AIMold: An Autonomous AI-based Pipeline for Complex Mold Design

arXiv 2026 46.9 method

TLDR

Introduces MoldCAD dataset and AI pipeline for automating complex injection mold design, including auxiliary components.

Reasoning

The paper's strength lies in addressing a practical industrial challenge with a curated dataset (MoldCAD) and a comprehensive pipeline. However, it lacks explicit quantitative results and does not detail the underlying AI methods, limiting the assessment of its effectiveness.

Read-first score

Read-first score 46.9, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 54.

Recency 8%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Methodology quality 25%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=dataset,result

Reproducibility 25%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=dataset

Topical relevance 42%

33.8

Uses existing LLM keyword relevance scores normalized to 0-100. AI for CAD,computer-aided design,neural CAD,generative CAD,parametric CAD,B-Rep,boundary representation,constructive solid geometry,CSG,sketch extrusion,CAD generation,CAD reconstruction,text-to-CAD,image-to-CAD,point cloud to CAD,CAD program

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 25.

Keyword Scores

AI for CAD

computer-aided design

generative CAD

CAD generation

neural CAD

CAD reconstruction

parametric CAD

CAD program

B-Rep

boundary representation

constructive solid geometry

CSG

sketch extrusion

text-to-CAD

image-to-CAD

point cloud to CAD

Deep Analysis

Innovations

MoldCAD dataset: a curated dataset of 4,934 complex CAD models paired with industry-standard mold assemblies, including upper/lower molds, parting surfaces, demolding orientations, and auxiliary components.
AIMold pipeline: an autonomous system that predicts demolding orientations, identifies necessary auxiliary components, and constructs parting surfaces to generate complete manufacturing-ready mold assemblies.

Methodology

The pipeline takes a complex CAD part as input, predicts optimal demolding orientations, identifies required auxiliary components, and constructs parting surfaces to assemble a complete mold. The method is trained and evaluated on the newly introduced MoldCAD dataset.

Key Results

The results demonstrate a promising path toward fully automated industrial mold design and contribute to the advancement of manufacturing-aware CAD generation.

Resources

Paper