Journal
JOURNAL OF MANUFACTURING PROCESSES
Volume 64, Issue -, Pages 1336-1348Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.jmapro.2021.02.034
Keywords
Deep learning; CAD data; Machining; 3D voxel representation; Transfer learning
Categories
Funding
- program -Engineering Faculty Conversation (EFC) on Future Manufacturing from College of Engineering at Purdue University
Ask authors/readers for more resources
The manufacturing industry still relies on human labor and knowledge for Machining Process Identification (MPI), crucial for sourcing qualified suppliers and achieving efficient automated industrial logistic systems. This paper presents a novel two-step MPI system based on 3D Convolutional Neural Networks and transfer learning, demonstrating high accuracy in identifying manufacturability and manufacturing processes.
Today?s manufacturing industry still requires human labor and knowledge for Machining Process Identification (MPI). Before manufacturing a part, engineers need to judge the manufacturability and identify the machining processes according to CAD model, and then the customer needs to source for qualified suppliers based on the identified machining processes. In order to realize an efficient automated industrial logistic system, developing a competent Machining Process Identification system becomes important. In this paper, a novel two-step MPI system is presented based on 3D Convolutional Neural Networks (CNN) and transfer learning. The proposed system admits triangularly tessellated surface (STL) models as inputs and outputs the manufacturability of the CAD design and machining process labels (e.g., milling, turning) as the results of classification from the neural networks. Computer-synthesized workpiece models are utilized in training the networks. In addition to the MPI system, a pre-trained framework was developed for future applications in related fields. The MPI system shows more than 98% accuracy in identifying manufacturability of a part and about 98% accuracy in identifying the manufacturing processes of synthesized workpiece models which validates the robustness of the model.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available