Improved Crossover Operator Research Articles

Research on the Optimization of the Numerical Value Based on Improved Genetic Algorithm

For the lack of crossover operation, from three aspects of crossover operation , systemically proposed one kind of improved Crossover operation of Genetic Algorithms, namely used a kind of new consistent Crossover Operator and determined which two individuals to be paired for crossover based on relevance index, which can enhance the algorithms global searching ability; Based on the concentrating degree of fitness, a kind of adaptive crossover probability can guarantee the population will not fall into a local optimal result. Simulation results show that: Compared with the traditional cross-adaptive genetic Algorithms and other adaptive genetic algorithm, the new algorithms convergence velocity and global searching ability are improved greatly, the average optimal results and the rate of converging to the optimal results are better.

A New Approach to Solve the TSP using an Improved Genetic Algorithm

Genetic algorithms are one of the most important methods used to solve the Traveling Salesman Problem. Therefore, many researchers have tried to improve the Genetic Algorithm by using different methods and operations in order to find the optimal solution within reasonable time. This paper intends to find a new approach that adopts an improved genetic algorithm to solve the Traveling Salesman Problem, and compare with the well known heuristic method, namely, Kohonen Self-Organizing Map by using different data sets of symmetric TSP from TSPLIB. In order to improve the search process for the optimal solution, the proposed approach consists of three strategies: two separate tour segments sets, the improved crossover operator, and the improved mutation operator. The two separate tour segments sets are construction heuristic which produces tour of the first generation with low cost. The improved crossover operator finds the candidate fine tour segments in parents and preserves them for descendants. The mutation operator is an operator which can optimize a chromosome with mutation successfully by altering the mutation probability dynamically. The two improved operators can be used to avoid the premature convergence. Simulation experiments are executed to investigate the quality of the solution and convergence speed by using a representative set of test problems taken from TSPLIB. The results of a comparison between the new approach using the improved genetic algorithm and the Kohonen Self-Organizing Map show that the new approach yields better results for problems up to 200 cities.

A Novel Genetic Algorithm and its Application in Fuzzy Variable Structure Control of Fuel Cell

A novel genetic algorithm (GA) is proposed; a ranking genetic algorithm with improved crossover operator. The whole colony is divided into several sub-colonies, and each sub-colony is called a family, which is represented by its best individual. This algorithm includes two levels of structure: the family level and the harmonizing level. The families are parallel during the process of evolution. The harmonizing level ranks all families based on their fitness values, and transports the best individual of the first-rank family to low-grade families so as to accelerate their evolution. Two levels of competition are constructed; one among individuals of a family, and the other among families. The competition within a family is accomplished by a genetic algorithm with improved crossover operator. A family's mutation probability is determined by its relative competitive power. In this way, a rapid and global convergence to the optimum goal is obtained. The GA crossover operator is improved for the case of floating point operations. The improved crossover operator can generate child individuals at random within the space of the supercube, which enhances the space searching rate and precision. Finally, the proposed novel GA is applied to the fuzzy-variable structure control (FVSC) system of a molten carbonate fuel cell (MCFC). The simulation results are satisfying.