This paper presents the prognosis of LED luminaires based on supervised machine learning. Several gradient-boosting decision tree (GBDT) classifiers, viz. AdaBoost, GBM, XGBoost, CatBoost and LightGBM are selected for their high accuracy and speed. At first, a temperature-dependent linear model of LED is developed and validated. Using this model, complete LED systems comprising of LED module and constant-current flyback driver, having 50 W to 120 W rated power, four dimming levels within 25% to 100% range and various series–parallel combinations of the LED array are designed and implemented in NI-Multisim software. From the simulation results, datasets required for the training and testing of the GBDT classifiers are generated. The trained classifiers can efficiently predict five operational conditions, viz. healthy, overheating, faulty capacitor, open circuit and short circuit by taking time-domain electrical features as input. A comparative evaluation conducted among the GBDT classifiers indicates that LightGBM is the best performer as it exhibits the highest validation accuracy (97.78%) and test accuracy (95.83%) with smallest margin of error (±3.58%), the lowest generalization error (0.042) and the fastest speed of execution (0.43 s). Therefore, LightGBM can be recommended for the prognosis of LED luminaires for smart lighting applications.
Get full access to this article
View all access options for this article.
References
1.
BhadraRDuttaSKediaAGuptaSPanigrahyPSChattopadhyayP.Applied machine learning for bearing fault prognostics. Proceedings of 2018 IEEE Applied Signal Processing Conference (ASPCON), Kolkata, India, 7–9December2018: 158–162.
2.
ZhangMChenWZhangYet al. Fault Diagnosis of oil-immersed power transformer based on difference-mutation brain storm optimized CatBoost model. IEEE Access2021; 9: 168767–168782.
3.
PandharipandeA.Editorial: Data and connected lighting. Lighting Research and Technology2021; 53: 525–525.
4.
DingCZhangT.Research on health monitoring of LED lighting system. Proceedings of 2016 Prognostics and System Health Management Conference (PHM-Chengdu), Chengdu, China, 19–21October2016: 1–5.
5.
PadmasaliAKiniS.LED life prediction based on lumen depreciation and colour shift. Lighting Research & Technology2017; 49: 84–99.
6.
QianCFanJFanXZhangG.Prediction of lumen depreciation and color shift for phosphor-converted white light-emitting diodes based on a spectral power distribution analysis method. IEEE Access2017; 5: 24054–24061.
7.
BaranKRóżowiczAWachtaHRóżowiczS.Modeling of selected lighting parameters of LED panel. Energies2020; 13: 3583.
8.
PadmasaliANKiniSG.A generalized methodology for predicting the lifetime performance of LED luminaire. IEEE Transactions on Electron Devices2020; 67: 2831–2836.
9.
SunGBaiYZhangZ.Overview of high-power LED life prediction algorithms. Frontiers in Sustainable Energy Policy2024; 3: 1343339.
10.
YuanCCAFanJFanX. Deep machine learning of the spectral power distribution of the LED system with multiple degradation mechanisms. Journal of Mechanics2021; 37: 172–183.
11.
LethaSSBollenMHJRönnbergSK.Analysis and recommendations for LED catastrophic failure due to voltage stress. Energies2022; 15: 540.
12.
GuptaVBasakBRoyB.A Fault-Detecting and motion-sensing wireless light controller for LED lighting system. Proceedings of 2020 IEEE Calcutta Conference (CALCON), Kolkata, India, 28–29February2020: 462–466.
13.
RoyAGangulyARoyB.Real-time condition monitoring system for LED luminaires: an approach. Proceedings of 2020 IEEE Applied Signal Processing Conference (ASPCON), Kolkata, India, 7–9October2020: 217–221.
14.
ChenJYinHQinYZhaoDJiangW.A Supervised Contrast Focus Neural Network for LED packaging defects classification. Proceedings of 2023 CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS), Yibin, China, 22–24September2023: 1–6.
15.
TorresGORumbo-MoralesJYSánchezROMartínez-GarcíaMBlancoMAR. Fault tolerant control via input-output linearization method for LED-driver using a boost converter. IEEE Access2023; 11: 10390–10397.
16.
AlexeevALinnartzJOnushkinGAKumarAMartinG.Dynamic response-based LEDs health and temperature monitoring. Measurement2020; 156: 107599.
17.
ShaileshKRKurianCPKiniSG.LED lighting reliability from a failure perspective. 2012 International Conference on Emerging Trends in Electrical Engineering and Energy Management (ICETEEEM), Chennai, India, 13–15December2012: 468–472.
18.
HegedüsJHantosGPoppeA.Lifetime modelling issues of power light emitting diodes. Energies2020; 13: 3370.
19.
SunBFanXQianCZhangG.PoF-simulation-assisted reliability prediction for electrolytic capacitor in LED drivers. IEEE Transactions on Industrial Electronics2016; 63: 6726–6735.
20.
