In-trainNet: A Two-Step Data-Driven Framework for Enhancing Railway In-Train Forces Monitoring

Abstract

Railway in-train forces are critical for ensuring safe and efficient train operations. However, real-time monitoring of these forces across multiple couplers in various trains remains challenge due to variations in train configurations and coupler locations. This paper proposes In-trainNet, a two-step data-driven framework that leverages automatic train operation system to enhance in-train forces monitoring. In the first step, a specially designed multi-task model is pre-trained to simultaneously estimate multiple in-train forces on multiple couplers for a specific train configuration. In the second step, a transfer learning scheme transfers and adapts the pre-trained model to different train configurations, significantly reducing the need for extensive training data and computational resources. Comparative experiments demonstrate the superior performance of the pre-trained model, which achieves higher accuracy and efficiency compared to single-task models. The integration of transfer learning further enhances the framework’s adaptability, enabling robust and accurate monitoring across diverse train configurations. The proposed approach offers a promising solution for real-time, in-situ monitoring of railway in-train forces, with potential applications in both research and industrial applications.