Automated HEMT Model Construction from Datasheets via Multi-Modal Intelligence and Prior-Knowledge-Free Optimization

2025-07-28

AI Summary

Conventional high-frequency HEMT device modeling suffers from incomplete datasheet information and labor-intensive, non-automatable parameter extraction. Method: This paper proposes an end-to-end multimodal AI framework integrating OCR and large language models for PDF datasheet content understanding and curve digitization, coupled with an adaptive iterative focusing optimization algorithm (IF-TPE)—a black-box optimization method based on tree-structured Parzen estimators—to achieve accurate fitting in high-dimensional, sparse parameter spaces without prior knowledge. Contribution/Results: The framework enables fully automated construction of simulation-ready ASM-HEMT SPICE models directly from raw PDF datasheets—the first such approach. Validated on 17 commercial HEMT devices, the generated models exhibit excellent agreement with measured DC and RF characteristics, significantly improving modeling efficiency, accuracy, and reproducibility.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Sampling/Simulation-based Search
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Parameter extraction for industry-standard device models like ASM-HEMT is crucial in circuit design workflows. However, many manufacturers do not provide such models, leaving users to build them using only datasheets. Unfortunately, datasheets lack sufficient information for standard step-by-step extraction. Moreover, manual data extraction from datasheets is highly time-consuming, and the absence of a fully automated method forces engineers to perform tedious manual work. To address this challenge, this paper introduces a novel, end-to-end framework that fully automates the generation of simulation-ready ASM-HEMT SPICE models directly from PDF datasheets. Our framework is founded on two core innovations: 1) a multi-modal AI pipeline that integrates computer vision with a large language model (LLM) to robustly parse heterogeneous datasheet layouts and digitize characteristic curves, and 2) a novel Iterative-Focusing Tree-structured Parzen Estimator (IF-TPE) optimization algorithm is specifically designed for device parameter extraction under the high-dimensional, sparse-data condition by adaptively refining the parameter search space. Experimental validation on a diverse set of 17 commercial HEMT devices from 10 manufacturers confirms the framework's accuracy and robustness. The generated models demonstrate excellent agreement with published DC and RF characteristics. As the first fully automated workflow of its kind, our proposed solution offers a transformative approach to device modeling, poised to significantly accelerate the circuit design cycle by eliminating the need for manual parameter extraction.

Problem

• Automates HEMT model construction from PDF datasheets
• Eliminates manual parameter extraction in circuit design
• Handles sparse data in high-dimensional parameter optimization

Innovation

• Multi-modal AI pipeline for datasheet parsing
• IF-TPE algorithm for parameter extraction
• End-to-end automated ASM-HEMT model generation