Skip to main content
2024 47th International Conference on Telecommunications and Signal Processing (TSP)

Full Program »
Video (.mp4)
View File

Comparative Analysis of Boosting Algorithms for Contactor Fault Classification from Fiber Bragg Grating Sensor Signals

It is important for safety to monitor the structural health of AC contactors and intervene in advance where possible. This is possible with fiber Bragg grating sensors that can take measurements with high precision and speed, and machine learning algorithms that can perform fast and highly accurate fault detection from sensor data. In this study, fault classification was performed using vibration data obtained with the FBG sensor placed on a contactor. In the classification study, 4 different boosting algorithms were analyzed comparatively. According to the results obtained, the light gradient boosting machine algorithm classified 4 different fault conditions with 85% accuracy. The lowest accuracy rate of 66% was obtained with Adaptive Boosting algorithm.

Serif Ali Sadik
Kütahya Dumlupınar University


Privacy Policy

Powered by OpenConf®
Copyright ©2002-2024 Zakon Group LLC