Urda, PedroFernández-Aceituno, JavierMuñoz-Moreno, SergioEscalona, José Luis2024-01-312024-01-3120200094-114Xhttps://doi.org/10.1016/j.mechmachtheory.2020.103968https://hdl.handle.net/10953/1771This paper presents a method for the experimental measurement of the lateral wheel-rail contact force based on Artificial Neural Networks (ANN). It is intended to demonstrate how an Artificial Intelligence (AI) method proves to be a valid alternative to other approaches based on sophisticated mathematical models when it is applied to the wheel-rail contact force measurement problem. This manuscript addresses the problem from a computational and experimental approach. The artificial intelligence algorithm has been experimentally tested in a real scenario using a 1:10 instrumented scaled railway vehicle equipped with a dynamometric wheelset running on a 5-inch-wide track. The obtained results show that the ANN approach is an easy and computationally efficient method to measure the applied lateral force on the instrumented wheel that requires the use of fewer sensors.engArtificial neural networkMultibody systemContact force measurementScaled railway vehicleDynamometric wheelsetExperimental validationinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/openAccess