could self-tune with the convergence speed. The improved genetic algorithm applies to optimizing PID parameters, the simulation results show that the improved genetic algorithm is better than the simple genetic algorithm on searching for the global optimum.