مدلسازی مبتنی بر یادگیری ماشین فرآیندهای ساخت افزایشی فلزی با استفاده از روش‌های داده افزایی و یادگیری گروهی

نوع مقاله : مقاله پژوهشی

نویسندگان

نیما ایوبی

رضا محبوبی اسفنجانی

احمد اکبری الوانق

حبیب بدری قویفکر

دانشکده مهندسی برق و کامپیوتر ـ کنترل، دانشگاه صنعتی سهند تبریز، تبریز.

10.22067/jmme.2025.91745.1177

چکیده

با وجود قابلیت‌های فراوان ساخت افزایشی فلزی، این روش با محدویت‌هایی از جمله قابلیت تکرارپذیری و تضمین کیفیت قطعات مواجه می‌باشد. جهت رفع این محدودیت‌ها به مدلسازی دقیق فرآیند نیاز است. از طرفی، کارایی روش‌های مدلسازی سنتی برای این امر پایین می‌باشد. یکی از روش‌های جدید مدلسازی مبتنی بر داده که امکان کشف الگوهای پنهان در فرآیندهای غیرخطی را فراهم می‌کند، یادگیری ماشین است. با وجود مزایای فراوان، به دلیل تعداد محدود داده در فرایند ساخت افزایشی، پیاده‌سازی یادگیری ماشین با مشکلاتی مواجه است. در این مقاله برای رفع این موارد از ترکیب داده‌افزایی و یادگیری ماشین برای مدلسازی دو روش شناخته شده ساخت افزایشی فلزی استفاده شده است. یادگیری گروهی برای بهبود دقت مدل به کار رفته است. نتایج شبیه‌سازی نشان دهنده کارایی روش پیشنهادی در مدلسازی مناسب فرآیند ساخت افزایشی فلزی می‌باشد. عملکرد مدل‌های پیشنهادی به ترتیب به اندازه 53 و 48 درصدی نسبت به حالت بدون داده افزایی بهبود یافته است.

کلیدواژه‌ها

ساخت افزایشی فلزی

یادگیری ماشین

داده افزایی

یادگیری گروهی

مدلسازی

موضوعات

• شکل دادن فلزات

---

عنوان مقاله English

Machine Learning-Based Modeling of Metal Additive Manufacturing Processes Using Data Augmentation and Ensemble Learning

نویسندگان English

Nima Ayobi

Reza Mahboobi Esfanjani

Ahmad Akbari Alvanagh

Habib Badri Ghavifekr

, Department of Electrical and Computer Engineering – Control, Sahand University of Technology, Tabriz, Iran. Corresponding Author: Professor, Department of Electrical and Computer Engineering – Control, Sahand University of Technology, Tabriz, Iran.

چکیده English

Although metal additive manufacturing offers many advantages, it is restricted by the repeatability and quality assurance of the produced parts. Accurate mathematical modeling of the mentioned process is essential to tackle these limitations. Traditional mathematical modeling approaches are inefficient in describing this complicated system. Machine learning is a novel data-based modeling approach to discover hidden patterns in nonlinear systems. However, applying this scheme in the metal additive manufacturing process is challenging due to the limited data samples. This paper combines machine learning and data augmentation to tackle the mentioned issues and model two well-known metal additive manufacturing processes, Selective Laser Melting and Laser Direct Metal Deposition. Ensemble learning is utilized here to improve the model's accuracy. Simulation results demonstrate the effectiveness of the proposed method in modeling the metal additive manufacturing processes. The performance of the proposed models has been improved by 53% and 48%, respectively, compared to the case without data augmentation.

کلیدواژه‌ها English

Metal additive manufacturing

Machine learning

Data augmentation

Ensemble learning

Modeling

مراجع

[1]    I. Gibson, D. Rosen, B. Stucker, and M. Khorasani, “Introduction and basic principles,” in Additive Manufacturing Technologies, Cham: Springer International Publishing, pp. 1–21, 2020. https://doi.org/10.1007/978-3-030-56127-7_1

[2]    S. Dharmadhikari, N. Menon, and A. Basak, "A reinforcement learning approach for process parameter optimization in additive manufacturing," Additive Manufacturing, vol. 71, p. 103556, 2023. https://doi.org/10.1016/j.addma.2023.103556

[3]    J. Qin et al., "Research and application of machine learning for additive manufacturing," Additive Manufacturing, vol. 52, p. 102691, 2022. https://doi.org/10.1016/j.addma.2022.102691

[4]    S. Kumar et al., "Machine learning techniques in additive manufacturing: a state of the art review on design, processes and production control," Journal of Intelligent Manufacturing, vol. 34, no. 1, pp. 21-55, 2023. https://doi.org/10.1007/s10845-022-02029-5

[5]    A. M. Schweidtmann et al., "Machine Learning in Chemical Engineering: A Perspective," Chemie Ingenieur Technik, vol. 93, no. 12, pp. 2029-2039, 2021. https://doi.org/10.1002/cite.202100083

