Awesome AI4CAD Hub Papers · Datasets · Projects
← Back to papers

CAD-feature enhanced machine learning for manufacturing effort estimation on sheet metal bending parts

arXiv 2026 58.9 method

TLDR

Hybrid approach enriches B-rep graphs with manufacturing features for sheet metal bending effort estimation, validated on synthetic and real industrial data.

Reasoning

The paper's strength lies in its hybrid method combining rule-based feature recognition with graph ML, and its real-world validation on industrial bending time data. Weakness is the narrow focus on sheet metal bending, limiting generalizability to other manufacturing domains.

Read-first score

Read-first score 58.9, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 54.

Methodology quality 25%
100

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

Recency 8%
100

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

Reproducibility 25%
46

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

FrontierMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 41.

Keyword Scores

B-Rep
10
boundary representation
10
computer-aided design
9
AI for CAD
8
neural CAD
5
parametric CAD
3
generative CAD
2
CAD program
2
constructive solid geometry
1
CSG
1
sketch extrusion
1
CAD generation
1
CAD reconstruction
1
text-to-CAD
0
image-to-CAD
0
point cloud to CAD
0

Deep Analysis

Innovations

  • Hybrid approach enriching B-rep attributed adjacency graphs with manufacturing features recognized by a rule-based module
  • Integration of process-specific features (bend characteristics, flange lengths, surface roles) as node attributes to focus learning on relevant geometric patterns
  • Validation on a real-world industrial dataset with measured bending times, one of the first such validations on genuine production data

Methodology

The method enriches B-rep attributed adjacency graphs with manufacturing features (bend characteristics, flange lengths, surface roles) recognized by a rule-based module, then applies graph-based machine learning for manufacturability prediction and effort estimation. It is evaluated on a large-scale synthetic benchmark and a real-world industrial sheet metal bending dataset.

Key Results

Combining domain knowledge with graph-based learning improves prediction accuracy on both a synthetic manufacturability benchmark and a real-world industrial dataset with measured bending times.

Tags

CV