A data fusion approach for track monitoring from multiple in-service trains

Abstract

We present a data fusion approach for enabling data-driven rail-infrastructure monitoring from multiple in-service trains. A number of researchers have proposed using vibration data collected from in-service trains as a low-cost method to monitor track geometry. The majority of this work has focused on developing novel features to extract information about the tracks from data produced by individual sensors on individual trains. We extend this work by presenting a technique to combine extracted features from multiple passes over the tracks from multiple sensors aboard multiple vehicles. There are a number of challenges in combining multiple data sources, like different relative position coordinates depending on the location of the sensor within the train. Furthermore, as the number of sensors increases, the likelihood that some will malfunction also increases. We use a two-step approach that first minimizes position offset errors through data alignment, then fuses the data with a novel adaptive Kalman filter that weights data according to its estimated reliability. We show the efficacy of this approach both through simulations and on a data-set collected from two instrumented trains operating over a one-year period. Combining data from numerous in-service trains allows for more continuous and more reliable data-driven monitoring than analyzing data from any one train alone; as the number of instrumented trains increases, the proposed fusion approach could facilitate track monitoring of entire rail-networks.

Dynamic responses, GPS positions and environmental conditions of two light rail vehicles in Pittsburgh

“…Bottom left figure shows a schematic of the sensor locations on the LRV, and the inside view of the train and one highlighted uni-axle accelerometer are shown in the right hand side pictures. (Figures from paper 11 are reused here with license).…”

“…Also, the likelihood of any sensor malfunctioning increases with increasing number of sensors. To address this problem, our group has developed a data fusion approach 11 . The approach helps to combine raw data (or features extracted from raw data) that is collected from different sensors and from multiple trains for producing more reliable and accurate information than that provided by any individual sensor channel.…”

“…Due to its high cost and interruptions, it is difficult to conduct frequent inspections using a track-geometry car. In recent years, researchers have proposed many indirect track inspection methods using sensors, such as accelerometers and GPS, installed on in-service trains for track geometry monitoring and change detection 3–11 since it can be more reliable than visual inspection and costs less than inspection using a track-geometry car. Also, sensors installed on in-service trains can provide continuous monitoring of the track without affecting regular operations.…”

“…Data fusion methods integrate multiple data sources, such as multiple sensor channels on multiple light rail vehicles, to produce more consistent, accurate, and useful information than that provided by any individual data source. Our group has proposed a data fusion approach that integrates multiple accelerometers and GPS data sources from the same or different vehicles 11 . The DR-Train dataset has many other potential usages.…”

Damage-Sensitive and Domain-Invariant Feature Extraction for Vehicle-Vibration-Based Bridge Health Monitoring

“…The use of vibration signals collected from travelling vehicles to monitor structures ( Figure 1) has recently become a viable alternative to traditional structural health monitoring approaches [2,3,4,5,6,7]. This approach does not require intensive deployment and maintenance.…”