Theses and Dissertations
Date of Award
12-1-2025
Document Type
Thesis
Degree Name
Master of Science in Engineering (MSE)
Department
Mechanical Engineering
First Advisor
Constantine Tarawneh
Second Advisor
Ping Xu
Third Advisor
Heinrich Foltz
Abstract
The University Transportation Center for Railway Safety (UTCRS) has developed an algorithm capable of identifying defective railroad bearings, determining damaged component(s) within, and quantifying severity of the defects. The defect-detection algorithm requires the operating speed as an input, which is not readily available in field operation of onboard sensors. Therefore, onboard sensors deployed in rail revenue service must rely on Global Positioning Systems (GPS) to obtain speed, which can be power-intensive and susceptible to signal interference. This study covers the development of a vibration-based model that extracts operating speed from wireless sensor data to enable fully autonomous onboard diagnostics. Signal filtering and envelope-analysis are applied to extract the fundamental defect frequency and its harmonics. The K-Means clustering machine learning algorithm then estimates the rotational speed across multiple filter-envelope combinations. The resulting model produces reliable speed extraction, supporting real-time integration of the UTCRS bearing health monitoring algorithm in field service conditions.
Recommended Citation
Cantu, D. (2025). Feature Extraction From Railroad Bearing Onboard Vibration Sensors Using Machine Learning Models [Master's thesis, The University of Texas Rio Grande Valley]. ScholarWorks @ UTRGV. https://scholarworks.utrgv.edu/etd/1862
Comments
Copyright 2025 Diego Cantu. All Rights Reserved. https://proquest.com/docview/3371399385