用物理约束强化学习，从头设计高效安全的可持续制冷剂。
Discovery of Sustainable Refrigerants through Physics-Informed RL Fine-Tuning of Sequence Models
- 将物理规律融入生成模型，确保分子设计符合热力学原理。
- 在有限数据下生成新制冷剂，且通过循环模拟验证性能。
- 适合材料发现与绿色化学领域研究者参考。
当前空调系统广泛使用的氢氟碳化物等制冷剂是强效温室气体，正逐步被淘汰。尽管大规模分子筛选已被用于寻找替代品，但实际可用的制冷剂仅约300种，且新增候选物缺乏实验验证。这一可靠数据的稀缺限制了纯数据驱动方法的效果。本文提出Refgen，一种融合机器学习与物理先验知识的生成式流程。该流程在确保分子结构有效生成的基础上，集成关键物性预测模型、状态方程、热化学多项式及完整蒸气压缩循环仿真。这些模型支持在热力学约束下进行强化学习微调，保证一致性并引导发现兼顾效率、安全与环境影响的分子。通过将物理知识嵌入学习过程，Refgen有效利用稀缺数据，实现对已知化合物集之外的新制冷剂的从头发现。
原文摘要 · Abstract (English)
Most refrigerants currently used in air-conditioning systems, such as hydrofluorocarbons, are potent greenhouse gases and are being phased down. Large-scale molecular screening has been applied to the search for alternatives, but in practice only about 300 refrigerants are known, and only a few additional candidates have been suggested without experimental validation. This scarcity of reliable data limits the effectiveness of purely data-driven methods. We present Refgen, a generative pipeline that integrates machine learning with physics-grounded inductive biases. Alongside fine-tuning for valid molecular generation, Refgen incorporates predictive models for critical properties, equations of state, thermochemical polynomials, and full vapor compression cycle simulations. These models enable reinforcement learning fine-tuning under thermodynamic constraints, enforcing consistency and guiding discovery toward molecules that balance efficiency, safety, and environmental impact. By embedding physics into the learning process, Refgen leverages scarce data effectively and enables de novo refrigerant discovery beyond the known set of compounds.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。