Multisource data fusion for defect detection in composite additive manufacturing using explainable deep neural network

被引:0
作者
Kumar, Deepak [1 ]
Phillips, Nicholas A. [1 ]
Liu, Yongxin [2 ]
Namilae, Sirish [1 ]
机构
[1] Embry Riddle Aeronaut Univ, Dept Aerosp Engn, 1 Aerosp Blvd, Daytona Beach, FL 32114 USA
[2] Embry Riddle Aeronaut Univ, Dept Math, 1 Aerosp Blvd, Daytona Beach, FL 32114 USA
关键词
Composites; Additive manufacturing; Defect detection; Deep neural network; Multisource data; DEPOSITION; PRINTERS; SYSTEM;
D O I
10.1016/j.ast.2024.109729
中图分类号
V [航空、航天];
学科分类号
08 ; 0825 ;
摘要
Composite additive manufacturing has the potential to replace traditional composite manufacturing for aerospace applications. Additive manufacturing provides greater adaptability to complex designs, reduce material waste, and streamline the production process. However, in comparison to conventional composite manufacturing methods, additive manufacturing is inherently more susceptible to processing anomalies and defects, primarily due to the novelty of the process and the absence of applied pressure. To effectively capitalize on the benefits of additive manufacturing, a quality and reliability assurance system is critical. In this study, we have generated multisource data to analyze the inner layer thermography and surface quality, employing a multi-camera system including thermal and charge-coupled device cameras. This multisource data is utilized in an explainable zero bias deep neural network framework to detect manufacturing defects. This deep learning algorithm introduces a new zero bias layer following the regular dense layer. After being trained on normal (defect-free) samples of each data stream, the trained model is transformed into an anomaly detector by extracting low dimension features from the zero-bias layer. This allowed identification various anomalies without having to train the model on any defective inputs. As a result, the model's accuracy to detect multiple types of anomalies is higher with multisource data compared to models based on single data source. Anomaly detection accuracy was 99.72% when using data from multiple sources, 98.28% when using only CCD images, and 95% when using only thermal camera data.
引用
收藏
页数:14
相关论文
共 33 条
  • [1] Aniwaa Pte. Ltd, About us
  • [2] [Anonymous], 2021, EUROPEAN SPACE AGENC
  • [3] Banadaki Y, 2020, Arxiv, DOI [arXiv:2003.08749, 10.48550/arXiv.2003.08749, DOI 10.48550/ARXIV.2003.08749]
  • [4] Analytical modelling of in situ layer-wise defect detection in 3D-printed parts: additive manufacturing
    Bowoto, Oluwole K.
    Oladapo, Bankole I.
    Zahedi, S. A.
    Omigbodun, Francis T.
    Emenuvwe, Omonigho P.
    [J]. INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2020, 111 (7-8) : 2311 - 2321
  • [5] Machine learning-based image processing for on-line defect recognition in additive manufacturing
    Caggiano, Alessandra
    Zhang, Jianjing
    Alfieri, Vittorio
    Caiazzo, Fabrizia
    Gao, Robert
    Teti, Roberto
    [J]. CIRP ANNALS-MANUFACTURING TECHNOLOGY, 2019, 68 (01) : 451 - 454
  • [6] Direct digital manufacturing: definition, evolution, and sustainability implications
    Chen, Danfang
    Heyer, Steffen
    Ibbotson, Suphunnika
    Salonitis, Konstantinos
    Steingrimsson, Jon Gardar
    Thiede, Sebastian
    [J]. JOURNAL OF CLEANER PRODUCTION, 2015, 107 : 615 - 625
  • [7] 3D printed continuous fiber reinforced composite lightweight structures: A review and outlook
    Cheng, Ping
    Peng, Yong
    Li, Shixian
    Rao, Yanni
    Le Duigou, Antoine
    Wang, Kui
    Ahzi, Said
    [J]. COMPOSITES PART B-ENGINEERING, 2023, 250
  • [8] 3D printing technologies applied to the manufacturing of aircraft components
    Chung, Kun-Chen
    Shu, Ming-Hung
    Wang, Yu-Cheng
    Huang, Jui-Chan
    Lau, Edwin M.
    [J]. MODERN PHYSICS LETTERS B, 2020, 34 (7-9):
  • [9] The Mahalanobis distance
    De Maesschalck, R
    Jouan-Rimbaud, D
    Massart, DL
    [J]. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2000, 50 (01) : 1 - 18
  • [10] What makes a material printable? A viscoelastic model for extrusion-based 3D printing of polymers
    Duty, Chad
    Ajinjeru, Christine
    Kishore, Vidya
    Compton, Brett
    Hmeidat, Nadim
    Chen, Xun
    Liu, Peng
    Hassen, Ahmed Arabi
    Lindahl, John
    Kunc, Vlastimil
    [J]. JOURNAL OF MANUFACTURING PROCESSES, 2018, 35 : 526 - 537