Theses and Dissertations
Date of Award
8-1-2024
Document Type
Thesis
Degree Name
Master of Science in Engineering (MSE)
Department
Mechanical Engineering
First Advisor
Constantine Tarawneh
Second Advisor
Ping Xu
Third Advisor
Arturo Fuentes
Abstract
The University Transportation Center for Railway Safety (UTCRS) has designed an onboard monitoring system that tracks vibration waveforms over time, to obtain a direct and more accurate indicator of bearing health. The data collected by these sensors is used for vibrational analyses of the bearings. The speed of the bearing is a fundamental parameter needed to carry out the analysis. GPS data can be used to determine bearing speed if available; however, due to size, cost and power constraints GPS is typically not available at the sensor location. This means that analysis must be delayed until the data is uploaded to a location where it can be matched with GPS data, unless the speed is determined immediately at the bearing. It is proposed to solve this problem with the introduction of Machine Learning (ML) algorithm that would extract features, such as the speed, from the vibration data that is already being acquired by the onboard sensing module. The PSD plots contain embedded signatures corresponding to the speed. Rapid extraction of this data would allow for real time analysis of bearing condition as the train is moving, which could be sent to a cloud accessible by train dispatchers and railcar owners for assessment of bearing health and scheduling of proactive maintenance before defects reach a critical size.
Recommended Citation
Quaye, Kevin, "Feature Extraction From Vibration Signature Acquired From Railroad Bearing Onboard Condition Monitoring Sensor Modules" (2024). Theses and Dissertations. 1600.
https://scholarworks.utrgv.edu/etd/1600
Comments
Copyright 2024 Kevin Quaye. https://proquest.com/docview/3115384932