Army Aviation Flight Support Management Information System Based On Convergence Of Ant Colony Algorithm And Genetic Algorithm

With the large number of high-tech weaponry in the war of the application of high-tech weapons, the number and complexity of rapidly growing, and the corresponding logistical support research in the role of logistics command and management is increasing. Flight security is a kind of logistical work, because it is just specifically for training of air force, combating readiness of the security work, so which ground forces of logistical support also has a relatively more distinctive features:the supply of materials in large quantities and variety of coordinated logistics business sector categories and more complex and stringent supply requirements, motor speed is high, and in order to protect the high quality requirements. In this case, the Army Aviation Flight Support Management Information System has become an important way to solve this problem.As the flight security work is a multi-disciplinary collaboration with protect equipment and vehicles to conduct high-precision and high speed protection of the jobs. At this stage to protect the grass-roots army aviation units in the actual work, which is scheduling the coordination of protection of resources, protection of the command group personnel are relying on experience to carry out the organization and deployment. In order to solve this problem and to give us the security work and the introduction of more scientific, more efficient ant colony algorithm which is based on genetic algorithms optimize the integration of technology in the global search and route choice, making features better. This article will apply this technology to the system design of to address the protection of equipment and vehicles reasonable distribution of scheduling problem. And it uses the Visual Basic 6.0 and Delphi 7.0 software, the main using of C/S model system to develop.In the algorithm design, we combine genetic algorithms and ant colony algorithm. After the genetic algorithm is crossover, from the current group to find the best chromosome, which it can be considered as better solutions, using ants to find better chromosomes. Selection probability function of each ant according to select a path, to produce a new chromosome. If the new chromosome is better than the original chromosome fitness, then we can reserve, and make the chromosome as a variation of a new operation to be chromosomes; and on other hand, is not retained by the ants continue to search for the next one. When we find the number of useful chromosomes to achieve population size, stop looking. On this way, with the ant colony algorithm for computing the variation to guide genetic algorithms is enhancing the intelligence of the mutation operator.According to the results obtained for vehicle scheduling, you can actually use the current start of the scheduling to reduce the number of time-saving and protection of resources, and then improving service efficiency.