Improved Glowworm Swarm Optimization Research And Threat Assessment Application

The difference between modern warfare and modern warfare under the current situation has gradually increased over time.There is no longer a lack of basic status information in modern warfare operations.On the contrary,situation information is mixed,the combat environment is complex and changeable,and the combat speed is fast.High mobility,which triggers frequent information exchange.In today’s general environment,the factors that influence the decision-making of commanders and fighters have increased,and the requirements for commanders and fighters to understand the situation are higher.It is difficult to meet the needs of modern warfare situation understanding by the commanders and fighters alone.Therefore,the commander’s situation understanding must use other auxiliary tools to complete the task to improve the accuracy and intelligence of combat threat assessment.However,classic combat threat assessment methods often have certain limitations,leading to inaccurate judgments.At this stage,the use of various algorithms to assess threats is a relatively common method,but when solving a problem,it is not difficult to obtain a feasible solution.The difficulty is how to obtain the optimal solution to the problem,or in other words It is a special solution that meets certain specific conditions.In response to this problem,this article studies the fundamental principles and operational logic of situation assessment and threat assessment,and specifically describes the issues of battlefield combat threat assessment,constructs a threat assessment system,and proposes six principles that need to be followed to build the system.Combining the artificial firefly swarm optimization(GSO)algorithm with the fuzzy system,an improved algorithm based on the variable step size and random movement strategy of the fuzzy system(FSGSO algorithm for short)is proposed;The improved algorithm for anti-disturbance fuzzy system with variable step size(ADFSGSO algorithm for short)analyzes and proves the global convergence of the algorithm;through the comparison of experimental results,the improved algorithm has better optimization ability.According to the combat situation in the air battlefield,analyze its capability attributes and situation attributes to construct an air battlefield combat threat assessment model;and according to the advantages and disadvantages of the improved algorithm and the BP neural network,construct a threat assessment model based on the improved algorithm to optimize the BP neural network.The quantified result of threat assessment factors is used as the network input,and the output is the corresponding threat value.Analyzing and comparing the experimental results,the improved method proposed in this paper has better optimization effect,and can effectively and accurately solve the problem of battlefield combat threat assessment.