用因果推断分析模拟电路设计参数影响，让设计更可解释、更准确。
Causal AI For AMS Circuit Design: Interpretable Parameter Effects Analysis
- 从SPICE仿真数据构建有向无环图，用平均处理效应量化参数影响。
- 在三种运放电路中，因果模型误差低于25%，神经网络误差超80%且常错方向。
- 适合需要可解释性与高精度的模拟电路设计者使用。
模拟-混合信号（AMS）电路具有高度非线性且处理连续真实信号，使其比数字模块更难通过数据驱动的AI建模。为弥合结构化设计数据（如器件尺寸、偏置电压等）与实际性能之间的差距，我们提出一种因果推断框架：首先从SPICE仿真数据中发现有向无环图（DAG），然后通过平均处理效应（ATE）估计量化参数影响。该方法生成人类可读的设计旋钮重要性排序和明确的‘如果…会怎样’预测，使设计师能理解尺寸与拓扑调整中的权衡。我们在TSMC 65nm工艺下三种运算放大器（OTA、望远镜式、折叠共源共栅）上评估该流程，并与基准神经网络回归器对比。所有电路中，因果模型对仿真ATE的平均绝对误差小于25%，而神经网络偏差超过80%，且经常预测错误符号。结果表明，因果AI兼具更高准确性和可解释性，为更高效、可信的AMS设计自动化铺平道路。
原文摘要 · Abstract (English)
Analog-mixed-signal (AMS) circuits are highly non-linear and operate on continuous real-world signals, making them far more difficult to model with data-driven AI than digital blocks. To close the gap between structured design data (device dimensions, bias voltages, etc.) and real-world performance, we propose a causal-inference framework that first discovers a directed-acyclic graph (DAG) from SPICE simulation data and then quantifies parameter impact through Average Treatment Effect (ATE) estimation. The approach yields human-interpretable rankings of design knobs and explicit 'what-if' predictions, enabling designers to understand trade-offs in sizing and topology. We evaluate the pipeline on three operational-amplifier families (OTA, telescopic, and folded-cascode) implemented in TSMC 65nm and benchmark it against a baseline neural-network (NN) regressor. Across all circuits the causal model reproduces simulation-based ATEs with an average absolute error of less than 25%, whereas the neural network deviates by more than 80% and frequently predicts the wrong sign. These results demonstrate that causal AI provides both higher accuracy and explainability, paving the way for more efficient, trustworthy AMS design automation.
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。