用大模型辅助开关电源设计，效率提升近6倍
Evaluating LLM-based Workflows for Switched-Mode Power Supply Design
- 结合推理与电路仿真反馈的智能设计流程
- 任务解决率从15%提升至91%，参数调优效果显著
- 适合硬件工程师快速验证电路方案
大型语言模型（LLMs）在软件工程等领域展现出巨大潜力，但在电子电路设计中的应用尚不明确。本文聚焦于印刷电路板（PCBs）上开关模式电源（SMPS）的设计，提出多种基于LLM的工作流，融合推理能力、检索增强生成（RAG）以及自定义工具包，使模型可与SPICE仿真交互以评估电路修改的影响。通过两个基准实验，分析了不同设计任务中LLM助手的表现，包括参数调优、拓扑适配与优化。实验结果表明，在269个手工创建的基准任务中，结合SPICE仿真反馈和当前LLM的推理能力，任务解决率从15%提升至91%。分析显示，多数参数调优任务可被成功解决，但部分拓扑适配任务仍存在局限。研究为改进现有概念提供了启示，例如采用基于文本的电路表示方法。
原文摘要 · Abstract (English)
Large language models (LLMs) have great potential to enhance productivity in many disciplines, such as software engineering. However, it is unclear to what extent they can assist in the design process of electronic circuits. This paper focuses on the application of LLMs to switched-mode power supply (SMPS) design for printed circuit boards (PCBs). We present multiple LLM-based workflows that combine reasoning, retrieval-augmented generation (RAG), and a custom toolkit that enables the LLM to interact with SPICE simulations to estimate the impact of circuit modifications. Two benchmark experiments are presented to analyze the performance of LLM-based assistants for different design tasks, including parameter tuning, topology adaption and optimization of SMPS circuits. Experiment results show that SPICE simulation feedback and current LLM advancements, such as reasoning, significantly increase the solve rate on 269 manually created benchmark tasks from 15% to 91%. Furthermore, our analysis reveals that most parameter tuning design tasks can be solved, while limits remain for certain topology adaption tasks. Our experiments offer insights for improving current concepts, for example by adapting text-based circuit representations
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。