Scholarlink

In maritime container terminals, the storage yard is recognized as a crucial area in permitting the efficient management of import and export flows. This study focuses on developing the storage rules at a tactical level following the consignment strategy for the export yard based on a European layout. To obtain more rational storage rules, Unsupervised Learning is employed to cluster similar containers. Five algorithms are tested with historical data from an Italian container terminal through Three experimental campaigns. The particular data distribution of containers is analyzed. A comparison of the proposed rule with some benchmark solutions is presented. Some possible tracks to integrate Machine Learning and Operational Research are pointed out.

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

Machine Learning Algorithms for Supporting Optimization in Defining Yard Stacking Strategies

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Daniela Ambrosino,
  • Haoqi Xie

摘要

In maritime container terminals, the storage yard is recognized as a crucial area in permitting the efficient management of import and export flows. This study focuses on developing the storage rules at a tactical level following the consignment strategy for the export yard based on a European layout. To obtain more rational storage rules, Unsupervised Learning is employed to cluster similar containers. Five algorithms are tested with historical data from an Italian container terminal through Three experimental campaigns. The particular data distribution of containers is analyzed. A comparison of the proposed rule with some benchmark solutions is presented. Some possible tracks to integrate Machine Learning and Operational Research are pointed out.