Context-Aware Mapping of 2D Drawing Annotations to 3D CAD Features Using LLM-Assisted Reasoning for Manufacturing Automation

2026-02-20

AI Summary

This work addresses the challenge of reliably associating 2D engineering drawing annotations—such as geometric dimensioning and tolerancing (GD&T) and datum references—with corresponding geometric features in 3D CAD models, a task often hindered by contextual ambiguity, repetitive patterns, and non-traceable decision-making. The authors propose a deterministic, rule-first, context-aware mapping framework that initially performs interpretable matching through semantic enrichment, type compatibility, tolerance-aware alignment, and engineering heuristics. For ambiguous cases, a multimodal-constrained large language model (LLM) assists reasoning while preserving a human-in-the-loop verification mechanism. By integrating deterministic engineering rules with constrained LLM inference, the approach effectively resolves complex ambiguities while maintaining transparency and traceability. Evaluated on 20 real-world CAD–drawing pairs, the method achieves 83.67% precision, 90.46% recall, and an F1 score of 86.29%, with ablation studies confirming the contribution of each component.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Intelligent Robots: Localization, Mapping, and Navigation

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Manufacturing automation in process planning, inspection planning, and digital-thread integration depends on a unified specification that binds the geometric features of a 3D CAD model to the geometric dimensioning and tolerancing (GD&T) callouts, datum definitions, and surface requirements carried by the corresponding 2D engineering drawing. Although Model-Based Definition (MBD) allows such specifications to be embedded directly in 3D models, 2D drawings remain the primary carrier of manufacturing intent in automotive, aerospace, shipbuilding, and heavy-machinery industries. Correctly linking drawing annotations to the corresponding 3D features is difficult because of contextual ambiguity, repeated feature patterns, and the need for transparent and traceable decisions. This paper presents a deterministic-first, context-aware framework that maps 2D drawing entities to 3D CAD features to produce a unified manufacturing specification. Drawing callouts are first semantically enriched and then scored against candidate features using an interpretable metric that combines type compatibility, tolerance-aware dimensional agreement, and conservative context consistency, along with engineering-domain heuristics. When deterministic scoring cannot resolve an ambiguity, the system escalates to multimodal and constrained large-language-model reasoning, followed by a single human-in-the-loop (HITL) review step. Experiments on 20 real CAD-drawing pairs achieve a mean precision of 83.67%, recall of 90.46%, and F1 score of 86.29%. An ablation study shows that each pipeline component contributes to overall accuracy, with the full system outperforming all reduced variants. By prioritizing deterministic rules, clear decision tracking, and retaining unresolved cases for human review, the framework provides a practical foundation for downstream manufacturing automation in real-world industrial environments.

Problem

• 2D-to-3D mapping
• engineering drawing annotation
• CAD feature association
• geometric dimensioning and tolerancing
• manufacturing automation

Innovation

• context-aware mapping
• LLM-assisted reasoning
• deterministic-first framework
• GD&T annotation linking
• human-in-the-loop (HITL)