An investigation into wayside hot-box detector efficacy and optimization

Abstract

Wayside hot-box detectors (HBDs) are devices used to assess the health of railcar components including bearings, axles, and brakes by monitoring their temperatures. HBDs use infrared (IR) sensors to record the temperatures of railroad bearings. Bearings that trigger an alarm or exhibit warm trending are removed and sent for inspection. In many cases, no discernable defects were found in the flagged bearings. Motivated by this finding, an investigation was conducted which included performing a controlled field test as well as exhaustive laboratory testing utilizing an HBD simulator. Data acquired from field and laboratory testing was used to evaluate the accuracy and efficacy of wayside HBDs. The results suggest that the scanning location on the bearing cup significantly affects the temperature measurement. Different calibrations for the field-and laboratory-acquired data were also explored. An optimized calibration technique along with proper IR sensor alignment can markedly improve the accuracy of HBD measurements.

WITHDRAWN: New Perspectives for the Intelligent Rolling Stock Classification in Railways: An Artificial Neural Networks-Based Approach

“…In this context, a great number of trains are used constantly, which may promote stress in these trains' components, causing a lifetime reduction and, consequently, increasing the maintenance costs. An example is presented in [2] and [3], which describe the heating in the wheels and bearings, which can cause failure, resulting in catastrophic derailments. Thus, it is essential to observe the components involved in rail transportation to decrease maintenance costs and improve their performance.…”

Moving train wheel axles automated detection, counting, and tracking by combining AI with Kalman filter applied to thermal infrared image sequences

“…Second, precise temperature measurements rely on accurate calibration of the scanning zone of these systems. 2 Moreover, their operation is contingent upon the availability of other facilities, such as triggers that are responsible for activating and deactivating the system.…”

Quantification of the Effect of Train Type on Concrete Sleeper Ballast Pressure Using a Support Condition Back-Calculator

“…Distributed motive power, Positive Train Control (PTC) (Resor et al, 2005), Automatic Train Control (ATC) (Kim et al, 2015), and self-driving cars (Bruner, 2018) are examples of implementing technology to improve safety and efficiency of transportation operations. And while wheel impact load detectors (WILDs) (Van Dyk, 2014) and hot bearing detectors (Tarawneh et al, 2020) have been around for decades, there is increased interest in analyzing data from these systems to develop predictive maintenance strategies for the rolling stock. Autonomous track geometry measurement systems (ATGMS) (Van Dyk, 2014;Saadat et al, 2018), unmanned aerial vehicles (UAVs) (Baniae et al, 2019), and machine vision and laser-based inspection systems (Ye et al, 2019;Fox-Ivey et al, 2020) are being developed and deployed to provide actionable information about the overall state of the track's health (Stuart et al, 2012;Saadat et al, 2014).…”