Reliability testing and machine learning approach for modelling high-power light-emitting diode reliability

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26210%2F26%3A0201476" target="_blank" >RIV/00216305:26210/26:0201476 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1051/matecconf/202541303005" target="_blank" >https://doi.org/10.1051/matecconf/202541303005</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1051/matecconf/202541303005" target="_blank" >10.1051/matecconf/202541303005</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Reliability testing and machine learning approach for modelling high-power light-emitting diode reliability

Popis výsledku v původním jazyce

The high-power Light Emitting Diode (LED) is a specialized type of LED that has found extensive use in a wide array of fields, particularly in areas such as lighting, signalling, and medical applications due to their cost-effectiveness and replace-ability. As a result of significant technological advancements, high-power LEDs have undergone rapid development, leading to improvements in quality, variety, and application. Within the realm of reliability research, high-power LEDs have garnered considerable attention. The primary aim of this paper is to conduct a comprehensive exploration and analysis of the existing methodologies for testing the reliability of high-power LEDs. This endeavour will involve a thorough investigation into the types of objects utilized for testing, the diverse testing methods employed, the techniques for data collection, and the parameters measured during testing. Furthermore, the paper aims to delve into the potential application of machine learning techniques for modelling, estimating, and predicting the reliability of high-power LEDs. The anticipated outcomes of this paper are intended to establish the foundation for the adoption of innovative approaches in reliability testing and to enhance the prediction and estimation of high-power LEDs reliability.

Název v anglickém jazyce

Reliability testing and machine learning approach for modelling high-power light-emitting diode reliability

Popis výsledku anglicky

The high-power Light Emitting Diode (LED) is a specialized type of LED that has found extensive use in a wide array of fields, particularly in areas such as lighting, signalling, and medical applications due to their cost-effectiveness and replace-ability. As a result of significant technological advancements, high-power LEDs have undergone rapid development, leading to improvements in quality, variety, and application. Within the realm of reliability research, high-power LEDs have garnered considerable attention. The primary aim of this paper is to conduct a comprehensive exploration and analysis of the existing methodologies for testing the reliability of high-power LEDs. This endeavour will involve a thorough investigation into the types of objects utilized for testing, the diverse testing methods employed, the techniques for data collection, and the parameters measured during testing. Furthermore, the paper aims to delve into the potential application of machine learning techniques for modelling, estimating, and predicting the reliability of high-power LEDs. The anticipated outcomes of this paper are intended to establish the foundation for the adoption of innovative approaches in reliability testing and to enhance the prediction and estimation of high-power LEDs reliability.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

21100 - Other engineering and technologies

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

MATEC web of conferences

ISSN

2274-7214

e-ISSN

2261-236X

Svazek periodika

2025

Číslo periodika v rámci svazku

413

Stát vydavatele periodika

FR - Francouzská republika

Počet stran výsledku

6

Strana od-do

—

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-105018047449