[6]    F. Rahimi, S. Ziaei, and R. M. Esfanjani, "A Reinforcement Learning-Based Control Approach for Tracking Problem of a Class of Nonlinear Systems: Applied to a Single-Link Manipulator," in 2023 31st International Conference on Electrical Engineering (ICEE), 2023, pp. 58-63. https://doi.org/10.1109/ICEE59167.2023.10334874

[7]    M. H. Sulaiman, M. S. Jadin, Z. Mustaffa, M. N. M. Azlan, and H. Daniyal, "Short-Term Forecasting of Floating Photovoltaic Power Generation Using Machine Learning Models," Cleaner Energy Systems, p. 100137, 2024. https://doi.org/10.1016/j.cles.2024.100137

[8]    H. Mahanna, N. El-Rashidy, M. R. Kaloop, S. El-Sapakh, A. Alluqmani, and R. Hassan, "Prediction of wastewater treatment plant performance through machine learning techniques," Desalination and Water Treatment, vol. 319, p. 100524, 2024. https://doi.org/10.1016/j.dwt.2024.100524

[9]    S. Hamal, B. K. Mishra, R. Baldock, W. Sayers, T. N. Adhikari, and R. M. Gibson, "A comparative analysis of machine learning algorithms for detecting COVID-19 using lung X-ray images," Decision Analytics Journal, vol. 11, p. 100460, 2024. https://doi.org/10.1016/j.dajour.2024.100460

[10]  D. J. McGregor, M. V. Bimrose, C. Shao, S. Tawfick, and W. P. King, "Using machine learning to predict dimensions and qualify diverse part designs across multiple additive machines and materials," Additive Manufacturing, vol. 55, p. 102848, 2022. https://doi.org/10.1016/j.addma.2022.102848

[11]  Z. Gu et al., "A universal predictor-based machine learning model for optimal process maps in laser powder bed fusion process," Journal of Intelligent Manufacturing, vol. 34, no. 8, pp. 3341-3363, 2023. https://doi.org/10.1007/s10845-022-02004-0

[12]  Z. Zhang, Z. Liu, and D. Wu, "Prediction of melt pool temperature in directed energy deposition using machine learning," Additive Manufacturing, vol. 37, p. 101692, 202. https://doi.org/10.1016/j.addma.2020.101692

[13]  J. Akhavan, J. Lyu, and S. Manoochehri, "A deep learning solution for real-time quality assessment and control in additive manufacturing using point cloud data," Journal of Intelligent Manufacturing, vol. 35, no. 3, pp. 1389-1406, 2024. https://doi.org/10.1007/s10845-023-02121-4

[14]  L. Meng et al., "Machine Learning in Additive Manufacturing: A Review," JOM, vol. 72, no. 6, pp. 2363-2377, 2020. https://doi.org/10.1007/s11837-020-04155-y

[15]  K. Azizi, H. Taheri, and S. Khooyooz, "Using Structured Pruning to Find Winning Lottery Tickets," in 2023 28th International Computer Conference, Computer Society of Iran, 2023, pp. 1-5. https://doi.org/10.1109/CSICC58665.2023.10105376

[16]  J. F. Rodrigues, L. Florea, M. C. F. de Oliveira, D. Diamond, and O. N. Oliveira, "Big data and machine learning for materials science," Discover Materials, vol. 1, no. 1 , p. 12, 2021. https://doi.org/10.1007/s43939-021-00012-0

[17]  I. H. Sarker, "Machine Learning: Algorithms, Real-World Applications and Research Directions," SN Computer Science, vol. 2, no. 3, p. 160, 2021. https://doi.org/10.1007/s42979-021-00592-x

[18]  A. Yafouz et al., "Comprehensive comparison of various machine learning algorithms for short-term ozone concentration prediction," Alexandria Engineering Journal, vol. 61, no. 6, pp. 4607-4622, 2022. https://doi.org/10.1016/j.aej.2021.10.021

[19]  X. Su, J. An, Y. Zhang, P. Zhu, and B. Zhu, "Prediction of ozone hourly concentrations by support vector machine and kernel extreme learning machine using wavelet transformation and partial least squares methods," Atmospheric Pollution Research, vol. 11, no. 6, pp. 51-60, 2020. https://doi.org/10.1016/j.apr.2020.02.024

[20]  I. D. Mienye and Y. Sun, "A Survey of Ensemble Learning: Concepts, Algorithms, Applications, and Prospects," IEEE Access, vol. 10, pp. 99129-99149, 2022. https://doi.org/10.1109/ACCESS.2022.3207287

[21]  P. Kokol, M. Kokol, and S. Zagoranski, "Machine learning on small size samples: A synthetic knowledge synthesis," Science Progress, vol. 105, no. 1, 2022. https://doi.org/10.1177/00368504211029777

