Using Voxelisation-Based Data Analysis Techniques for Porosity Prediction in Metal Additive Manufacturing

被引:0
|
作者
George, Abraham [1 ]
Mota, Marco Trevisan [1 ]
Maguire, Conor [1 ]
O'Callaghan, Ciara [1 ]
Roche, Kevin [1 ]
Papakostas, Nikolaos [1 ]
机构
[1] Univ Coll Dublin, Sch Mech & Mat Engn, Lab Adv Mfg Simulat & Robot, Dublin D04 V1W8, Ireland
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 11期
基金
爱尔兰科学基金会;
关键词
additive manufacturing; voxelisation; porosity; in-process monitoring; machine learning; POWDER-BED FUSION; LASER; CLASSIFICATION; OPTIMIZATION; BEHAVIOR;
D O I
10.3390/app14114367
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Featured Application In-process porosity prediction in metal additive manufacturing.Abstract Additive manufacturing workflows generate large amounts of data in each phase, which can be very useful for monitoring process performance and predicting the quality of the finished part if used correctly. In this paper, a framework is presented that utilises machine learning methods to predict porosity defects in printed parts. Data from process settings, in-process sensor readings, and post-process computed tomography scans are first aligned and discretised using a voxelisation approach to create a training dataset. A multi-step classification system is then proposed to classify the presence and type of porosity in a voxel, which can then be utilised to find the distribution of porosity within the build volume. Titanium parts were printed using a laser powder bed fusion system. Two discretisation techniques based on voxelisation were utilised: a defect-centric and a uniform discretisation method. Different machine learning models, feature sets, and other parameters were also tested. Promising results were achieved in identifying porous voxels; however, the accuracy of the classification requires improvement before being applied industrially. The potential of the voxelisation-based framework for this application and its ability to incorporate data from different stages of the additive manufacturing workflow as well as different machine learning models was clearly demonstrated.
引用
收藏
页数:21
相关论文
共 50 条
  • [31] Simplified Prediction of Melt Pool Shape in Metal Additive Manufacturing Using Maraging Steel
    Fukunaga, Taiichiro
    Narahara, Hiroyuki
    INTERNATIONAL JOURNAL OF AUTOMATION TECHNOLOGY, 2022, 16 (05) : 609 - 614
  • [32] Automated Process State Identification for Metal Additive Manufacturing based on Power Data
    Lu, Zedi
    Peng, Tao
    Chen, Wei
    2018 IEEE 14TH INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING (CASE), 2018, : 1587 - 1592
  • [33] Mechanistic data-driven prediction of as-built mechanical properties in metal additive manufacturing
    Xiaoyu Xie
    Jennifer Bennett
    Sourav Saha
    Ye Lu
    Jian Cao
    Wing Kam Liu
    Zhengtao Gan
    npj Computational Materials, 7
  • [34] Mechanistic data-driven prediction of as-built mechanical properties in metal additive manufacturing
    Xie, Xiaoyu
    Bennett, Jennifer
    Saha, Sourav
    Lu, Ye
    Cao, Jian
    Liu, Wing Kam
    Gan, Zhengtao
    NPJ COMPUTATIONAL MATERIALS, 2021, 7 (01)
  • [35] Metal Additive Manufacturing and Its Post-Processing Techniques
    Wang, Hao
    Fuh, Jerry Ying Hsi
    JOURNAL OF MANUFACTURING AND MATERIALS PROCESSING, 2023, 7 (01):
  • [36] Development of Additive Strategy Generator for Metal Additive Manufacturing Build Prediction Using Laser Path Generation Algorithm
    Kim, Byungsu
    Lee, Seungyup
    Sung, Jihyun
    Lee, Jaewook
    Lee, Mincheol
    INTERNATIONAL JOURNAL OF PRECISION ENGINEERING AND MANUFACTURING, 2023, 24 (11) : 2113 - 2131
  • [37] Development of Additive Strategy Generator for Metal Additive Manufacturing Build Prediction Using Laser Path Generation Algorithm
    Byungsu Kim
    Seungyup Lee
    Jihyun Sung
    Jaewook Lee
    Mincheol Lee
    International Journal of Precision Engineering and Manufacturing, 2023, 24 : 2113 - 2131
  • [38] Damage mechanics-based fatigue life prediction for additive manufacturing metal materials
    Hong H.
    Zhan Z.
    Wang J.
    Beijing Hangkong Hangtian Daxue Xuebao/Journal of Beijing University of Aeronautics and Astronautics, 2022, 48 (06): : 950 - 956
  • [39] In-situ porosity prediction in metal powder bed fusion additive manufacturing using spectral emissions: a prior-guided machine learning approach
    Atwya, Mohamed
    Panoutsos, George
    JOURNAL OF INTELLIGENT MANUFACTURING, 2024, 35 (06) : 2719 - 2742
  • [40] Standard method for microCT-based additive manufacturing quality control 1: Porosity analysis
    du Plessis, Anton
    Sperling, Philip
    Beerlink, Andre
    Tshabalala, Lerato
    Hoosain, Shaik
    Mathe, Ntombi
    le Roux, Stephan G.
    METHODSX, 2018, 5 : 1102 - 1110