| Genetic algorithm (GA) is highly parallel and random search algorithm that simulates biological evolution mechanisms such as natural selection and "survival of the fittest".and has a main characteristic which is that the group searching strategy and the switching and searching for message between individuals are independent of gradient information. It especially suits to the sophisticated and no-linear problems which are difficult to the traditional methods and can be widely applied in the yields of machine learning,adaptive controlling, combinatory designing, artificial life and so on.Assignment problem is to assign the resources with certain method to various works, making its result attain the superior proceeds. Its military application are very extensive, such as target assign and force allocation. Because of special, complexity and indeterminations of the wartime military activity, the factor that demand consider is usually more, can hardly estimate with the accurate value, contrary, by employing experts opinion using fuzzy numbers and linguistic variables can obtain the good result.This paper introduce the basic theories and the implementary process of GA, and summarize the familiar improvement method. It studying the fuzzy multi-objective problem. By solving the concentrate of fuzzy synthetical evaluation matrix, the multi-objective can be converted to the single-objective. Then,introduce the application in the military assignment problem.The keystone of our work is focused on as following: the first is using the knowledge of fuzzy maths for solving the multi-objective assignment problem. Employing experts opinion using fuzzy numbers and linguistic variables, the fuzzy synthetical evaluation valuematrix is aggregated using fuzzy arithmetic, the problem can be converted to the classical assingment problem which can be solved by GA. The second is solving the classical assingment problem with GA toolbox of Sheffield. |
PDF Full Text Request