用大模型模拟工程师调参，自动优化化工过程的PID控制器。
A Physics-Informed Framework for PID Tuning of Chemical Processes Using Large Language Model Agents
- 用语言模型模仿工程师调参流程，结合控制诊断和性能反馈迭代优化。
- 小模型经微调后首次推荐成功率超94%，大模型在100个测试案例中成功率达75%-89%。
- 适合自动化控制、工业智能研发人员，尤其关注模型可解释性与稳定性提升。
化工过程的PID调参通常依赖于辨识出的过程模型，而现场工程师常通过观察闭环响应、诊断问题、调整增益并验证结果来反复调参。本文提出一种基于语言模型的物理信息框架，将此工程师式工作流形式化，适用于大型与小型语言模型（LLMs/SLMs）。托管型大模型接收闭环响应特征、控制工程诊断、调参偏好及基于内部模型控制（IMC）的示范，生成并迭代修正符合通用验收标准的PID参数。本地部署时，采用Qwen3-0.6B模型，通过监督微调（SFT）结合仿真验证的IMC目标，以及融合不可补偿稳定性与性能奖励的物理信息组相对策略优化（PI-GRPO）进行适配。在100个一阶加纯滞后（FOPDT）和100个二阶加纯滞后（SOPDT）测试案例中，托管模型（DeepSeek-V4-Flash和Qwen3.7-Plus）最终成功率分别为75%-89%和77%-79%；而Qwen3-0.6B经监督微调后首次推荐成功率提升至86.5%，使用PI-GRPO进一步增至94.0%，显著提高首次尝试的可靠性与稳定性裕度。
原文摘要 · Abstract (English)
PID tuning for chemical processes commonly relies on identified process models, whereas plant engineers often retune loops iteratively by observing responses, diagnosing deficiencies, adjusting gains, and validating the result. This work formalizes this engineer-like workflow in a language-model-assisted PID tuning framework applicable to both large and small language models (LLMs/SLMs). Hosted LLMs receive closed-loop response features, control-engineering diagnoses, tuning preferences, and internal model control (IMC)-based demonstrations to generate and iteratively correct PID gains under common acceptance criteria. For local deployment, Qwen3-0.6B is adapted through supervised fine-tuning (SFT) with simulation-verified IMC targets and physics-informed group relative policy optimization (PI-GRPO) with non-compensable stability and performance rewards. On 100 first-order plus dead time (FOPDT) and 100 second-order plus dead time (SOPDT) test cases, hosted LLMs (DeepSeek-V4-Flash and Qwen3.7-Plus) achieve final success rates of 75-89% and 77-79%, respectively. As for Qwen3-0.6B, supervised fine-tuning raises first-recommendation success to 86.5%, and PI-GRPO further increases it to 94.0%, primarily improving first-attempt reliability and stability margins.
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。