[22]  K. Maharana, S. Mondal, and B. Nemade, "A review: Data pre-processing and data augmentation techniques," Global Transitions Proceedings, vol. 3, no. 1, pp. 91-99, 2022. https://doi.org/10.1016/j.gltp.2022.04.020

[23]  H. Ohno, "Auto-encoder-based generative models for data augmentation on regression problems," Soft Computing, vol. 24, no. 11, pp. 7999-8009, 2020. https://doi.org/10.1007/s00500-019-04094-0

[24]  L.-M. Liu, X.-Y. Ren, F. Zhang, L. Gao, and B. Hao, "Dual-dimension Time-GGAN data augmentation method for improving the performance of deep learning models for PV power forecasting," Energy Reports, vol. 9, pp. 6419-6433, 2023. https://doi.org/10.1016/j.egyr.2023.05.226

[25]  K. Nawa, K. Hagiwara, and K. Nakamura, "Prediction-accuracy improvement of neural network to ferromagnetic multilayers by Gaussian data augmentation and ensemble learning," Computational Materials Science, vol. 219, p. 112032, 2023. https://doi.org/10.1016/j.commatsci.2023.112032

[26]  E. Pérez and S. Ventura, "Progressive growing of Generative Adversarial Networks for improving data augmentation and skin cancer diagnosis," Artificial Intelligence in Medicine, vol. 141, p. 102556, 2023. https://doi.org/10.1016/j.artmed.2023.102556

[27]  G. Celik, "CovidCoughNet: A new method based on convolutional neural networks and deep feature extraction using pitch-shifting data augmentation for covid-19 detection from cough, breath, and voice signals," Computers in Biology and Medicine, vol. 163, p. 107153, 2023. https://doi.org/10.1016/j.compbiomed.2023.107153

[28]  L. Xu, M. Skoularidou, A. Cuesta-Infante, and K. Veeramachaneni, "Modeling Tabular data using Conditional GAN," 2019. [Online].

[29]  E. Choi, S. Biswal, B. Malin, J. Duke, W. F. Stewart, and J. Sun, "Generating multi-label discrete patient records using generative adversarial networks," in Machine learning for healthcare conference, 2017: PMLR, pp. 286-305.

[30]  A. Srivastava, L. Valkov, C. Russell, M. U. Gutmann, and C. Sutton, "Veegan: Reducing mode collapse in gans using implicit variational learning," Advances in neural information processing systems, vol. 30, 2017.

[31]  N. Park, M. Mohammadi, K. Gorde, S. Jajodia, H. Park, and Y. Kim, "Data synthesis based on generative adversarial networks," arXiv preprint arXiv:1806.03384, 2018.

[32]  G. a. W. James, Daniela and Hastie, Trevor and Tibshirani, Robert, An Introduction to Statistical Learning: With Applications in R, 2nd ed. Springer, 2021.

[33]  T. Peng, J. Lv, A. Majeed, and X. Liang, "An experimental investigation on energy-effective additive manufacturing of aluminum parts via process parameter selection," Journal of Cleaner Production, vol. 279, p. 123609, 2021. https://doi.org/10.1016/j.jclepro.2020.123609

[34]  F. Caiazzo and A. Caggiano, "Laser Direct Metal Deposition of 2024 Al Alloy: Trace Geometry Prediction via Machine Learning," Materials, vol. 11, no. 3, p. 444, 2018. https://doi.org/10.3390/ma11030444

[35]  G. Tapia, S. Khairallah, M. Matthews, W. E. King, and A. Elwany, "Gaussian process-based surrogate modeling framework for process planning in laser powder-bed fusion additive manufacturing of 316L stainless steel," The International Journal of Advanced Manufacturing Technology, vol. 94, no. 9, pp. 3591-3603, 2018. https://doi.org/10.1007/s00170-017-1045-z

[36]  Y. Li, Y. Sun, Q. Han, G. Zhang, and I. Horváth, "Enhanced beads overlapping model for wire and arc additive manufacturing of multi-layer multi-bead metallic parts," Journal of Materials Processing Technology, vol. 252, pp. 838-848, 2018. https://doi.org/10.1016/j.jmatprotec.2017.10.017

[37]  A. Kalilayeva, D. Zhumashev, D. Wei, A. Perveen, and D. Talamona, "Investigation of Stereolithography Additively Manufactured Components for Deviations in Dimensional and Geometrical Features," Polymers, vol. 16, no. 23, 2024. https://doi.org/10.3390/polym16233311

[38]  A. Karadag and O. Ulkir, "Prediction of Dimensional Accuracy and Surface Quality in Additively Manufactured Biomedical Implants Using ANN," International Journal of Precision Engineering and Manufacturing, vol. 26, no. 5, pp. 1187-1213, 2025. https://doi.org/10.1007/s12541-025-01229-2