基于PSO-BP神经网络的高原寒地维修器材换算系数研究  

Research on Conversion Coefficient of Maintenance Equipment in Plateau Cold Area Based on PSO-BP Neural Network

作　　者：王金帼 王亚彬 王帅 乔智勇 WANG Jinguo;WANG Yabin;WANG Shuai;QIAO Zhiyong(Shijiazhuang Campus,Army Engineering University of PLA,Shijiazhuang 050003,China)

机构地区：[1]陆军工程大学石家庄校区,石家庄050003

出　　处：《火力与指挥控制》2023年第5期83-89,共7页Fire Control & Command Control

摘　　要：针对高原寒地部队担负任务和所处地理环境的特殊性,军械装备维修器材受各种因素的影响,需求规律难以掌握,从5个方面18个对维修器材需求影响因素分析的基础上,分别对18个影响因素进行量化并归一化处理。运用粒子群优化算法对BP神经网络进行优化,提出了一种基于PSO-BP神经网络的维修器材换算系数模型,将影响因素作为输入变量,对不同种类的维修器材进行预测,通过算例分析验证该方法的合理性和准确性。In view of the specialty for tasks taken on the troops and geographical environment of the troops in the plateau and cold regions,ordnance equipment maintenance equipment is affected by various factors,it is difficult to grasp the law of demand,based on the analysis of 18 factors affecting the demand for maintenance equipment from 5 aspects,the 18 factors are quantified and normalization processed.Then particle swarm optimization algorithm is used to optimize the BP neural network,a conversion coefficient model of maintenance equipment based on PSO-BP neural network is proposed,the influencing factors are regarded as input variables to predict different types of maintenance equipment,the rationality and accuracy of the proposed method are verified by numerical example analysis.

关 键 词：高原寒地 需求预测 PSO-BP神经网络 换算系数 

分 类 号：E939[军事—军事装备学]