Scholarlink

Spare parts support plays a critical role in advanced maintenance and support systems for aircraft equipment. Traditional spare parts prediction methods based on empirical formulas, due to their limited data dimensions and insufficient dynamic adaptability, often result in simultaneous inventory redundancy and shortages, significantly hindering the improvement of equipment efficiency. This paper proposes a multi-dimensional equipment-level spare parts demand prediction and support algorithm based on machine learning. By analyzing extensive historical data on equipment spare parts consumption and integrating operational condition data and maintenance logs, the algorithm identifies trends in spare parts consumption. Ultimately, it achieves accurate and flexible prediction of equipment-level spare parts demand, effectively reducing the risks of resource waste and inventory mismatches.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Machine Learning Based Multi-dimensional Equipment-Level Spare Parts Demand Forecasting and Support Algorithm

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Daqing Meng,
  • Qiuyan Yao,
  • Hui Yang,
  • Xiaoliang Luo,
  • Xiaojing Wang,
  • Lin Li

摘要

Spare parts support plays a critical role in advanced maintenance and support systems for aircraft equipment. Traditional spare parts prediction methods based on empirical formulas, due to their limited data dimensions and insufficient dynamic adaptability, often result in simultaneous inventory redundancy and shortages, significantly hindering the improvement of equipment efficiency. This paper proposes a multi-dimensional equipment-level spare parts demand prediction and support algorithm based on machine learning. By analyzing extensive historical data on equipment spare parts consumption and integrating operational condition data and maintenance logs, the algorithm identifies trends in spare parts consumption. Ultimately, it achieves accurate and flexible prediction of equipment-level spare parts demand, effectively reducing the risks of resource waste and inventory mismatches.