Machining feature recognition based on deep neural networks to support tight integration with 3D CAD systems

Recently, studies applying deep learning technology to recognize the machining feature of three-dimensional (3D) computer-aided design (CAD) models are increasing. Since the direct utilization of boundary representation (B-rep) models as input data for neural networks in terms of data structure is difficult, B-rep models are generally converted into a voxel, mesh, or point cloud model and used as inputs for neural networks for the application of 3D models to deep learning. However, the model’s resolution decreases during the format conversion of 3D models, causing the loss of some features or difficulties in identifying areas of the converted model corresponding to a specific face of the B-rep model. To solve these problems, this study proposes a method enabling tight integration of a 3D CAD system with a deep neural network using feature descriptors as inputs to neural networks for recognizing machining features. Feature descriptor denotes an explicit representation of the main property items of a face. We constructed 2236 data to train and evaluate the deep neural network. Of these, 1430 were used for training the deep neural network, and 358 were used for validation. And 448 were used to evaluate the performance of the trained deep neural network. In addition, we conducted an experiment to recognize a total of 17 types (16 types of machining features and a non-feature) from the B-rep model, and the types for all 75 test cases were successfully recognized.

Graph Representation of 3D CAD Models for Machining Feature Recognition With Deep Learning

In this paper, the application of deep learning methods to the task of machining feature recognition in CAD models is studied. Four contributions are made: 1. An automatic method to generate large datasets of 3D CAD models is proposed, where each model contains multiple machining features with face labels. 2. A concise and informative graph representation for 3D CAD models is presented. This is shown to be applicable to graph neural networks. 3. The graph representation is compared with voxels on their performance of training deep neural networks to segment 3D CAD models. 4. Experiments are also conducted to evaluate the effectiveness of graph-based deep learning for interacting feature recognition. Results show that the proposed graph representation is a more efficient representation of 3D CAD models than voxels for deep learning. It is also shown that graph neural networks can be used to recognize individual features on the model and also identify complex interacting features.