Scholarlink

Effective fleet maintenance planning is vital to the minimization of operational costs and downtime in industries where equipment longevity and performance are key. In this paper, we propose a deep reinforcement learning (DRL) approach to optimize fleet maintenance schedules, particularly in environments where machine lifetimes follow a Weibull distribution. Our model dynamically adjusts maintenance plans to reduce the incidence of unplanned maintenance events, which are costlier and more disruptive than planned interventions. Simulations demonstrate that our method significantly reduces unplanned maintenance rates while maintaining machine availability, outperforming traditional heuristic-based approaches.

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

Deep Reinforcement Learning for Maintenance Planning in Weibull Distributed Fleet Systems

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Kouroush Jenab,
  • Jorge A. Ortega-Moody,
  • William J. Muldoon,
  • Tyler B. Ward,
  • Cesar Isaza,
  • Lizeth D. C. Molina Acosta

摘要

Effective fleet maintenance planning is vital to the minimization of operational costs and downtime in industries where equipment longevity and performance are key. In this paper, we propose a deep reinforcement learning (DRL) approach to optimize fleet maintenance schedules, particularly in environments where machine lifetimes follow a Weibull distribution. Our model dynamically adjusts maintenance plans to reduce the incidence of unplanned maintenance events, which are costlier and more disruptive than planned interventions. Simulations demonstrate that our method significantly reduces unplanned maintenance rates while maintaining machine availability, outperforming traditional heuristic-based approaches.