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
  • [41] Variable layer thicknesses in laser powder-bed fusion for cost reduction of a gas turbine component
    Geisen, Ole
    Bogner, Jan
    Rule, David
    Purschke, Simon
    Jurisch, Martin
    PROGRESS IN ADDITIVE MANUFACTURING, 2024, 9 (04) : 779 - 789
  • [42] Towards Enhanced Eddy Current Testing Array Probes Scalability for Powder Bed Fusion Layer-Wise Imaging
    Barrancos, Andre
    Batalha, Rodolfo L.
    Rosado, Luis S.
    SENSORS, 2023, 23 (05)
  • [43] Effect of layer-wise femtosecond laser shock peening on cracking growth in laser powder bed fused AA 7075
    Wang, Dianzheng
    Li, Kailun
    Yao, Jun
    Geng, Xiaozhuo
    Du, Baorui
    ADDITIVE MANUFACTURING, 2024, 95
  • [44] Development of a defect-detection platform using photodiode signals collected from the melt pool of laser powder-bed fusion
    Taherkhani, Katayoon
    Sheydaeian, Esmat
    Eischer, Christopher
    Otto, Martin
    Toyserkani, Ehsan
    ADDITIVE MANUFACTURING, 2021, 46
  • [45] Calculating the Credibility of Test Samples at Inference by a Layer-wise Activation Cluster Analysis of Convolutional Neural Networks
    Lehmann, Daniel
    Ebner, Marc
    DELTA: PROCEEDINGS OF THE 3RD INTERNATIONAL CONFERENCE ON DEEP LEARNING THEORY AND APPLICATIONS, 2022, : 34 - 43
  • [46] Beyond saliency: Understanding convolutional neural networks from saliency prediction on layer-wise relevance propagation
    Li, Heyi
    Tian, Yunke
    Mueller, Klaus
    Chen, Xin
    IMAGE AND VISION COMPUTING, 2019, 83-84 : 70 - 86
  • [47] Fabrication of Sectionally Permeable Components with Curved Surface by Laser-Beam Powder-Bed Fusion
    Xie, Dongxu
    Fraenkle, Bernd
    Klahn, Christoph
    Dittmeyer, Roland
    CHEMIE INGENIEUR TECHNIK, 2022, 94 (07) : 983 - 992
  • [48] Correlation between surface texture and internal defects in laser powder-bed fusion additive manufacturing
    Makiko Yonehara
    Chika Kato
    Toshi-Taka Ikeshoji
    Koki Takeshita
    Hideki Kyogoku
    Scientific Reports, 11
  • [49] Correlation between surface texture and internal defects in laser powder-bed fusion additive manufacturing
    Yonehara, Makiko
    Kato, Chika
    Ikeshoji, Toshi-Taka
    Takeshita, Koki
    Kyogoku, Hideki
    SCIENTIFIC REPORTS, 2021, 11 (01)
  • [50] Internal surface roughness enhancement of parts made by laser powder-bed fusion additive manufacturing
    Ali, Usman
    Fayazfar, Haniyeh
    Ahmed, Farid
    Toyserkani, Ehsan
    VACUUM, 2020, 177