Detecting balling defects using multisource transfer learning in wire arc additive manufacturing

被引:12
作者
Shin, Seung-Jun [1 ]
Hong, Sung-Ho [2 ]
Jadhav, Sainand [3 ]
Kim, Duck Bong [4 ]
机构
[1] Hanyang Univ, Sch Interdisciplinary Ind Studies, 222 Wangsimni Ro,Seongdong Gu, Seoul, South Korea
[2] Hanyang Univ, Dept Ind Data Engn, 222 Wangsimni Ro, Seoul, South Korea
[3] Tennessee Technol Univ, Dept Mech Engn, 115 W 10th St, Cookeville, TN 38505 USA
[4] Tennessee Technol Univ, Dept Mfg & Engn Technol, 920 North Peachtree Ave, Cookeville, TN 38505 USA
基金
美国国家科学基金会;
关键词
wire arc additive manufacturing; anomaly detection; transfer learning; convolutional neural networks; domain adaptation; CONVOLUTIONAL NEURAL-NETWORKS; CHALLENGES; FRAMEWORK;
D O I
10.1093/jcde/qwad067
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Wire arc additive manufacturing (WAAM) has gained attention as a feasible process in large-scale metal additive manufacturing due to its high deposition rate, cost efficiency, and material diversity. However, WAAM induces a degree of uncertainty in the process stability and the part quality owing to its non-equilibrium thermal cycles and layer-by-layer stacking mechanism. Anomaly detection is therefore necessary for the quality monitoring of the parts. Most relevant studies have applied machine learning to derive data-driven models that detect defects through feature and pattern learning. However, acquiring sufficient data is time- and/or resource-intensive, which introduces a challenge to applying machine learning-based anomaly detection. This study proposes a multisource transfer learning method that generates anomaly detection models for balling defect detection, thus ensuring quality monitoring in WAAM. The proposed method uses convolutional neural network models to extract sufficient image features from multisource materials, then transfers and fine-tunes the models for anomaly detection in the target material. Stepwise learning is applied to extract image features sequentially from individual source materials, and composite learning is employed to assign the optimal frozen ratio for converging transferred and present features. Experiments were performed using a gas tungsten arc welding-based WAAM process to validate the classification accuracy of the models using low-carbon steel, stainless steel, and Inconel.
引用
收藏
页码:1423 / 1442
页数:20
相关论文
共 50 条
[41]   Characterisation of Al–Mg Alloy Cylindrical Component Made by Wire Arc Additive Manufacturing Using Cold Metal Transfer Arc Welding Process [J].
Bellamkonda Prasanna Nagasai ;
Sudersanan Malarvizhi ;
Visvalingam Balasubramanian .
Transactions of the Indian Institute of Metals, 2022, 75 :2019-2030
[42]   Investigation of Arc Stability in Wire Arc Additive Manufacturing of 2319 Aluminum Alloy [J].
Gao, Qiyu ;
Lyu, Feiyue ;
Wang, Leilei ;
Zhan, Xiaohong .
MATERIALS, 2024, 17 (21)
[43]   Mapping of Bead Geometry in Wire Arc Additive Manufacturing Systems Using Passive Vision [J].
Couto, Marcus O. ;
Rodrigues, Arthur G. ;
Coutinho, Fernando ;
Costa, Ramon R. ;
Leite, Antonio C. ;
Lizarralde, Fernando ;
Payao Filho, Joao C. .
JOURNAL OF CONTROL AUTOMATION AND ELECTRICAL SYSTEMS, 2022, 33 (04) :1136-1147
[44]   Mapping of Bead Geometry in Wire Arc Additive Manufacturing Systems Using Passive Vision [J].
Marcus O. Couto ;
Arthur G. Rodrigues ;
Fernando Coutinho ;
Ramon R. Costa ;
Antonio C. Leite ;
Fernando Lizarralde ;
João C. Payão Filho .
Journal of Control, Automation and Electrical Systems, 2022, 33 :1136-1147
[45]   IMPROVING GEOMETRIC ACCURACY IN WIRE AND ARC ADDITIVE MANUFACTURING WITH ENGINEERING-INFORMED MACHINE LEARNING [J].
Ruiz, Cesar ;
Jafari, Davoud ;
Subramanian, Vignesh Venkata ;
Vaneker, Tom H. J. ;
Ya, Wei ;
Huang, Qiang .
PROCEEDINGS OF ASME 2022 17TH INTERNATIONAL MANUFACTURING SCIENCE AND ENGINEERING CONFERENCE, MSEC2022, VOL 1, 2022,
[46]   A deep learning-based model for defect reorganisation in welding/wire arc additive manufacturing [J].
Nadiu, Jammu Bhargava ;
Sushma, Varri ;
Panicker, C. T. Justus ;
Dhanush, Madhiri ;
Senthilkumar, V. .
WELDING INTERNATIONAL, 2025, 39 (02) :76-85
[47]   Comparative Evaluation of Machine Learning Regressors for the Layer Geometry Prediction in Wire arc Additive manufacturing [J].
Barrionuevo, German Omar ;
Rios, Sergio ;
Williams, Stewart W. ;
Ramos-Grez, Jorge Andres .
2021 IEEE 12TH INTERNATIONAL CONFERENCE ON MECHANICAL AND INTELLIGENT MANUFACTURING TECHNOLOGIES, ICMIMT, 2021, :186-190
[48]   Automated Determination of Grain Features for Wire Arc Additive Manufacturing [J].
Karimi, J. ;
Bohlen, A. ;
Kamboj, N. ;
Seefeld, T. .
JOURNAL OF MATERIALS ENGINEERING AND PERFORMANCE, 2023, 32 (22) :10402-10411
[49]   Modelling of wire-arc additive manufacturing-A review [J].
Sampaio, R. F. V. ;
Pragana, J. P. M. ;
Braganca, I. M. F. ;
Silva, C. M. A. ;
Nielsen, C. V. ;
Martins, P. A. F. .
ADVANCES IN INDUSTRIAL AND MANUFACTURING ENGINEERING, 2023, 6
[50]   A Review of Path Planning for Wire Arc Additive Manufacturing (WAAM) [J].
Yaseer, Ahmed ;
Chen, Heping .
JOURNAL OF ADVANCED MANUFACTURING SYSTEMS, 2021, 20 (03) :589-609