Research And Implementation Of Cooperative Strike Strategy For Multi-Autonomous Platform Weapon Station

In the modern battlefield environment,intelligence and decentralization have become the trend of combat development.The weapon station that can complete the attack on the target independently,and the weapon station formed by the combination of multiple weapons has become an important component of modern warfare.Therefore,in small and medium-scale operations,the mode of coordinated strikes with multiple weapon stations is becoming more and more popular.Multiple weapon stations rely on network connections,share data,and coordinate to complete strike operations.In a coordinated combat mission,the purpose of weapon allocation is to find an appropriate weapon station to strike a target,so as to minimize the overall threat of the enemy’s threat to the target group.Therefore,this article focuses on the research of weapon and target strike allocation strategy in the study of multi-weapon station coordinated strike strategy.Based on the research of a large number of domestic and foreign related documents,this paper analyzed the optimal allocation strategy requirements of weapon targets in modern combat scenarios.Combining the actual combat situation in this paper,applying neural network algorithms,intelligent optimization algorithms and fuzzy processing and other related knowledge,designed an applying the optimal strike strategy of each weapon station to each threat target in the land combat scenario,the optimal allocation of weapon to target was completed.The main research contents of this article are:1)Aiming at the problem of insufficient accuracy of traditional threat assessment algorithms,this paper implemented the improvement of fuzzy neural network by adding new components to the traditional fuzzy neural network structure.The new network model proposed in this paper was used to complete the evaluation of the target threat degree,and realized the function of obtaining the target threat degree through the network model to obtain the data processing of the sensor device.Finally,the experimental resulted verify that the improved algorithm in this paper is in comparison with the traditional algorithm.The accuracy of threat assessment had been greatly improved.2)In view of the high complexity and slow running speed of static weapon allocation algorithms at home and abroad,this paper implemented the improvement of traditional particle swarm algorithm by adding chaos factor to traditional particle swarm algorithm.After that,the improved chaotic particle swarm algorithm was used to complete the weapon-target strike assignment in a static scenario,and the optimal strike target strategy of our weapon station under the static weapon assignment situation was obtained.Finally,the experiment in the simulation scenario proved that compared with Compared with the traditional particle swarm optimization algorithm,the improved chaotic particle swarm optimization algorithm greatly improved the efficiency of weapon target allocation in static scenarios.3)In view of the incomplete establishment of the dynamic weapon allocation model,this paper re-modeled the dynamic weapon allocation problem by adding constraints,and improve the transition probability formula in the traditional ant colony algorithm to improve the efficiency of weapon stations and threat targets under dynamic conditions.Finally,an experimental test was carried out in a simulation scenario.It was proved that compared with the traditional ant colony algorithm,the method in this paper reduces the probability of occurrence of local optimal conditions and improves the efficiency of target allocation under dynamic conditions.This paper finally obtains an optimal allocation method for multi-weapon station cooperative operations.Fuzzy wavelet neural network is used to solve the threat assessment problem,the improved particle swarm algorithm is used to solve the static weapon allocation problem,and the improved ant colony algorithm is used to solve the dynamic weapon allocation problem.