• In-trainNet enhances versality and efficiency in monitoring in-train forces by a multi-task transfer learning framework. • Pre-trained multi-task model effectively and efficiently estimates in-train forces on multiple couplers. • Transfer learning adapts pre-trained knowledge to various train configurations with small-scale data. • Robust and accurate performance of In-trainNet validated by comprehensive comparative experiments. 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.

Railway in-train forces are an essential element in assessing multiple aspects of rolling stocks. Conventional methods for obtaining the forces can be time-consuming and require significant investment in manpower and domain expertise, while only gathering the force data for specific service conditions one at a time. However, automatic train operation (ATO) systems can measure real-time information for trains and tracks by on-board and trackside devices, which could provide an opportunity for in-train forces monitoring. This paper presents a data-driven approach that uses ATO-measured data and a neural network model to monitor in-train forces under service conditions. To develop this approach, longitudinal train dynamics simulations (LTSs) for a freight train were conducted to establish the relationship between ATO measurements and in-train forces on specific couplers, which was embedded in a large amount of training data. After that, a specially developed self-attention-based causal convolutional neural network (SA-CNN) was employed to learn the underlying relationship and estimate the in-train force histories considering temporal dependencies. The comparative evaluation between the SA-CNN against four alternative neural network models revealed that the SA-CNN exhibits a slightly higher level of accuracy. Furthermore, the generalisation capability of the well-trained SA-CNN model was confirmed by numerical LTSs under four different service conditions. The results indicated that the data-driven approach has superior compatibility for arbitrarily combined inputs with significantly reduced computational time compared to LTSs. This approach holds the potential for achieving reliable in-situ monitoring of railway in-train forces, which is beneficial to both in-train force-related research and industrial applications.