In dynamic manufacturing environments, disruptions such as machine breakdowns and new order arrivals continuously shift the optimal dispatching strategy, making adaptive rule selection essential. Existing LLM-powered Automatic Heuristic Design (AHD) frameworks evolve toward a single elite rule that cannot meet this adaptability demand. To address this, we present DSevolve, an industrial scheduling framework that evolves a quality-diverse portfolio of dispatching rules offline and adaptively deploys them online with second-level response time. Multi-persona seeding and topology-aware evolutionary operators produce a behaviorally diverse rule archive indexed by a MAP-Elites feature space. Upon each disruption event, a probe-based fingerprinting mechanism characterizes the current shop floor state, retrieves high-quality candidate rules from an offline knowledge base, and selects the best one via rapid look-ahead simulation. Evaluated on 500 dynamic flexible job shop instances derived from real industrial data, DSevolve outperforms state-of-the-art AHD frameworks, classical dispatching rules, genetic programming, and deep reinforcement learning, offering a practical and deployable solution for intelligent shop floor scheduling.

翻译：在动态制造环境中，机器故障与新订单到达等扰动会持续改变最优调度策略，使得自适应规则选择至关重要。现有基于大型语言模型（LLM）的自动启发式设计框架倾向于演化出单一精英规则，无法满足这种适应性需求。针对该问题，我们提出DSevolve——一种工业调度框架，该框架离线演化出质量多样化调度规则组合，并在线以秒级响应时间自适应部署。通过多角色初始化和拓扑感知演化算子，生成由MAP-Elites特征空间索引的行为多样性规则档案库。每次扰动事件发生后，基于探测的指纹机制表征当前车间状态，从离线知识库中检索高质量候选规则，并通过快速前瞻仿真选取最优规则。在基于真实工业数据生成的500个动态柔性作业车间实例上的评估表明，DSevolve优于现有最先进的自动启发式设计框架、经典调度规则、遗传编程和深度强化学习方法，为智能车间调度提供了实用且可部署的解决方案。