Development of a Failure Prediction System for Industrial Laser Diodes Based on Artificial Neural Networks

Online First: 18/11/2026

Các tác giả

Email tác giả liên hệ:

thanhnp@hcmute.edu.vn

DOI:

https://doi.org/10.54644/jte.2026.2053

Từ khóa:

Laser Diode Degradation, Artificial Neural Networks (ANN), Semiconductor Diode Reliability, Fault Prediction Systems, Semiconductor Manufacturing

Tóm tắt

Industrial laser diodes are essential devices used in semiconductor chip manufacturing, where the precision and stability of laser output strongly affect the process yield. However, under long-time operation and high thermal stress, these lasers tend to degrade slowly, sometimes leading to unexpected failure that causes production interruption and cost increasing. In this work, a data-driven fault prediction system is proposed for early detection of degradation behavior in industrial laser diodes. The experimental data were collected from a Monaco 517-40-30 femtosecond laser operating in an actual production environment. The proposed system monitors a set of electrical, thermal, and optical parameters that reflect the operational condition and degradation characteristics of the laser diode. After normalization, noise filtering and outlier removal, a feedforward neural network was trained using the Levenberg-Marquardt algorithm with Mean Squared Error (MSE) and regularization to reduce the overfitting problem. The model achieved above 98.9% for both training and testing accuracy, with minimum F1-score and Recall values of 0.9. This shows that the system can do early fault detection quite reliably even in industrial conditions. From these results, the system is considered a practical solution for predictive maintenance and can help improve uptime and reliability of laser equipment.

Tải xuống: 0

Dữ liệu tải xuống chưa có sẵn.

Tiểu sử của Tác giả

Tan Phat Ngo, Ho Chi Minh City University of Technology and Engineering, Vietnam

Tan Phat Ngo is an Engineer in semiconductor manufacturing, focusing on New Product Introduction (NPI), process and equipment engineering, and product qualification. The author received the Bachelor’s degree in Electrical Engineering from Dong Nai Technology University (2016-2018) and is currently pursuing a Master’s degree in Electrical Engineering at Ho Chi Minh City University of Technology and Engineering (2024-2026).

Email: 2430608@student.hcmute.edu.vn. ORCID:  https://orcid.org/0009-0009-2228-5258

Phan Thanh Nguyen, Ho Chi Minh City University of Technology and Engineering, Vietnam

Phan Thanh Nguyen is currently a lecturer in the Faculty of Electronics and Electrical Engineering, Ho Chi Minh City University of Technology and Engineering, Vietnam, obtained his Ph.D. in Electrical Engineering at Southern Taiwan University of Science and Technology, Taiwan, in 2016. The current research interests are Intelligent control systems, Automatic motion control, Electric drives, Power system control and Renewable energy.

Email: thanhnp@hcmute.edu.vn. ORCID:  https://orcid.org/0000-0002-3257-037X

Tài liệu tham khảo

K. Abdelli, D. Rafique, H. Grießer, and S. Pachnicke, “Lifetime prediction of 1550 nm DFB laser using machine learning techniques,” in Proc. Optical Fiber Communication Conf. (OFC), San Diego, CA, USA, Mar. 2020, Paper Th2A.3, doi: 10.1364/OFC.2020.Th2A.3.

K. Abdelli, H. Grießer, and S. Pachnicke, “A machine learning-based framework for predictive maintenance of semiconductor laser for optical communication,” J. Lightw. Technol., vol. 40, no. 14, pp. 4698–4708, Jul. 2022, doi: 10.1109/JLT.2022.3163579.

K. Abdelli, D. Rafique, and S. Pachnicke, “Machine learning based laser failure mode detection,” in Proc. 21st Int. Conf. Transparent Opt. Netw. (ICTON), Angers, France, Jul. 2019, pp. 1–4, doi: 10.1109/ICTON.2019.8840267.

J. S. Huang, “Temperature and current dependences of reliability degradation of buried heterostructure semiconductor lasers,” IEEE Trans. Device Mater. Rel., vol. 5, no. 1, pp. 150–154, Mar. 2005, doi: 10.1109/TDMR.2005.843834.

Monaco 517 Industrial Femtosecond Laser, Coherent Corp., Santa Clara, CA, USA, Jan. 2020. [Online]. Available: https://www.coherent.com/content/dam/coherent/site/en/resources/datasheet/lasers/COHR_Monaco517_DS_0120_1.pdf (accessed Jul. 13, 2026).

N. J. Butt, R. A. Roberts, and S. S. Patnaik, “Laser diode optical output dependence on junction temperature for high-power laser systems,” Opt. Laser Technol., vol. 125, May 2020, Art. no. 106019, doi: 10.1016/j.optlastec.2019.106019.

Characterization of Laser Diode and Its Challenges, Application Note 5992-3708, Keysight Technologies, Santa Rosa, CA, USA, Nov. 2019. [Online]. Available: https://www.keysight.com/us/en/assets/7018-03184/application-notes/5992-3708.pdf (accessed Jul. 14, 2026).

P. W. Epperlein, “Basic diode laser engineering principles,” in Semiconductor Laser Engineering, Reliability and Diagnostics: A Practical Approach to High Power and Single Mode Devices, 1st ed. Hoboken, NJ, USA: Wiley, 2013, ch. 1, pp. 3–100.

M. Hempel, S. Dadgostar, J. Jiménez, R. Kernke, A. Gollhardt, and J. W. Tomm, “Catastrophic optical damage in semiconductor lasers: Physics and new results on InGaN high-power diode lasers,” Phys. Status Solidi RRL, vol. 16, no. 4, Apr. 2022, Art. no. 2100527, doi: 10.1002/pssr.202100527.

H. H. Sun, A Practical Guide to Handling Laser Diode Beams, 1st ed., vol. 199. Dordrecht, The Netherlands: Springer, 2015, doi: 10.1007/978-94-017-9783-2.

Tải xuống

Đã Xuất bản

2026-11-18

Cách trích dẫn

[1]
T. P. Ngo và P. T. Nguyen, “Development of a Failure Prediction System for Industrial Laser Diodes Based on Artificial Neural Networks: Online First: 18/11/2026”, JTE, tháng 11 2026.