Scholarlink

This paper proposes an innovative machine learning algorithm that integrates Graph Attention Networks (GAT) with Monte Carlo Markov Chain (MCMC) techniques to optimize the Work Breakdown Structure (WBS) in crude oil vessel production. This novel approach aims to reduce CO2 emissions, minimize lead times, and enhance cost savings within the supply chain. A synthetic dataset representing 15,000 companies in the oil and gas sector was used to test the algorithm. The results demonstrate potential improvements in key metrics, paving the way for more sustainable and efficient supply chain operations.

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

Adaptive Neural Network for CO2 Reduction: A Predictive Model Integrating MCMC and GAT Techniques for Oil Vessel Supply Chain

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Lapo Chirici,
  • Yi Wang,
  • Kesheng Wang

摘要

This paper proposes an innovative machine learning algorithm that integrates Graph Attention Networks (GAT) with Monte Carlo Markov Chain (MCMC) techniques to optimize the Work Breakdown Structure (WBS) in crude oil vessel production. This novel approach aims to reduce CO2 emissions, minimize lead times, and enhance cost savings within the supply chain. A synthetic dataset representing 15,000 companies in the oil and gas sector was used to test the algorithm. The results demonstrate potential improvements in key metrics, paving the way for more sustainable and efficient supply chain operations.