运筹与管理 ›› 2021, Vol. 30 ›› Issue (10): 165-168.DOI: 10.12005/orms.2021.0330

• 应用研究 • 上一篇    下一篇

一种基于随机森林的备件预测模型研究

黄国兴1, 曹先怀1, 钱晓飞2   

  1. 1.合肥工业大学 机械工程学院,安徽 合肥 230009;
    2.合肥工业大学 管理学院,安徽 合肥 230009
  • 收稿日期:2020-09-18 出版日期:2021-10-25
  • 作者简介:黄国兴,男,博士,硕士生导师。主要从事装备运维优化、决策科学与技术、振动控制与低噪声设计等方面的研究工作。
  • 基金资助:
    国家重点研发计划项目多要素动态协同的装备运维服务优化技术(2019YFB1705303)

Research on Spare Parts Prediction Model Based on Random Forest

HUANG Guo-xing1, CAO Xian-huai1, QIAN Xiao-fei2   

  1. 1. School of Mechanical Engineering, Hefei University of Technology, Hefei 230009, China;
    2. School of Management, Hefei University of Technology, Hefei 230009, China
  • Received:2020-09-18 Online:2021-10-25

摘要: 对舰船零部件发生故障问题进行故障诊断,并对故障诊断结果进行分析,建立舰船零部件备件需求模型,给出零部件之间的发生故障概率的关系与备件需求特征;将随机森林回归原理应用到了舰船零部件的备件需求预测领域,构建了基于随机森林的预测模型,以及预测结果准确率的评价。用诊断结果数据对算法进行验证,结果表明,将随机森林算法运用到舰船的备件预测领域可以为舰船装备在一次海上任务期内备件配置问题提供参考价值。

关键词: 随机森林, 备件, 需求预测

Abstract: The fault diagnosis of ship parts is carried out, the fault diagnosis results are analyzed, the spare parts demand model of ship parts is established, and the relationship between failure probability and spare parts demand characteristics are given; The principle of random forest regression is applied to the field of spare parts demand prediction of ship parts, the prediction model based on random forest is constructed, and the accuracy of prediction results is evaluated. The results show that the application of random forest algorithm to the field of ship spare parts prediction can provide reference value for the spare parts configuration of ship equipment in a marine mission.

Key words: random forest, spare parts, demand forecast

中图分类号: