MPC Research Reports |
Title: | Intelligent Transportation Systems Approach to Railroad Infrastructure Performance Evaluation: Track Surface Abnormality Identification with Smartphone-Based App |
Authors: | Pan Lu, Raj Bridgelall, Denver Tolliver, Leonard Chia, and Bhavana Bhardwaj |
University: | North Dakota State University |
Publication Date: | Jul 2019 |
Report #: | MPC-19-384 |
Project #: | MPC-505 |
TRID #: | 01715250 |
Keywords: | algorithms, flaw detection, information processing, inspection, intelligent transportation systems, maintenance of way, mobile applications, railroad safety, railroad tracks, sensors, validation |
Federal track safety regulations require railroads to inspect all tracks in operation as often as twice weekly. Railroad companies deploy expensive and relatively slow methods using human inspectors and expensive automated inspection vehicles to inspect and monitor their rail tracks. The current practices are not only expensive and decrease rail productivity by taking away track time to perform inspection, but also increase the safety risk for railway inspection workers.
Sensors, such as inertial sensors, accelerometers, gyroscopic sensors, and global positioning system (GPS), are carried on a railway vehicle to continually monitor and inspect rail assets to meet the growing safety improvement needs for reliable and low-cost rail operations. Smartphones use such sensor networks, including wireless communication microchips. In this research, smartphone-based signaling data collection applications, data fusion algorithms, and data processing algorithms to detect a wide variety of possible track surface abnormalities are developed and validated.
The research methods will not rely on adapting sensor configurations, and will require only a data upload capability. The new sensors will compress and upload their geo-tagged inertial data periodically to a centralized processor. Remote algorithms will combine and process the data from multiple train traversals to identify abnormal track surface symptoms, and localize their positions. Track surface abnormality identification will enable asset managers to allocate the appropriate specialists to scrutinize the abnormality location.
Lu, Pan, Raj Bridgelall, Denver Tolliver, Leonard Chia, and Bhavana Bhardwaj. Intelligent Transportation Systems Approach to Railroad Infrastructure Performance Evaluation: Track Surface Abnormality Identification with Smartphone-Based App, MPC-19-384. North Dakota State University - Upper Great Plains Transportation Institute, Fargo: Mountain-Plains Consortium, 2019.