Scholarlink

<p>Within the Industry 4.0 paradigm, manufacturers encounter mounting pressures to deliver personalized products while accelerating supply chain responsiveness. This necessitates dynamic adaptation to rapidly evolving production schedules to ensure product quality without compromising manufacturing efficiency. Unpredictable dynamic disruptions within production environments, however, significantly compromise scheduling stability and overall productivity. To solve these challenges with a focus on makespan minimization, this study proposes a Deep Reinforcement Learning (DRL) framework for solving the Dynamic Flexible Job Shop Scheduling Problem (DFJSP) under stochastic job insertions and machine breakdowns. By formulating the DFJSP as a Markov Decision Process (MDP), the DRL agent dynamically determines optimal actions at each scheduling point based on real-time system states, assigning pending operations to available machines. To effectively encapsulate complex shop-floor dynamics, a Heterogeneous Graph Transformer (HGT)-based representation approach extracts and augments salient features of jobs and machines, enabling the agent to make end-to-end decisions. Furthermore, a tailored reward function enhances learning efficiency and solution quality, while a <i>softmax</i> action selection strategy effectively balances the exploration–exploitation (EE) trade-off. Notably, the Proximal Policy Optimization (PPO) algorithm is employed for agent training, greatly enhancing the efficacy of policy optimization. Simulation-based experimental evaluation demonstrates that the proposed HGT-based Reinforcement Learning (HGTRL) methodology effectively solves the DFJSP. Comparative analysis confirms that HGTRL achieves superior scheduling performance: For small-scale instances, HGTRL maintains an average gap of less than 16% from optimal solutions while eliminating the need for prior global information required by exact algorithms. Unlike exact solvers that require substantial computational time, the approach model generates high-quality schedules in just seconds. Compared with mainstream DRL methods, HGTRL achieves lower makespan values with reduced variance across diverse problem scales, maintaining a win rate exceeding 17% against all competing methods, confirming its robust scalability and competitive efficacy in solving complex DFJSP problems.</p>

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 deep reinforcement learning method for dynamic flexible job shop scheduling via heterogeneous graph transformer

  • 期刊论文

  • 发表日期：

    2026年6月24日

查看全文
  • Jianlin Zhang,
  • Chao Du,
  • Wu Zhao,
  • Jie Cao,
  • Zuohan Chen

摘要

Within the Industry 4.0 paradigm, manufacturers encounter mounting pressures to deliver personalized products while accelerating supply chain responsiveness. This necessitates dynamic adaptation to rapidly evolving production schedules to ensure product quality without compromising manufacturing efficiency. Unpredictable dynamic disruptions within production environments, however, significantly compromise scheduling stability and overall productivity. To solve these challenges with a focus on makespan minimization, this study proposes a Deep Reinforcement Learning (DRL) framework for solving the Dynamic Flexible Job Shop Scheduling Problem (DFJSP) under stochastic job insertions and machine breakdowns. By formulating the DFJSP as a Markov Decision Process (MDP), the DRL agent dynamically determines optimal actions at each scheduling point based on real-time system states, assigning pending operations to available machines. To effectively encapsulate complex shop-floor dynamics, a Heterogeneous Graph Transformer (HGT)-based representation approach extracts and augments salient features of jobs and machines, enabling the agent to make end-to-end decisions. Furthermore, a tailored reward function enhances learning efficiency and solution quality, while a softmax action selection strategy effectively balances the exploration–exploitation (EE) trade-off. Notably, the Proximal Policy Optimization (PPO) algorithm is employed for agent training, greatly enhancing the efficacy of policy optimization. Simulation-based experimental evaluation demonstrates that the proposed HGT-based Reinforcement Learning (HGTRL) methodology effectively solves the DFJSP. Comparative analysis confirms that HGTRL achieves superior scheduling performance: For small-scale instances, HGTRL maintains an average gap of less than 16% from optimal solutions while eliminating the need for prior global information required by exact algorithms. Unlike exact solvers that require substantial computational time, the approach model generates high-quality schedules in just seconds. Compared with mainstream DRL methods, HGTRL achieves lower makespan values with reduced variance across diverse problem scales, maintaining a win rate exceeding 17% against all competing methods, confirming its robust scalability and competitive efficacy in solving complex DFJSP problems.