现代防御技术 ›› 2020, Vol. 48 ›› Issue (4): 102-109.DOI: 10.3969/j.issn.1009-086x.2020.04.15

• 综合保障性技术 • 上一篇    下一篇

装备保障备件需求预测算法

康警予1, 陈忠2, 刘延杰2, 蔡骏2, 王晖1   

  1. 1.陆军装甲兵学院 演训中心,北京 100072;
    2.中国电子科技集团公司 第二十八研究所,江苏 南京 210007
  • 收稿日期:2019-12-23 修回日期:2020-03-01 出版日期:2020-08-20 发布日期:2021-01-21
  • 作者简介:康警予(1988-),女,北京人。博士生,主要研究方向为作战装备保障。通信地址:100093 北京市海淀区西小府甲22号 E-mail:sky2007cz@163.com

Spare Parts Demand Prediction Algorithm for Equipment Support

KANG Jing-yu 1, CHEN Zhong2, LIU Yan-jie2, CAI Jun2, WANG Hui1   

  1. 1. Academy of Armored Force Engineering,Military Exercise and Training Center,Beijing 100072,China;
    2. The 28th Research Institute of China Electronics Technology Group Corporation,Jiangsu Nanjing 210007,China
  • Received:2019-12-23 Revised:2020-03-01 Online:2020-08-20 Published:2021-01-21

摘要: 面对维和装备种类繁杂与维和环境复杂恶劣、保障维修矛盾突出的问题,必须强化任务开始前的维和装备保障备件需求预测。首先分析了维和任务特点,提出了维和装备保障构想;其次提出了维和装备保障需求预测步骤,研究了基于PSO-BP神经网络的维和装备保障预测模型;最后基于实际数据,采用实验验证的方法检验了算法的有效性。实验结果表明:通过基于PSO-BP神经网络的维和装备保障预测模型可以有效对维和装备保障备件需求进行预测,提高维和装备保障效能。

关键词: 维和任务, 保障备件, PSO-BP神经网络, 保障效能, 需求算法

Abstract: Facing the problems of complex types of peacekeeping equipment,complex and harsh peacekeeping environment,and prominent contradiction in support maintenance,it is necessary to strengthen the demand prediction of spare parts for peacekeeping equipment support before the start of the mission.Firstly,the characteristics of peacekeeping mission are analyzed,and the concept of peacekeeping equipment support is put forward.Secondly,the steps of peacekeeping equipment support demand prediction are proposed,and the prediction model of peacekeeping equipment support based on particle swarm optimization (PSO)-back propagation (BP) neural network is studied.Finally,the effectiveness of the algorithm is verified by experiments based on actual data.The experimental results show that the prediction model of peacekeeping equipment support based on PSO-BP neural network can effectively predict the demand for spare parts of peacekeeping equipment support and improve the efficiency of peacekeeping equipment support.

Key words: peacekeeping mission, guarantee spare parts, particle swarm optimization (PSO)-back propagation (BP) neural network, guarantee effectiveness, prediction algorithm

中图分类号: