Equipment Vibration Condition Monitoring Technology Based on Spectrum Image Deep Learning Models

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Oct 28, 2022
Gun Sik Kim Deog Hyeon Kim Jae Min Lee Jin Woo Park

Abstract

We created a system that predicts failures in advance by analyzing the equipment spectrum for rotating equipment operated by Hyundai and Kia Motors. In the case of spectrum analysis through existing equipment rotation speed order tracking, if the equipment rotation speed or specifications change, it is often useless. To this end, we extracted and trained equipment spectrum images in various ways, and made it possible to know what kind of failure there is when a new spectrum is received. For easy use, (1) facility maintenance history management system (2) spectrum image collection program (3) spectrum image learning program (4) spectrum automatic analysis (5) analysis result UI and mailing service were developed separately.

How to Cite

Kim, G. S., Kim, D. H., Lee, J. M., & Park, J. W. (2022). Equipment Vibration Condition Monitoring Technology Based on Spectrum Image Deep Learning Models. Annual Conference of the PHM Society, 14(1). https://doi.org/10.36001/phmconf.2022.v14i1.3218
Abstract 507 | PDF Downloads 502

##plugins.themes.bootstrap3.article.details##

Keywords

Condition Monitoring; Sensors, Signal Analysis, Failure Analysis; From PHM and CBM considerations to Maintenance; Predictive Maintenance

References
Razvan-Gabriel Cirstea (2018). Correlated Time Series Forecasting using Deep Neural Networks: A Summary of Results. arXiv:1808.09794
Shuai Zheng (2017). Long Short-Term Memory Network for Remaining Useful Life Estimation. IEEE ICPHM. 978-1-5090-0382-2/16
Khan, S. and Yairi, T (2018). A review on the application of deep learning in system health management. Mechanical Systems and Signal Processing, 107, pp.241-265
Section
Technical Research Papers