LuGYangSHuangY.Analysis on failure modes and mechanisms of LED. 2009 8th International Conference on Reliability, Maintainability and Safety, Chengdu, China, 20–24July2009: 1237–1241.
21.
HewittDAGreenJEDavidsonJNFosterMPStoneDA.Observation of electrolytic capacitor ageing behaviour for the purpose of prognostics. IECON 2016 – 42nd Annual Conference of the IEEE Industrial Electronics Society, Florence, Italy, 23–26October2016: 2195–2200.
22.
AlmeidaPSJorgeJMRodriguesCRBSSoaresGMPintoDPBragaHAC.A novel method of current equalization in LED strings based on simple linear circuit. 2011 IEEE International Symposium on Industrial Electronics, Gdansk, Poland, 27–30June2011: 95–100.
23.
ThomasLRitzerM.Application Note AN006: Reliability and Lifetime of LEDs. Regensburg, Germany: OSRAM Opto Semiconductor, 2020.
24.
NorbertH.Application Note AN059: LED Diagnosis in Automotive Applications. Regensburg, Germany: OSRAM Opto Semiconductor, 2018.
25.
CuiYShiJWangZ.Analog circuits fault diagnosis using multi-valued Fisher’s fuzzy decision tree (MFFDT). International Journal of Circuit Theory and Applications2016; 44: 240–260.
26.
LiNLiBGaoL.Transient stability assessment of power system based on XGBoost and factorization machine. IEEE Access2020; 8: 28403–28414.
PtakPPrauznerTNogaHMigoP.Testing of inductors using the NI Multisim simulation program. Journal of Physics: Conference Series2022; 2408: 012007.
29.
TaheriMMSeyediHNojavanMKhoshbouyMIvatlooBM.High-speed decision tree based series-compensated transmission lines protection using differential phase angle of superimposed current. IEEE Transactions on Power Delivery2018; 33: 3130–3138.
30.
Nemat SaberiABelahcenASobraJVaimannT. LightGBM-based fault diagnosis of rotating machinery under changing working conditions using modified recursive feature elimination. IEEE Access2022; 10: 81910–81925.
31.
JiangXXuYKeWZhangYZhuQHeY.An imbalanced multifault diagnosis method based on bias weights AdaBoost. IEEE Transactions on Instrumentation and Measurement2022; 71: 1–8.
32.
ToharudinTCarakaREPratiwiIRet al. Boosting algorithm to handle unbalanced classification of PM2.5 concentration levels by observing meteorological parameters in Jakarta-Indonesia using AdaBoost, XGBoost, CatBoost, and LightGBM. IEEE Access2023; 11: 35680–35696.
33.
SamatALiEDuPLiuSMiaoZZhangW.CatBoost for RS image classification with pseudo label support from neighbor patches-based clustering. IEEE Geoscience and Remote Sensing Letters2022; 19: 1–5.
MaoZXiaMJiangBXuDShiP.Incipient fault diagnosis for high-speed train traction systems via stacked generalization. IEEE Transactions on Cybernetics2022; 52: 7624–7633.
36.
LinRTsaiJAlonsoJMGacioD.Four-parameter Taylor series-based Light-Emitting-Diode model. IEEE Journal of Emerging and Selected Topics in Power Electronics2015; 3: 581–588.
Gupta BakshiBRoyB. Electrical model formulation for multicolor light-emitting diode modules and its application to design dimmable driver. International Journal of Circuit Theory and Applications2021; 49: 1559–1582.
39.
Gupta BakshiBLaskarSWasifS.Dual-output flyback driver topologies for tunable white LED lighting applications. 2022 IEEE Calcutta Conference (CALCON), Kolkata, India, 10–11December2022: 55–59.
40.
PadiyarUSKamathV.Design and implementation of a universal input flyback converter. 2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT), Chennai, India, 3–5March2016: 3428–3433.
41.
RameshCHVShettySKulkarniSVBallalR.Design and implementation of flyback converter topology for dual DC outputs. In: Emerging Research in Computing, Information, Communication and Applications. Lecture Notes in Electrical Engineering, Volume 928. Singapore: Springer, 2023: 87–98.
42.
GhoneimSSMRashedAEElkalashyNI. Fault detection algorithms for achieving service continuity in photovoltaic farms. Intelligent Automation and Soft Computing2021; 30: 467–479.
RoelofsR.Measuring generalization and overfitting in machine learning. Doctor of Philosophy dissertation, Electrical Engineering and Computer Sciences, University of California at Berkeley, USA, 2019.
47.
ZhangDGongY.The comparison of LightGBM and XGBoost coupling factor analysis and prediagnosis of acute liver failure. IEEE Access2020; 8: 220990–221003.
48.
NugrohoASuhartantoH.Hyper-parameter tuning based on random search for DenseNet optimization. 2020 7th International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE), Semarang, Indonesia, 24–25September2020: 96–99.
49.
gradio.app. Build & share delightful machine learning apps. Retrieved 7 May 2023 from https://gradio.app/
