Monitoring of lateral and cross level track geometry irregularities through onboard vehicle dynamics measurements using machine learning classification algorithms
| Autor: | Mats Berg, A De Rosa, Alan Facchinetti, Stefano Bruni, Rohan Kulkarni, E. Di Gialleonardo, Alireza Qazizadeh |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
lateral dynamics
Vehicle Engineering fault classifier Computer science business.industry Mechanical Engineering Decision tree 020302 automobile design & engineering 02 engineering and technology Farkostteknik High-speed railway Vehicle dynamics Support vector machine Statistical classification Vehicle engineering 020303 mechanical engineering & transports 0203 mechanical engineering onboard diagnostics decision tree Computer vision Track geometry support vector machine Artificial intelligence business |
| Popis: | In recent years, significant studies have focused on monitoring the track geometry irregularities through measurements of vehicle dynamics acquired onboard. Most of these studies analyse the vertical irregularity and the vertical vehicle dynamics since the lateral direction is much more challenging due to the non-linearities caused by the contact between the wheels and the rails. In the present work, a machine learning-based fault classifier for the condition monitoring of track irregularities in the lateral direction is proposed. The classifiers are trained with a dataset composed of numerical simulation results and validated with a dataset of measurements acquired by a diagnostic vehicle on the straight track sections of a high-speed line (300 km/h). Classifiers based on decision tree, linear and Gaussian support vector machine algorithms are developed and compared in terms of performance: good results are achieved with the three algorithms, especially with the Gaussian support vector machine. Even though classifiers are data driven, they retain the essence of lateral dynamics. QC 20200302 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|