A Layer-Wise Surface Deformation Defect Detection by Convolutional Neural Networks in Laser Powder-Bed Fusion Images

被引:14
|
作者
Ansari, Muhammad Ayub [1 ]
Crampton, Andrew [1 ]
Parkinson, Simon [1 ]
机构
[1] Univ Huddersfield, Sch Comp & Engn, Huddersfield HD1 3DH, W Yorkshire, England
关键词
surface deformation; LPBF; metal additive manufacturing; convolutional neural network; machine learning; deep learning; RESIDUAL-STRESS; MECHANICAL-PROPERTIES; MICROSTRUCTURE; CLASSIFICATION; TEMPERATURE; DISTORTION; DESIGN; WIRE;
D O I
10.3390/ma15207166
中图分类号
O64 [物理化学(理论化学)、化学物理学];
学科分类号
070304 ; 081704 ;
摘要
Surface deformation is a multi-factor, laser powder-bed fusion (LPBF) defect that cannot be avoided entirely using current monitoring systems. Distortion and warping, if left unchecked, can compromise the mechanical and physical properties resulting in a build with an undesired geometry. Increasing dwell time, pre-heating the substrate, and selecting appropriate values for the printing parameters are common ways to combat surface deformation. However, the absence of real-time detection and correction of surface deformation is a crucial LPBF problem. In this work, we propose a novel approach to identifying surface deformation problems from powder-bed images in real time by employing a convolutional neural network-based solution. Identifying surface deformation from powder-bed images is a significant step toward real-time monitoring of LPBF. Thirteen bars, with overhangs, were printed to simulate surface deformation defects naturally. The carefully chosen geometric design overcomes problems relating to unlabelled data by providing both normal and defective examples for the model to train. To improve the quality and robustness of the model, we employed several deep learning techniques such as data augmentation and various model evaluation criteria. Our model is 99% accurate in identifying the surface distortion from powder-bed images.
引用
收藏
页数:20
相关论文
共 50 条
  • [21] Convolutional neural networks for melt depth prediction and visualization in laser powder bed fusion
    Ogoke, Francis
    Lee, William
    Kao, Ning-Yu
    Myers, Alexander
    Beuth, Jack
    Malen, Jonathan
    Barati Farimani, Amir
    INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2023, 129 (7-8): : 3047 - 3062
  • [22] Convolutional neural networks for melt depth prediction and visualization in laser powder bed fusion
    Francis Ogoke
    William Lee
    Ning-Yu Kao
    Alexander Myers
    Jack Beuth
    Jonathan Malen
    Amir Barati Farimani
    The International Journal of Advanced Manufacturing Technology, 2023, 129 : 3047 - 3062
  • [23] Layer-wise engineering of grain orientation (LEGO) in laser powder bed fusion of stainless steel 316L
    Sofinowski, Karl A.
    Raman, Sudharshan
    Wang, Xiaogang
    Gaskey, Bernard
    Seita, Matteo
    ADDITIVE MANUFACTURING, 2021, 38
  • [24] Lessons learned in the design of reference fiducials for layer-wise analysis of test coupons made by laser powder bed fusion
    Ferrucci, Massimiliano
    Craeghs, Tom
    Cornelissen, Sven
    Pavan, Michele
    Dewulf, Wim
    Donmez, Alkan
    ADDITIVE MANUFACTURING, 2021, 42
  • [25] Micron-Level Layer-Wise Surface Profilometry to Detect Porosity Defects in Powder Bed Fusion of Inconel 718
    Barrett, Chris
    Macdonald, Eric
    Conner, Brett
    Persi, Fred
    JOM, 2018, 70 (09) : 1844 - 1852
  • [26] Micron-Level Layer-Wise Surface Profilometry to Detect Porosity Defects in Powder Bed Fusion of Inconel 718
    Chris Barrett
    Eric MacDonald
    Brett Conner
    Fred Persi
    JOM, 2018, 70 : 1844 - 1852
  • [27] On the measurement of effective powder layer thickness in laser powder-bed fusion additive manufacturing of metals
    Yahya Mahmoodkhani
    Usman Ali
    Shahriar Imani Shahabad
    Adhitan Rani Kasinathan
    Reza Esmaeilizadeh
    Ali Keshavarzkermani
    Ehsan Marzbanrad
    Ehsan Toyserkani
    Progress in Additive Manufacturing, 2019, 4 : 109 - 116
  • [28] Optimization Based Layer-Wise Pruning Threshold Method for Accelerating Convolutional Neural Networks
    Ding, Yunlong
    Chen, Di-Rong
    MATHEMATICS, 2023, 11 (15)
  • [29] Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagation
    Iwana, Brian Kenji
    Kuroki, Ryohei
    Uchida, Seiichi
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2019, : 4176 - 4185
  • [30] Forward layer-wise learning of convolutional neural networks through separation index maximizing
    Karimi, Ali
    Kalhor, Ahmad
    Tabrizi, Melika Sadeghi
    SCIENTIFIC REPORTS, 2024, 14 (01)