Special lssues
Table of Content

Data-driven Additive Manufacturing: Methodology, Fabrication, and Applications

Submission Deadline: 31 May 2024 Submit to Special Issue

Guest Editors

Prof. Hung Nguyen Xuan, Ho Chi Minh City University of Technology (HUTECH), VIETNAM
Prof. Lei Chen, University of Michigan-Dearborn, USA
Prof. Jonathan Tran, RMIT University, AUSTRALIA
Dr. Zhuo Wang, University of Michigan-Ann Arbor, USA

Summary

Additive manufacturing (AM) or 3D printing with potential benefits to the automation, low cost, rapid prototyping, and customizability can greatly outperform conventional manufacturing technologies that suffer from time-consuming and labor-intensive problems during operation. However, the complex underlying physics of AM processes also brings challenges in understanding the relationship between process parameters and quality of the product, thereby hindering industrial applications that harness the full potential of AM.


With the increasing availability of digital AM data and rapid development of data-driven modeling techniques, especially machine learning (ML), data-driven AM modeling is emerging as an effective approach towards this end. It allows for automatic exploration of pattern and trend in the data, construction of quantitative process-structure-property (P-S-P) relationship over the parameter space and prediction at unseen points without having to perform new physical modeling or experiments. In this way, data-driven methods can reduce the expensive experiments and time-consuming physics-simulations to create the P-S-P database which can quantify the quality of the product and inform the design of materials and manufacturing processes to optimize the quality of the product. In addition, data-driven approaches, typically off-line trained, can be used to achieve real-time and online prediction of AM processes that can be used as the backbone to real-time control or optimize the process parameters for smart AM manufacturing. Here, we just name two applications of data-driven approaches which have potential to benefit AM technologies from many aspects. Therefore, this special issue aims to highlight data-driven modeling of additive manufacturing, including development of novel data-driven approaches, application of existing data-driven approaches and the hybrid to promote the AM technologies. This special issue will be a collection of peer-reviewed contributions that present original breakthrough research, comprehensive reviews, perspectives, or highlights to advance the frontier of data-driven modeling of additive manufacturing.


Contributed articles are sought in the following areas (not limited):

· Advances in development of novel data-driven approaches for additive manufacturing

· Advances in data-driven modeling of process-structure-property relation for additive manufacturing

· Advances in data-driven material selection and design for additive manufacturing

· Advances in data-driven modeling of topology optimization for additive manufacturing

· Advances in big (sensor) data analytics using data-driven modeling for smart additive manufacturing

· Advances in data collection, denoising and sorting for training of additive manufacturing 


Keywords

Data-driven, Additive manufacturing, Process-structure-property, Topology optimization, Data collection and sorting

Published Papers


  • Open Access

    ARTICLE

    Advancing Wound Filling Extraction on 3D Faces: An Auto-Segmentation and Wound Face Regeneration Approach

    Duong Q. Nguyen, Thinh D. Le, Phuong D. Nguyen, Nga T. K. Le, H. Nguyen-Xuan
    CMES-Computer Modeling in Engineering & Sciences, Vol.139, No.2, pp. 2197-2214, 2024, DOI:10.32604/cmes.2023.043992
    (This article belongs to this Special Issue: Data-driven Additive Manufacturing: Methodology, Fabrication, and Applications )
    Abstract Facial wound segmentation plays a crucial role in preoperative planning and optimizing patient outcomes in various medical applications. In this paper, we propose an efficient approach for automating 3D facial wound segmentation using a two-stream graph convolutional network. Our method leverages the Cir3D-FaIR dataset and addresses the challenge of data imbalance through extensive experimentation with different loss functions. To achieve accurate segmentation, we conducted thorough experiments and selected a high-performing model from the trained models. The selected model demonstrates exceptional segmentation performance for complex 3D facial wounds. Furthermore, based on the segmentation model, we propose an improved approach for extracting… More >

    Graphic Abstract

    Advancing Wound Filling Extraction on 3D Faces: An Auto-Segmentation and Wound Face Regeneration Approach

Share Link