DeepMill: Neural Accessibility Learning for Subtractive Manufacturing

TL;DR

DeepMill is a neural framework that efficiently predicts inaccessible and occlusion regions in subtractive manufacturing, improving accuracy and speed over traditional methods by leveraging a cutter-aware neural network trained on a specialized dataset.

Contribution

This paper introduces DeepMill, the first neural network model capable of predicting accessibility issues in manufacturing models with high accuracy and efficiency, addressing previous limitations.

Findings

Achieves 94.7% accuracy in inaccessible region prediction

Achieves 88.7% accuracy in occlusion region prediction

Processes complex geometries in 0.04 seconds on average

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.