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
  • [31] Pruning Ratio Optimization with Layer-Wise Pruning Method for Accelerating Convolutional Neural Networks
    Kamma, Koji
    Inoue, Sarimu
    Wada, Toshikazu
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2022, E105D (01) : 161 - 169
  • [32] On the measurement of effective powder layer thickness in laser powder-bed fusion additive manufacturing of metals
    Mahmoodkhani, Yahya
    Ali, Usman
    Shahabad, Shahriar Imani
    Kasinathan, Adhitan Rani
    Esmaeilizadeh, Reza
    Keshavarzkermani, Ali
    Marzbanrad, Ehsan
    Toyserkani, Ehsan
    PROGRESS IN ADDITIVE MANUFACTURING, 2019, 4 (02) : 109 - 116
  • [33] A layer-wise multi-defect detection system for powder bed monitoring: Lighting strategy for imaging, adaptive segmentation and classification
    Shi, Binbin
    Chen, Zhehan
    MATERIALS & DESIGN, 2021, 210
  • [34] A layer-wise melting defects mitigation method in laser powder bed fusion process based on machine learning and fuzzy inference
    Ma, Chenguang
    Zhang, Yingjie
    ISA TRANSACTIONS, 2025, 156 : 698 - 711
  • [35] Layerwise Anomaly Detection in Laser Powder-Bed Fusion Metal Additive Manufacturing
    Mahmoudi, Mohamad
    Ezzat, Ahmed Aziz
    Elwany, Alaa
    JOURNAL OF MANUFACTURING SCIENCE AND ENGINEERING-TRANSACTIONS OF THE ASME, 2019, 141 (03):
  • [36] Convolutional Neural Networks for Steel Surface Defect Detection from Photometric Stereo Images
    Soukup, D.
    Huber-Moerk, R.
    ADVANCES IN VISUAL COMPUTING (ISVC 2014), PT 1, 2014, 8887 : 668 - 677
  • [37] A Convolutional Neural Network for Prediction of Laser Power Using Melt-Pool Images in Laser Powder Bed Fusion
    Kwon, Ohyung
    Kim, Hyung Giun
    Kim, Wonrae
    Kim, Gun-Hee
    Kim, Kangil
    IEEE ACCESS, 2020, 8 : 23255 - 23263
  • [38] Surface Formation of Sloping Features in Laser Powder-Bed Fusion by Multi-Track Multi-Layer Simulations
    Le, Trong-Nhan
    Chou, Kevin
    METALS, 2023, 13 (05)
  • [39] A deep learning framework for layer-wise porosity prediction in metal powder bed fusion using thermal signatures
    Mao, Yuwei
    Lin, Hui
    Yu, Christina Xuan
    Frye, Roger
    Beckett, Darren
    Anderson, Kevin
    Jacquemetton, Lars
    Carter, Fred
    Gao, Zhangyuan
    Liao, Wei-keng
    Choudhary, Alok N.
    Ehmann, Kornel
    Agrawal, Ankit
    JOURNAL OF INTELLIGENT MANUFACTURING, 2023, 34 (01) : 315 - 329
  • [40] A deep learning framework for layer-wise porosity prediction in metal powder bed fusion using thermal signatures
    Yuwei Mao
    Hui Lin
    Christina Xuan Yu
    Roger Frye
    Darren Beckett
    Kevin Anderson
    Lars Jacquemetton
    Fred Carter
    Zhangyuan Gao
    Wei-keng Liao
    Alok N. Choudhary
    Kornel Ehmann
    Ankit Agrawal
    Journal of Intelligent Manufacturing, 2023, 34 : 315 - 329