cs.CEFeb 20, 2026

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

Authors: Muhammad Tayyab Khan, Lequn Chen, Wenhe Feng, Seung Ki Moon

Organizations: Singapore Institute of Manufacturing Technology (SIMTech), A*STAR, Singapore 636732, Republic of Singapore · School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore 639798 · Advanced Remanufacturing and Technology Centre (ARTC), A*STAR, Singapore 637143, Republic of Singapore

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

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.

Figures & tables

Fig. 1: Overview of the deterministic-first, context-aware fusion pipeline for mapping 2D drawing entities to 3D CAD features.
Fig. 2: Structure of the unified manufacturing specification binding 2D drawing constraints to 3D CAD features with mapping metadata and provenance.
CharacteristicMinMaxMean
3D features per part295.1
2D entities per part2135.6
Repeated/patterned features062.0
GD&T annotations per part010.05
TABLE I: Dataset Characterization: Complexity Statistics Across 20 CAD–Drawing Pairs.
Fig. 3: Representative result of the proposed framework. (a) 3D CAD model with recognized features (F1–F4). (b) Corresponding 2D engineering drawing with extracted entities (E1–E4). (c) Unified mapping showing resolved correspondences with mapping method, source, and confidence.
MetricMeanStdMinMax
Mapping Precision0.83670.16980.501.0
Mapping Recall0.90460.11650.57141.0
Mapping F1 score0.86290.13670.57141.0
Exact Match Rate0.79190.19960.401.0
Partial Match Rate0.90250.12270.57141.0
Inference Time (s)54.9420.6530.05104.63
TABLE II: Aggregated Mapping Accuracy, Robustness, and Inference Time Statistics Across 20 CAD–Drawing Pairs.
VariantPRF1
Deterministic only0.50880.34810.4057
No engineering heuristics0.44230.88670.5470
No LLM escalation0.72220.54170.6066
No context scoring ( wc=0w_{c}{=}0 )0.64950.90930.7432
Full pipeline (proposed)0.83670.90460.8629
TABLE III: Ablation Study: Impact of Removing Individual Pipeline Components on Mapping Performance (Mean Across 20 Parts).
More in this topic

Industrial Automation

See all 17 papers

Explore similar work

CardsList
Aug 25, 2026

Design-to-Plan: A Large Language Model-Based Multi-Agent Framework for Manufacturing Process Planning from 3D CAD Models and 2D Engineering Drawings

Manufacturing process planning transforms heterogeneous design information into coherent manufacturing decisions. However, existing approaches focus on isolated subtasks, such as feature recognition, drawing interpretation, or tool selection, and struggle to support the full reasoning chain from design artifacts to process plans. This is critical when planning must interpret 3D CAD models, 2D engineering drawings, materials, and domain-specific rules. To address this gap, this paper presents Design-to-Plan, a large language model (LLM)-based multi-agent framework for end-to-end manufacturing process planning. An orchestrator coordinates specialized agents for 3D feature recognition, 2D drawing analysis, 2D-3D context fusion, knowledge retrieval, process sequencing, tool selection, and report generation. Rather than using LLMs as standalone text generators, the framework deploys them as reasoning agents that interact with deterministic modules and knowledge sources to produce consistent and traceable decisions. In this hybrid design, deterministic modules and specialized agents extract structured information from CAD and drawing inputs, while LLM agents perform context-aware reasoning, retrieve manufacturing rules, resolve conflicts, and generate planning outputs. The framework is evaluated using 300 benchmark cases across three downstream ReAct-enabled agents, plus separate evaluations of CAD feature recognition, drawing analysis, and 2D-3D context fusion. The parallel architecture achieves 100% success across downstream agents, Tool F1 scores of 95.9%-97.6%, 90% source detection accuracy in conflict analysis, and a 60%-68% reduction in token usage for key planning tasks. Results show that structured LLM-based multi-agent coordination can bridge design representations and manufacturing knowledge, enabling scalable, efficient, and traceable design-to-plan automation.

