arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.22657cs.NE
收藏

结合种群自进化大语言模型的动态模糊作业车间调度问题自动编程

Automatic programming via large language models with population self-evolution for dynamic fuzzy job shop scheduling problem

State Key Laboratory of Intelligent Manufacturing Equipment and Technology, Huazhong University of Science and Technology(华中科技大学智能制造装备与技术国家重点实验室)

Jin Huang, Qihao Liu, Xinyu Li, Liang Gao, Yue Teng

AI总结:

该研究针对动态模糊作业车间调度问题,提出种群自进化框架结合大语言模型自动设计启发式调度规则,性能优于多种现有方法。

摘要:

启发式调度规则(HDRs)被广泛用于求解动态模糊作业车间调度问题(DFJSSP),但其性能高度依赖特定场景,常需专家定制。为解决该问题,遗传编程(GP)、基因表达式编程(GEP)等自动化设计方法被提出,但这些方法存在搜索过程随机性高的挑战。近期,大语言模型(LLMs)与进化算法的结合为提示工程和自动化算法设计开辟了新可能。为提升LLMs在自动HDR设计中的能力,本文提出一种新颖的种群自进化(SeEvo)框架,该框架借鉴人类专家的自反思设计策略。值得注意的是,此框架采用一种新颖的师生学习机制,使LLM(学生)能生成鲁棒的HDRs。在掌握实际加工时间完整知识的教师模型引导下,学生学习从历史偏差中推断模糊不确定性,从而有效预判并适应模糊影响。实验结果表明,SeEvo显著优于GP、GEP、深度强化学习(DRL)方法及文献中十余种常用HDRs,尤其在未见过的动态场景中表现突出。

英文摘要:

Heuristic dispatching rules (HDRs) are widely used for solving the dynamic fuzzy job shop scheduling problem (DFJSSP). However, their performance is highly sensitive to specific scenarios and often necessitates expert customization. To overcome this, automated design methods like genetic programming (GP) and gene expression programming (GEP) have been proposed. Despite their success, these methods face challenges, such as high randomness in the search process. Recently, the combination of large language models (LLMs) with evolutionary algorithms has opened new possibilities for prompt engineering and automated algorithm design. To improve the ability of LLMs in automatic HDR design, this paper introduces a novel population self-evolutionary (SeEvo) framework, which draws inspiration from the self-reflective design strategies employed by human experts. Notably, this framework employs a novel teacher-student learning mechanism, allowing the LLM (student) to generate robust HDRs. Guided by a teacher model with complete knowledge of actual processing times, the student learns to infer fuzzy uncertainties from historical deviations, enabling it to effectively anticipate and adapt to fuzzy impacts. Experimental results demonstrate that SeEvo significantly outperforms GP, GEP, deep reinforcement learning (DRL) methods, and more than ten commonly used HDRs from the literature, particularly in previously unseen and dynamic scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