Machine Learning and Digital Twin Driven Diagnostics and Prognostics of Light‐Emitting Diodes

• Published in: Laser & photonics reviews Vol. 14; no. 12
• Main Authors: Ibrahim, Mesfin Seid, Fan, Jiajie, Yung, Winco K. C., Prisacaru, Alexandru, Driel, Willem, Fan, Xuejun, Zhang, Guoqi
• Format: Journal Article
• Language: English
• Published: Weinheim Wiley Subscription Services, Inc 01.12.2020
• Subjects: Algorithms; Artificial neural networks; Bayesian analysis; Component reliability; Data analysis; data‐driven methods; Diagnostic systems; diagnostics and prognostics; Digital twins; Failure analysis; Fault detection; Light emitting diodes; Light sources; light‐emitting diodes (LEDs); Machine learning; machine learning (ML) algorithms; Markov chains; Principal components analysis; Reliability analysis; statistical methods; Support vector machines; System reliability; Technology assessment
• ISSN: 1863-8880; 1863-8899; 1863-8899
• DOI: 10.1002/lpor.202000254

Light‐emitting diodes (LEDs) are among the key innovations that have revolutionized the lighting industry, due to their versatility in applications, higher reliability, longer lifetime, and higher efficiency compared with other light sources. The demand for increased lifetime and higher reliability has attracted a significant number of research studies on the prognostics and lifetime estimation of LEDs, ranging from the traditional failure data analysis to the latest degradation modeling and machine learning based approaches over the past couple of years. However, there is a lack of reviews that systematically address the currently evolving machine learning algorithms and methods for fault detection, diagnostics, and lifetime prediction of LEDs. To address those deficiencies, a review on the diagnostic and prognostic methods and algorithms based on machine learning that helps to improve system performance, reliability, and lifetime assessment of LEDs is provided. The fundamental principles, pros and cons of methods including artificial neural networks, principal component analysis, hidden Markov models, support vector machines, and Bayesian networks are presented. Finally, discussion on the prospects of the machine learning implementation from LED packages, components to system level reliability analysis, potential challenges and opportunities, and the future digital twin technology for LEDs lifetime analysis is provided. Due to the limitations manifested by conventional methods, machine learning approaches arise as powerful tools to enhance the reliability assessment and lifetime prediction of light‐emitting diodes (LEDs) products with a better accuracy and faster computation. The future trend shows the emergence of digital twins through machine learning algorithms to simulate and analyze the performance behavior of LEDs.