Scholarlink

Emerging technologies like Artificial Intelligence (AI) are transforming the railway sector. Analytical AI (AAI) is increasingly being integrated into asset management, operations, and maintenance to enhance decision-making processes. Recently, Generative AI (GenAI), including Large Language Models (LLMs), has introduced new opportunities. Although widely adopted in fields such as engineering and medicine, the application of GenAI in transportation remains limited. Railway maintenance, which is critical for ensuring safety and managing costs, stands to benefit significantly from AI by improving the production and consumption of information within railway processes. This paper reviews the current trends in the use of LLMs within the railway maintenance process, examining the approaches and applications of LLMs in each phase of maintenance. The review highlights a significant gap in the application of LLMs in railway maintenance, suggesting a need for further exploration and development in this area.

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

How Large Language Models Can Be Utilized in the Railway Maintenance Processes

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Chathuri Madhushika,
  • Ramin Karim,
  • Peter Söderholm,
  • Veronica Jägare,
  • Ravdeep Kour

摘要

Emerging technologies like Artificial Intelligence (AI) are transforming the railway sector. Analytical AI (AAI) is increasingly being integrated into asset management, operations, and maintenance to enhance decision-making processes. Recently, Generative AI (GenAI), including Large Language Models (LLMs), has introduced new opportunities. Although widely adopted in fields such as engineering and medicine, the application of GenAI in transportation remains limited. Railway maintenance, which is critical for ensuring safety and managing costs, stands to benefit significantly from AI by improving the production and consumption of information within railway processes. This paper reviews the current trends in the use of LLMs within the railway maintenance process, examining the approaches and applications of LLMs in each phase of maintenance. The review highlights a significant gap in the application of LLMs in railway maintenance, suggesting a need for further exploration and development in this area.