Muhammad Tayyab Khan, Lequn Chen, Wenhe Feng +1

Singapore Institute of Manufacturing Technology (SIMTech), Agency for Science, Technology and Research (A*STAR), 5 CleanTech Loop, #01-01 CleanTech Two Block B, Singapore 636732, Republic of Singapore · School of Mechanical and Aerospace Engineering, Nanyang Technological University, 639798, Singapore · Advanced Remanufacturing and Technology Centre (ARTC), Agency for Science, Technology and Research (A*STAR), 3 CleanTech Loop, #01-01 CleanTech Two, Singapore 637143, Republic of Singapore

ManufacturingMulti-Agent LLMsLLM Agent Orchestration
AskPDF
Jul 30, 2026

Drawing-Recode: Annotation Grounding for Parametric CAD Code Generation from Raster 2D CAD Drawings

Recovering Parametric CAD sequences from raster-format 2D Computer-Aided Design (CAD) drawings accumulated prior to digital transformation is important for part reproduction and manufacturing process automation. However, existing studies either process only vector drawings or are limited to specific domains, and fail to explicitly connect dimensional annotations to geometric information, limiting their use of dimensional information for 3D Parametric CAD sequences recovery. We propose Drawing-Recode, a framework that generates Parametric CAD sequences as CAD code from raster 2D CAD drawings. Drawing-Recode extracts geometric features via an image encoder and recognizes annotations through a separate text recognition module, then explicitly grounds annotations to geometric information using cross-attention and our proposed Annotation Grounding Loss (AGL). The resulting features are fed into a Large Language Model (LLM) to generate CAD code in the Structured Parametric CAD Code (SPCC) format. Experiments show that Drawing-Recode outperforms existing baselines and remains robust on scanned drawings resembling industrial conditions. We expect Drawing-Recode contributes to digitizing raster 2D CAD drawings in industrial settings and to part reproduction and manufacturing automation.

Mingi Kim, Yongjun Kim, Hyungki Kim

Department of Computer Science and Engineering Chungnam National University Daejeon, Republic of Korea

Code GenerationParametric CAD Modeling
AskPDF
Jul 6, 2026

Foundation Models for Automatic CAD Generation

Recent advances in Large Language Models (LLMs) and Vision-Language Models (VLMs) enable the automatic generation of parametric 3D designs from natural-language specifications. This chapter presents an empirical study of foundation models for automatic Computer-Aided Design (CAD) generation of mechanical parts, using a unified evaluation pipeline and a curated benchmark of 97 engineering design problems. We introduce LLMForge, a multi-model text-to-CAD framework integrating JSON-schema validation, analytic feature scoring, mesh synthesis, and multi-round iterative refinement, studied under two critique regimes. IterTracer uses a Phong-shaded ray-trace renderer with analytic visual metrics (silhouette IoU, hole visibility, edge clearance, aspect-ratio conformance) for lightweight geometry-aware feedback across rounds. IterVision replaces the analytic scorer with a VLM semantic critic (Qwen2.5-VL-72B) that evaluates rendered views via chain-of-thought visual reasoning, assessing spatial coherence and design intent. On a benchmark spanning four canonical geometry families (plates with holes and bolt circles, multi-feature boxes, flanged cylinders, and L-brackets), we evaluate seven foundation models: DeepSeek-V3.2, Qwen3-235B-A22B, Llama-3.3-70B, Gemma-3-27B, GLM-4.5, MiniMax-M2.1, and INTELLECT. Under IterTracer, the four highest-ranked models form a tight cluster (overall mean in [0.885, 0.890]) with 98.97% mesh success, showing that compact instruction-tuned models can match substantially larger systems. VLM-based critique in IterVision yields 100% watertight mesh generation on the leading model while surfacing systematic difficulty on rotationally symmetric geometries such as cylinders, where visual and semantic scoring diverge most. We discuss benchmark design, failure modes, CAD-oriented prompting, and implications for industrial workflows and scalable automated mechanical design.

J de Curtò, Victoria Guillén, I. de Zarzà

Department of Computer Applications in Science & Engineering, BARCELONA Supercomputing Center, 08034 Barcelona, Spain · Escuela T´ecnica Superior de Ingenier´ıa (ICAI), Universidad Pontificia Comillas, 28015 Madrid, Spain · Department of Artificial Intelligence, Chung-Ang University, Seoul, Republic of Korea +1

Parametric CAD ModelingLarge Vision-Language ModelsText-to-CAD Generation
AskPDF