CNCGEN improves machining plans and toolpaths from CAD models
CNCGEN: A Dataset and Framework for Machining Process Planning and Toolpath Generation from B-rep Models
Machine Learning
Summary
Making parts with a machine tool involves deciding the order of cutting steps and precisely moving the cutting tool along a path. Getting the order right does not guarantee a perfect part because each cut changes the material left to work on. The authors created CNCGEN, a large dataset and method that learns to make better cutting plans and paths by simulating each step’s effect on the material shape. They tested CNCGEN on both fake and real machine data and showed it helps produce more accurate parts with less leftover or extra cuts.
What this means in practice
- •For manufacturing engineers: Generate more accurate machining process plans and toolpaths directly from CAD models to improve part quality and reduce errors in production.
- •For cnc programmers: Use CNCGEN’s framework to assist in creating verified step-by-step operation sequences and cutting paths that account for evolving stock material states.
Authors
Xiaolei Zhou, Boyi Lin, Yuchao Feng, Jianwei Zheng
Abstract
Learning to generate machining process plans and toolpaths from B-rep CAD requires coupling discrete operation decisions with continuous tool motion as the workpiece evolves. Correctly predicting an operation sequence does not by itself ensure correct material removal, because each toolpath acts on the stock left by preceding cuts. We formulate this problem around persistent manufacturing objects: object identity determines the target of an operation, while the evolving stock state conditions the generation of its toolpath. Based on this formulation, we propose CNCGEN, a dataset and learning framework for three-axis machining. CNCGEN-Dataset contains approximately 50k geometrically verified synthetic machining flows and 800 held-out real CNC records. Each flow aligns B-rep geometry with object-referenced operations, parameterized toolpaths, intermediate stock states, and verification outcomes, enabling supervision of the correspondence between planning decisions and their geometric effects. CNCGEN generates operations and toolpaths for selected objects step by step, updating a compact machining state to guide subsequent predictions. During training, a learned surrogate verifier provides material-removal feedback that links local predictions to their geometric consequences. Experiments on synthetic and held-out real CNC records show that CNCGEN improves the resulting workpiece geometry and reduces residual material and overcut compared with adapted CNC generation baselines.