Problem
Research questions and friction points this paper is trying to address.
manufacturability analysis
sheet metal bending
CAD models
manufacturing effort estimation
process-specific semantics
CAD-feature enhanced machine learning for manufacturing effort estimation on sheet metal bending parts
🤖 AI Summary
This work addresses the limitation of purely geometric representations of sheet metal parts, which lack manufacturing semantics and thus struggle to accurately predict bend manufacturability and processing time. The authors propose a novel approach that integrates rule-driven manufacturing feature recognition with graph neural networks. Specifically, a rule-based module first extracts key manufacturing features—such as bend attributes, flange lengths, and face roles—and embeds them as semantic attributes into a B-rep adjacency graph. A graph neural network then leverages this enriched representation to predict manufacturing time. By uniquely combining domain-specific manufacturing knowledge with geometric graph structures, the method significantly improves prediction accuracy on both a large-scale synthetic dataset and real-world industrial bending time data, demonstrating its effectiveness and practical deployment potential in manufacturing evaluation.
📝 Abstract
Graph-based machine learning has emerged as a promising approach for manufacturability analysis by learning directly from CAD models represented as Boundary Representations (B-reps), exploiting both surface geometry and topological connectivity. However, purely geometric representations often lack the process-specific semantics required for accurate manufacturability prediction: many manufacturing factors, such as surface roles or bend intent, are not explicitly encoded in shape alone and are difficult for data-driven models to infer reliably. We propose a hybrid approach that addresses this challenge by enriching B-rep attributed adjacency graphs with manufacturing features recognized through a rule-based module. Applied to sheet metal bending, recognized features, such as bend characteristics, flange lengths, and surface roles are integrated as node attributes, concentrating the learning signal on process-relevant geometric patterns. Experiments on both a large-scale synthetic manufacturability benchmark and a real-world industrial dataset with measured bending times, one of the first such validations on genuine production data, demonstrate that combining domain knowledge with graph-based learning improves prediction accuracy across both tasks. The results demonstrate that hybrid modeling offers a feasible and effective path toward deployable tools for manufacturability assessment and effort estimation in industrial CAD environments.
Innovation
Methods, ideas, or system contributions that make the work stand out.
CAD-feature enrichment
graph-based machine learning
manufacturability analysis
sheet metal bending
hybrid modeling
🔎 Similar Papers
No similar papers found.
