Mechanical Engineering Commons^™

Vibration-Based Machine Learning Models For Condition Monitoring Of Railroad Rolling Stock, Sergio M. Martinez

Theses and Dissertations

One of the primary causes of rail rolling stock derailments is attributed to bearing and wheel axle failures. The health of train bearings is primarily monitored at target locations through wayside detection systems. This practice is susceptible to bearing failure and potential derailments at points in between these wayside systems. To remedy this, the University Transportation Center for Railway Safety (UTCRS) has developed a wireless onboard monitoring system that can continuously monitor the vibration response, which directly correlates to the health of bearings. This data is used to train regression-based machine learning algorithms and long-term prediction neural networks to predict …

Assessing The Effectiveness And Efficacy Of Wireless Onboard Condition Monitoring Modules In Identifying Defects In Railroad Rolling Stock, Lee R. Cantu

Theses and Dissertations

Many industries have begun shifting into the Internet of Things (IoT) in the 21st century. To help ease this transition for the rail industry, The University Transportation Center for Railway Safety (UTCRS) has partnered with Hum Industrial Technology, Inc. (HUM) to help complete the development of a Wireless Onboard Condition Monitoring system named the ‘Boomerang™’. This product allows customers to schedule proactive maintenance on their railcars to replace defective wheels and/or bearings, saving them time, money and potentially preventing costly catastrophic derailments. The UTCRS research team has established thresholds to determine defective bearings utilizing thermal and mechanical sensors.

The effectiveness …

Development, Optimization, And Implementation Of A Vibration Based Defect Detection Algorithm For Railroad Bearings, Amy Gonzalez

Theses and Dissertations - UTB/UTPA

Of the three main rail accident types in the United States, derailments are the most common. Studies have shown that derailments occurring above 25 mph are caused by equipment failures such as bearing failures. As a preventative measure, condition-monitoring systems are required to detect defective bearings in the field. Based on data compiled from multiple experiments of healthy and defective bearings at UTPA, an algorithm has been devised to identify bearing abnormalities. Vibration analysis techniques are utilized to potentially determine whether a bearing is defective and the defect type and size using the acquired vibration signatures. Implementation of a defect …

Defect Detection In Railroad Tapered-Roller Bearings Using Vibration Analysis Techniques, Iris L. Alvarado

Theses and Dissertations - UTB/UTPA

Derailments can often lead to great damage, loss of lives, and massive costs associated with the railroad infrastructure. A significant cause of derailments is premature bearing failure, and therefore bearing condition-monitoring systems that can detect developing defects are of great importance. Based on an investigation conducted at the University of Texas-Pan American on the development of a vibration and temperature monitoring system, an algorithm is devised utilizing various vibration analysis techniques. The proposed algorithm determines whether a bearing is defective, the type of defect present, the defective component (i.e. cup, cone, or roller), and the size of the defect. Speed-dependent …

A Study Of The Effect Of Vibration On Railroad Bearing Temperature, Bertha Alicia Gonzalez

Theses and Dissertations - UTB/UTPA

An on-track collaborative field test and laboratory experiments were conducted in order to determine the relationship between abrupt rises in surface temperature of a railroad bearing and vibration signatures captured during the experiments. The collaborative field test was conducted in order to investigate the root cause for this abrupt temperature change known as bearing temperature trending. The research presented in this thesis will show that temperature trending is correlated to an increase in the magnitude of vibration within the bearing and the fundamental frequencies that are generated by the internal components of a rotating bearing assembly. Distinct vibration mechanisms are …