Principal Investigators/Researcher

Nii Attoh-Okine, University of Delaware

Project Description

The multi-modal transportation network in which the freight rail plays an essential role continues to enhance the United States’ contributions in the global market. For years, track geometry defects data are often gathered by visual inspections. However, automated track vehicles are now deployed for the same purpose to save time and cost. One of the limitations of an automated vehicle is the likelihood of non-stationarity of the gathered data due to external influence. The effect of non-stationarity may lead to the wrong representation of track conditions and thereby increases the possibility of false model output. This study applies the supervised Machine Learning (ML) methods to detect the non-stationarity of the geometry data. The methods include Random Forest (RF), Logistic Regression (LR), and Support Vector Machine (SVM). The authors vary the train-test and validation ratio in phases to ascertain each Machine Learning methods’ accuracy and adaptability to different distributions. In the first phase, the Random Forest and the Support Vector Machine show an accuracy of 97.1% while the Logistic Regression reveals 96% accuracy. In the second and third phases, the Random forest method gives a better result than other supervised learners with an accuracy of 97% and 97.1% respectively. Similarly, for validation, the Random Forest performs better than other classifiers with an accuracy of 98%. Conclusively, the developed models’ application indicates that the Random Forest is a more effective approach to detecting non-stationarity of track geometry data.  

Implementation of Research Outcomes

On-going

Impacts/Benefits of Implementation

N/A