Geometry Based Machining Feature Retrieval with Inductive Transfer Learning

TL;DR

This paper presents a method for retrieving machining features from CAD models using geometric features and inductive transfer learning, significantly improving feature matching accuracy in manufacturing contexts.

Contribution

The study introduces a novel approach combining geometric feature extraction with inductive transfer learning and deep neural networks for improved machining feature retrieval.

Findings

Enhanced retrieval accuracy with deep CNN and spatial pyramid pooling

Effective capture of geometrical elements from CAD models

Significant performance improvement over traditional methods

Abstract

Manufacturing industries have widely adopted the reuse of machine parts as a method to reduce costs and as a sustainable manufacturing practice. Identification of reusable features from the design of the parts and finding their similar features from the database is an important part of this process. In this project, with the help of fully convolutional geometric features, we are able to extract and learn the high level semantic features from CAD models with inductive transfer learning. The extracted features are then compared with that of other CAD models from the database using Frobenius norm and identical features are retrieved. Later we passed the extracted features to a deep convolutional neural network with a spatial pyramid pooling layer and the performance of the feature retrieval increased significantly. It was evident from the results that the model could effectively capture the geometrical elements from machining features.