Technology Category
Machine Learning: Feature Construction/ReformulationKnowledge Representation and Reasoning: Computational Complexity of ReasoningCognitive Modeling & Cognitive Systems: Computational Creativity
BenDFM: A taxonomy and synthetic CAD dataset for manufacturability assessment in sheet metal bending
🤖 AI Summary
This study addresses the challenge of accurately assessing the manufacturability and complexity of CAD models in sheet metal bending during early design stages, a task hindered by the absence of a standardized definition of manufacturability and high-quality datasets. To bridge this gap, the work proposes the first manufacturability classification framework tailored specifically for sheet metal bending and introduces BenDFM, a synthetic CAD dataset comprising 20,000 parts annotated with binary feasibility labels and multidimensional process-related attributes. The dataset is generated through process-aware bending simulation and supports both folded and unfolded geometric representations. Experimental results using graph neural networks to model surface relationships demonstrate the superiority of graph-based representations for manufacturability prediction and reveal that metrics dependent on specific manufacturing configurations present greater predictive challenges.
Technology Category
Application Category
📝 Abstract
Predicting the manufacturability of CAD designs early, in terms of both feasibility and required effort, is a key goal of Design for Manufacturing (DFM). Despite advances in deep learning for CAD and its widespread use in manufacturing process selection, learning-based approaches for predicting manufacturability within a specific process remain limited. Two key challenges limit progress: inconsistency across prior work in how manufacturability is defined and consequently in the associated learning targets, and a scarcity of suitable datasets. Existing labels vary significantly: they may reflect intrinsic design constraints or depend on specific manufacturing capabilities (such as available tools), and they range from discrete feasibility checks to continuous complexity measures. Furthermore, industrial datasets typically contain only manufacturable parts, offering little signal for infeasible cases, while existing synthetic datasets focus on simple geometries and subtractive processes. To address these gaps, we propose a taxonomy of manufacturability metrics along the axes of configuration dependence and measurement type, allowing clearer scoping of generalizability and learning objectives. Next, we introduce BenDFM, the first synthetic dataset for manufacturability assessment in sheet metal bending. BenDFM contains 20,000 parts, both manufacturable and unmanufacturable, generated with process-aware bending simulations, providing both folded and unfolded geometries and multiple manufacturability labels across the taxonomy, enabling systematic study of previously unexplored learning-based DFM challenges. We benchmark two state-of-the-art 3D learning architectures on BenDFM, showing that graph-based representations that capture relationships between part surfaces achieve better accuracy, and that predicting metrics that depend on specific manufacturing setups remains more challenging.
Problem
Research questions and friction points this paper is trying to address.
manufacturability assessment
sheet metal bending
Design for Manufacturing
CAD dataset
feasibility prediction
Innovation
Methods, ideas, or system contributions that make the work stand out.
manufacturability assessment
sheet metal bending
synthetic CAD dataset
DFM taxonomy
graph-based 3D learning
🔎 Similar Papers
No similar papers found.
