Machine Vision Observation, Artificial Intelligence Pattern Recognition, Protective Circuit Design, Characterization of Multiple Materials, and Nano-Structural Analysis for Investigating InGaN Green Light Emitting Diode Degradation in a Salty Water Vapor Environment

This study delves into the degradation of GaN-based LEDs in saline environments, a relatively underexplored area of research. LEDs are known for their longevity, but face challenges under extreme conditions. Utilizing artificial intelligence, machine vision, and material analysis, this study detects...

Full description

Saved in:
Bibliographic Details
Main Authors: Chen, Cheng-Shan, Yang, Chun-Yen, Yang, Shao-Jui, Wang, Deng-Yi, Kuo, Yaw-Wen, Hsiao, Wei-Han, Chou, Hsin-Hung, Lin, Chia-Feng, Li, Yung-Hui, Wu, YewChung Sermon, Chen, Hsiang, Han, Jung
Format: Conference Proceeding
Language:English
Subjects:
Circuit synthesis
Computer science
Degradation
Electrical engineering
InGaN LED degradation
Light emitting diodes
Machine vision
Machine vision and AI recognition
Material characterizations
Protective circuit design
Reliability engineering
Saline mist environment
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study delves into the degradation of GaN-based LEDs in saline environments, a relatively underexplored area of research. LEDs are known for their longevity, but face challenges under extreme conditions. Utilizing artificial intelligence, machine vision, and material analysis, this study detects early signs of LED degradation[1], [2]. The results highlight the impact of saline exposure on LED performance, with some LEDs continuing to function for up to 30 minutes before failure. Advanced circuits ensure uninterrupted operation. Encompassing electrical engineering, computer science, and materials science, this study provides a comprehensive approach to LED fault detection and protection.
ISSN:1938-1891
DOI:10.1109/IRPS48228.2024.10529494