| Optimization problems need to be solved in many fields, and the fine solutions to the problems may lead to great economic benefit. With the increasing of the complexity and scale of the of the optimization problems, classical optimization methods which base on the strict modeling become difficult to be carried out.Artificial fish-swarm algorithm is an animal's autonomous method that bases on the principle of artificial intelligent. It has some characters, such as no special requirement for object functions, Being insensitive to the initial values, tolerating wide range of values of parameters, having the abilities of parallel processing and global search. In the article, the improving and application of the artificial fish-swam algorithm are mainly discussed. The major innovations are as follows:For the continuous optimization problems, we mainly introduce the modified AFSA to solve the optimization problems of non-constrained function, constrained function and multi-objective function.Via the analysis of the parameters and the introduction of the method of section-search, we made the algorithm adjust the parameters automatically in the process of optimization. And the combination with the characteristics of AFSA made us get an adaptive artificial fish-swarm algorithm. The application to several test functions indicates that the new method has the feature of high rate of convergence and high optimizing precision.Aiming at the constrained optimization problems, we introduce the concept of semi-feasible region, proposed a novel rule of tournament selection, and improved the fitness function of evolutionary algorithm, which is based on tournament selection and penalty function. Meanwhile, we designed a selection operator for the semi-feasible region and proposed a novel evolutionary algorithm to solve constrained optimization problems. Numerical experiments on the non-linear equality and inequality constrained problems shows the fine stability and precision... |
PDF Full Text Request