DeepMill: Neural Accessibility Learning for Subtractive Manufacturing

2025-02-10

AI Summary

In subtractive manufacturing, geometric accessibility analysis is computationally expensive and poorly scalable; existing deep learning approaches neglect tool geometry constraints and exhibit limited generalization. To address these issues, this paper proposes the first tool-aware neural machinability analysis framework. Its core is a dual-head octree convolutional neural network (O-CNN), which implicitly models tool–workpiece geometric interactions to jointly learn local accessibility and global occlusion features. We introduce a novel synthetic dataset of inaccessible regions and occlusions tailored for CAD and freeform surface models, enabling the first systematic application of geometric deep learning to 3D machinability prediction. Experiments demonstrate state-of-the-art performance: 94.7% accuracy in inaccessible region prediction, 88.7% in occlusion identification, and an average inference time of only 0.04 seconds per model—significantly outperforming both conventional methods and prior deep learning solutions.

Technology Category

• Machine Learning: Hardware-aware ML
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Computer Vision: 3D Computer Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Manufacturability is vital for product design and production, with accessibility being a key element, especially in subtractive manufacturing. Traditional methods for geometric accessibility analysis are time-consuming and struggle with scalability, while existing deep learning approaches in manufacturability analysis often neglect geometric challenges in accessibility and are limited to specific model types. In this paper, we introduce DeepMill, the first neural framework designed to accurately and efficiently predict inaccessible and occlusion regions under varying machining tool parameters, applicable to both CAD and freeform models. To address the challenges posed by cutter collisions and the lack of extensive training datasets, we construct a cutter-aware dual-head octree-based convolutional neural network (O-CNN) and generate an inaccessible and occlusion regions analysis dataset with a variety of cutter sizes for network training. Experiments demonstrate that DeepMill achieves 94.7% accuracy in predicting inaccessible regions and 88.7% accuracy in identifying occlusion regions, with an average processing time of 0.04 seconds for complex geometries. Based on the outcomes, DeepMill implicitly captures both local and global geometric features, as well as the complex interactions between cutters and intricate 3D models.

Problem

• Neural accessibility learning
• Subtractive manufacturing challenges
• Geometric accessibility analysis

Innovation

• Neural framework for accessibility prediction
• Cutter-aware dual-head octree-based CNN
• Generates dataset for occlusion analysis