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.

The introduction of high-power white LEDs has revolutionized the lighting industry in the past few decades due to the multiple benefits in terms of high reliability, environmental friendliness and versatile applications. However, challenges have arisen in assessing the reliability and lifetime prediction because it is difficult to record the failure data in a short period of time. Currently, the nonlinear least squares (NLS) regression-based method is used in industry for projecting the lumen maintenance lifetime from degradation data. The model parameters estimated using the NLS regression approach are deterministic and introduce high prediction errors. In this paper, a Bayesian method is proposed to estimate the remaining useful lifetimes (RULs) of both high-power white LED packages and lamps. The accelerated degradation tests conducted for gathering lumen degradation data are used to validate the proposed method. The exponential decay model is used as the degradation model and the parameters are estimated based on Markov Chain Monte Carlo (MCMC) sampling and using the Metropolis-Hasting (MH) algorithm. The lifetime prediction results showed that the Bayesian method has better prediction accuracy compared to the NLS method. Thus, the proposed Bayesian method is shown to be a promising approach to address the lifetime prediction issue for high-power white LEDs with improved prediction accuracy.

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.

Nowadays, due to the advancement of design and manufacturing technology, there are many consumer products with high reliability. Similarly, the competition in the business sector influences the product development time to become shorter and that makes it difficult for manufacturers to evaluate the reliability of current products before new products are released to the market. This phenomenon is manifested in the lighting industry, especially for the high power white light-emitting diodes (LEDs) as these products have a long lifetime and high reliability. Currently, the standard to predict the lifetime of LEDs is based on a deterministic nonlinear least squares method which has low prediction accuracy. To overcome this, degradation models are being used to study the reliability of such products, considering the uncertainties and the quality characteristics whose degradation over a period of time can be related to the product lifetime. A stochastic approach based on gamma distributed degradation (GDD) is proposed in this study to estimate the long-term lumen degradation lifetime of phosphor-converted white LEDs. An accelerated thermal degradation test was designed to gather luminous flux degradation data which was analyzed based on maximum likelihood estimation (MLE) and the method of moments (MM) to estimate the parameters for the GDD model. The MLE method has shown superiority over MM in terms of the estimation of the model parameters due to its iterative algorithm being likely to find the optimal estimation. The lifetime prediction results show that the accuracy of the proposed method is much better than the TM-21 nonlinear least squares (NLS) approach which makes it promising for future industrial applications.