基于APSO-BP神经网络的末敏弹作战效能评估方法  

Evaluation method of operational effectiveness of terminal sensitive projectiles based on APSO-BP neural network

作　　者：唐永果 TANG Yongguo(Shijiazhuang Campus of Army Engineering University,Shijiazhuang 050000,China)

机构地区：[1]陆军工程大学石家庄校区,石家庄050000

出　　处：《兵器装备工程学报》2024年第10期100-106,共7页Journal of Ordnance Equipment Engineering

基　　金：装供〔2023〕920号。

摘　　要：针对末敏弹结构复杂、影响因素多、作战效能分析困难等问题,以末敏弹命中概率作为目标函数,建立了作战效能评估指标体系,提出了一种基于APSO-BP神经网络的作战效能评估模型,并构建了BP神经网络和PSO-BP神经网络2种对比模型,利用MATLAB工具对3种模型进行了仿真分析。结果显示,APSO-BP神经网络的运行耗时为0.6513 s,均方误差为0.0032,相关系数为0.9789;PSO-BP神经网络的运行耗时为2.0154 s,均方误差为0.0075,相关系数为0.9688;BP神经网络的运行耗时为14.1375 s,均方误差为0.0159,相关系数为0.8900。APSO-BP神经网络评估模型运行耗时更短,预测精度更高,对于末敏弹的作战运用具有重要的理论意义和现实价值。In view of the complex structure,many influencing factors and difficulties in operational effectiveness analysis of terminal sensitive projectiles,the operational effectiveness evaluation index system was established by taking the hit probability of the terminal sensitive projectiles as the objective function.An operational effectiveness evaluation model based on APSO-BP neural network was proposed,two models of BP neural network and PSO-BP neural network were constructed for comparison,and the three models were simulated by Matlab.The results show that the running time of APSO-BP neural network is 0.6513 s,the mean square error is 0.0032,and the correlation coefficient is 0.9789.The running time of PSO-BP neural network is 2.0154 s,the mean square error is 0.0075,and the correlation coefficient is 0.9688.The running time of BP neural network is 14.1375 s,the mean square error is 0.0159,and the correlation coefficient is 0.8900.APSO-BP neural network evaluation model has shorter running time and higher prediction accuracy,which has important theoretical significance and practical value for the operational application of terminal sensitive projectiles.

关 键 词：末敏弹 命中概率 效能评估 BP神经网络 粒子群算法 APSO-BP算法 

分 类 号：TJ413.3[兵器科学与技术—火炮、自动武器与弹药工程] E917[军事] TP183[自动化与计算机技术—控制理论与控制工程]