CPSO优化参数的战斗机空战效能MELM评估模型  

MELM Evaluation Model of Fighter Air Combat Effectiveness Based on CPSOParameters Optimization

作　　者：魏燕明[1] 甘旭升[2] 程毅东 吴依涵 李胜厚 WEI Yan-ming;GAN Xu-sheng;CHENG Yi-dong;WU Yi-han;LI Sheng-hou(Xijing University,Xi’an 710123,China;Air Traffic Control and Navigation College,Air Force Engineering University,Xi’an 710051,China)

机构地区：[1]西京学院,西安710123 [2]空军工程大学空管领航学院,西安710051

出　　处：《火力与指挥控制》2022年第3期129-135,共7页Fire Control & Command Control

摘　　要：针对近距与超视距空战的特点,提出一种基于粒子群优化(PSO)算法与极限学习机(ELM)的空战效能评估模型。引入一种基于M估计的ELM,以抵御样本数据中粗差的干扰;采用基于混沌策略的PSO算法优化ELM隐含层的输入权值和偏差,以降低随机选取参数的影响,提升评估模型的精度;利用所建模型对战斗机空战效能进行评估。仿真表明,所提方法仅通过20次迭代就收敛到令人满意的精度,并具较强的抗粗差能力,从而验证了其可行性和有效性。For the characteristics of air combat beyond visual range and within visual range,an air combat effectiveness evaluation model is proposed on the basis of Particle Swarm Optimization(PSO)algorithm and Extreme Learning Machine(ELM).First,an ELM based on M estimation is introduced to resist the interference of gross errors in the sample data.Then the PSO algorithm with chaotic strategy is used to optimize the input weight value and deviation of hidden layer in ELM,which can reduce the impact of random selection of parameters and can improve the accuracy of the evaluation model.Finally,the built model is utilized to evaluate of the effectiveness of air combat of the fighter.The simulation indicates that the proposed method can converge a satisfactory accuracy through only 20 iterations,with strong resistence ability of gross errors.Its feasibility and effectiveness are verified.

关 键 词：极限学习机 粒子群优化算法 粗差 空战效能 评估模型 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TM930[自动化与计算机技术—控制科学与工程]