Learn to Predict Vertical Track Irregularity with Extremely Imbalanced Data
This work provides a more precise and efficient approach for railway operators to detect track deformation, which is crucial for train safety and reducing maintenance costs.
This paper addresses the challenge of predicting vertical track irregularity using a large-scale, real-world dataset from Chinese railways. The authors developed an application framework and proposed a novel approach combining adaptive data sampling and penalized loss to handle extremely imbalanced data, which improved performance in predicting rare extreme values.
Railway systems require regular manual maintenance, a large part of which is dedicated to inspecting track deformation. Such deformation might severely impact trains' runtime security, whereas such inspections remain costly for both finance and human resources. Therefore, a more precise and efficient approach to detect railway track deformation is in urgent need. In this paper, we showcase an application framework for predicting vertical track irregularity, based on a real-world, large-scale dataset produced by several operating railways in China. We have conducted extensive experiments on various machine learning & ensemble learning algorithms in an effort to maximize the model's capability in capturing any irregularity. We also proposed a novel approach for handling imbalanced data in multivariate time series prediction tasks with adaptive data sampling and penalized loss. Such an approach has proven to reduce models' sensitivity to the imbalanced target domain, thus improving its performance in predicting rare extreme values.