A Convolutional Neural Network Approach to the Classification of Engineering Models

TL;DR

This paper introduces a CNN-based method using residual networks and Light Field Descriptor features for classifying engineering CAD models, achieving high accuracy on a new dataset called CADNET.

Contribution

It presents a novel deep learning approach for functional classification of CAD models, combining LFD features with residual CNNs and addressing class imbalance.

Findings

Best accuracy achieved with LFD-based CNN and gradient boosting.

CADNET dataset created from multiple sources for model training.

Residual network architecture improves classification performance.

Abstract

This paper presents a deep learning approach for the classification of Engineering (CAD) models using Convolutional Neural Networks (CNNs). Owing to the availability of large annotated datasets and also enough computational power in the form of GPUs, many deep learning-based solutions for object classification have been proposed of late, especially in the domain of images and graphical models. Nevertheless, very few solutions have been proposed for the task of functional classification of CAD models. Hence, for this research, CAD models have been collected from Engineering Shape Benchmark (ESB), National Design Repository (NDR) and augmented with newer models created using a modelling software to form a dataset - 'CADNET'. It is proposed to use a residual network architecture for CADNET, inspired by the popular ResNet. A weighted Light Field Descriptor (LFD) scheme is chosen as the method of feature extraction, and the generated images are fed as inputs to the CNN. The problem of class imbalance in the dataset is addressed using a class weights approach. Experiments have been conducted with other signatures such as geodesic distance etc. using deep networks as well as other network architectures on the CADNET. The LFD-based CNN approach using the proposed network architecture, along with gradient boosting yielded the best classification accuracy on CADNET.