High-power white light-emitting diodes (LEDs) have demonstrated superior efficiency and reliability compared to traditional white light sources. However, ensuring maximum performance for a prolonged lifetime use presents a significant challenge for manufacturers and end users, especially in safety–critical applications. Thus, identifying functional anomalies and predicting the remaining useful lifetime (RUL) is of enormous importance in the operational longevity of the device. To address such challenges, this study proposes a combination of distance-based Mahalanobis distance (MD), entropy generation rate (EGR), and deep learning models for improved anomaly detection and RUL prediction accuracy. Unlike conventional health indicators based on luminous flux data that are challenging to monitor relevant optical performance, the MD and EGR methods are employed to extract in-situ monitored thermal and electrical data as new health indicators. Long short-term memory recurrent neural networks (LSTM-RNN) and convolutional neural networks (CNN) are established to detect anomalies and predict the RUL. The accelerated degradation tests of 3 W high-power white LED have been conducted, and the online and offline collected experimental data are deployed for model development and performance evaluation. The performance of the proposed methods is compared against the Illuminating Engineering Society of North America (IESNA) TM-21 method. The results indicate that LSTM-RNN, when combined with either MD or EGR, can detect anomalies with significantly fewer data (70 %) than is typically required. Furthermore, a significant improvement in prediction accuracy in RUL prediction based on MD and EGR-constructed time series health indicators and employed with the LSTM-RNN model demonstrates the effectiveness of the proposed methods.

@en

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.@en

With their advantages of high efficiency, long lifetime, compact size and being free of mercury, ultraviolet light-emitting diodes (UV LEDs) are widely applied in disinfection and purification, photolithography, curing and biomedical devices. However, it is challenging to assess the reliability of UV LEDs based on the traditional life test or even the accelerated life test. In this paper, radiation power degradation modeling is proposed to estimate the lifetime of UV LEDs under both constant stress and step stress degradation tests. Stochastic data-driven predictions with both Gamma process and Wiener process methods are implemented, and the degradation mechanisms occurring under different aging conditions are also analyzed. The results show that, compared to least squares regression in the IESNA TM-21 industry standard recommended by the Illuminating Engineering Society of North America (IESNA), the proposed stochastic data-driven methods can predict the lifetime with high accuracy and narrow confidence intervals, which confirms that they provide more reliable information than the IESNA TM-21 standard with greater robustness.

@en

The LED degradation failure is highly dependent on temperature and this degradation failure is an irreversible energy dissipation process in thermodynamics. In this paper, the entropy generation is used to quantify the energy dissipation, which is regarded as one of the main performance characteristics of LED's degradation process. Considering the thermodynamic characteristics of entropy generation in the LED failure, a hybrid degradation prediction model based on the permutation entropy (PE) and data-driven methods was proposed. Firstly, a thermal aging test was designed for white LEDs in which the entropy generation rates (EGRs) of LEDs were extracted from the online collected thermoelectric performance parameters. Then, the EGRs of LEDs were treated as a time-series signal to perform phase space reconstruction and calculate PEs. Finally, both neural network model and Wiener process based data-driven methods were used to process the PEs. This hybrid model links the thermodynamic entropy of LEDs with its optical performance. The results show that: (1) Entropy generation based on thermodynamics can characterize the degradation process of LEDs; (2) The proposed hybrid degradation prediction model based on the PE and Wiener method can achieve early failure warning of LEDs before the actual failure occurs.@en

The increased system complexity in electronic products brings challenges in a system level reliability assessment and lifetime estimation. Traditionally, the graph model-based reliability block diagrams (RBD) and fault tree analysis (FTA) have been used to assess the reliability of products and systems. However, these methods are based on deterministic relationships between components that introduce prediction inaccuracy. To fill the gap, a Bayesian Network (BN) method is introduced that considers the intricacies of the high-power light-emitting diode (LED) lamp system and the functional interaction among components for reliability assessment and lifetime prediction. An accelerated degradation test was conducted to analyze the evolution of the degradation and failure of components that influence the system level lifetime and performance of LED lamps. The Gamma process and Weibull distribution are used for component level lifetime prediction. The junction tree algorithm was deployed in the BN structure to estimate the joint probability distributions of the lifetime states. The degradation and prediction results showed that LED modules contribute a major part for lumen degradation of LED lamps followed by drivers and the least effect is from diffuser and reflector. The BN based lifetime estimation results also exhibited an accurate prediction as validated with the Gamma process and such improved reliability assessment outcomes are beneficial to LED manufacturers and customers. Thus, the proposed approach is effective to evaluate and address the long-term reliability assessment concerns of high-reliability LED lamps and fulfill the guarantee of high prediction accuracy in less time and cost-effective manner.

@en

Ultraviolet light-emitting diodes (UV LEDs) play an important role in inactivating novel coronavirus pneumonia, but the lack of rapid lifetime prediction can easily cause untimely failure detection, long product development cycles, and high costs. This study predicts the lifetime of UV LEDs based on the long short-term memory (LSTM) recurrent neural network (RNN). First, the equipment setup was designed to conduct an aging test to obtain a predicted length of life for the UV LED samples using a Weibull distribution. Next, LSTM RNN was employed to predict the lifetime of the UV LEDs based on the radiation power degradation. The results were then compared with those from nonlinear least squares (NLS) regression recommended by the IESNA TM-21 industry standard. Finally, the robustness of the two methods was analyzed by changing the starting times of the predictions. The results showed that the LSTM RNN proposed in this letter reveals not only a 29.7% lower lifetime prediction error compared with the NLS regression, but also a more stable robustness. Thus, the LSTM RNN method is found to be more accurate and more robust in predicting the lifetime of UV LEDs.

@en

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.

@en