Title
Machine learning assisted early anomaly detection of LEDs with spectral power distribution modeling
Author
Liu, Minne (Fudan University)
Ibrahim, Mesfin S. (New Territories)
Wen, Minzhen (Fudan University)
Li, Sheng (Shanhai Yaming Lighting Co.Ltd)
Wang, An (Shanhai Yaming Lighting Co.Ltd)
Zhang, Kouchi (TU Delft Electronic Components, Technology and Materials) ![ORCID 0000-0002-8023-5170 ORCID 0000-0002-8023-5170](/sites/all/themes/tud_repo3/img/icons/orcid_16x16.png)
Fan, J. (TU Delft Electronic Components, Technology and Materials; Fudan University; Chinese Academy of Sciences; Fudan Zhangjiang Institute,) ![ORCID 0000-0001-5400-737X ORCID 0000-0001-5400-737X](/sites/all/themes/tud_repo3/img/icons/orcid_16x16.png)
Date
2023
Abstract
Spectral power distribution (SPD) is the radiation power intensity at different wavelengths, containing the most basic photometric and colorimetric performance of the illuminant, which is able to predict the lifetime of LEDs. This paper proposes an SPD model assisted by machine learning algorithms to detect the early failure of white LEDs. The SPD features of 3W high-power white LEDs were firstly extracted by the statistical models of Gaussian, Lorentz, and Asym2sig functions. An unsupervised learning method, principal component analysis (PCA), was then used to reduce the extracted features parameters’ dimensions. Next a K-nearest neighbor (KNN)-based method was used to detect LEDs’ anomalies by dividing the main cluster into groups, and estimating the distance from the center of mass of each cluster to the test point. The results showed the following: (1) for selected white LEDs, the Asym2sig function has a better fitting result than Gaussian and Lorentz functions; (2) machine learning methods can significantly assist in LED anomaly detection and can decrease the amount of anomaly detection time to 789.6 h, compared to the 1311 h when lumen maintenance degradation reaches 70% as required by IES TM21.
Subject
White LEDs
Spectral power distribution
Anomaly detection
Principal component analysis
K-nearest neighbor
To reference this document use:
http://resolver.tudelft.nl/uuid:7b386549-93d1-499f-97cc-a0f55f41405a
DOI
https://doi.org/10.1109/SSLChinaIFWS57942.2023.10071010
Publisher
IEEE, Danvers
Embargo date
2023-09-24
ISBN
979-8-3503-4639-8
Source
Proceedings - 2022 19th China International Forum on Solid State Lighting and 2022 8th International Forum on Wide Bandgap Semiconductors, SSLCHINA: IFWS 2022
Event
2022 19th China International Forum on Solid State Lighting & 2022 8th International Forum on Wide Bandgap Semiconductors (SSLCHINA: IFWS), 2023-02-07 → 2023-02-10, Suzhou, China
Series
Proceedings - 2022 19th China International Forum on Solid State Lighting and 2022 8th International Forum on Wide Bandgap Semiconductors, SSLCHINA: IFWS 2022
Bibliographical note
Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Part of collection
Institutional Repository
Document type
conference paper
Rights
© 2023 Minne Liu, Mesfin S. Ibrahim, Minzhen Wen, Sheng Li, An Wang, Kouchi Zhang, J. Fan