Artificial neural networks applied to the measurement of lateral wheel-rail contact force: A comparison with a harmonic cancellation method
This 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 mathem...
| Autores: | , , , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión aceptada para publicación |
| Fecha de publicación: | 2020 |
| País: | España |
| Institución: | Universidad de Sevilla (US) |
| Repositorio: | idUS. Depósito de Investigación de la Universidad de Sevilla |
| OAI Identifier: | oai:idus.us.es:11441/162078 |
| Acceso en línea: | https://hdl.handle.net/11441/162078 https://doi.org/10.1016/j.mechmachtheory.2020.103968 |
| Access Level: | acceso abierto |
| Palabra clave: | Artificial neural network Multibody system Contact force measurement Scaled railway vehicle Dynamometric wheelset Experimental validation |
| Sumario: | This 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. |
|---|