A model for predicting the acceleration time histories induced on a two-wheeler mechanical frame has been set up and validated. The model is based on the Artifical Neural Network (ANN) technique and does not introduce any simplifying hypothesis for the physics governing the system. The model accounts for different road roughness, variable vehicle speed and adjustable suspension preload, but other variables of interest can in principle be added without changing the model architekture. The height profile of the road is considered as a random steady-state process characterized by its power spectral density (PSD). The functions describing the road-PSD have been experimentally measured for the pavements of interest. During this study, ANNs have proven to be a viable economical way of modeling suspension behavior. Feedforward neural networks have been successfully trained by means of the back-propagation algorithm. Such networks provide accurate predictions when compared with experimental time histories recorded during typical riding conditions.
Suspension modeling in two-wheelers by artificial neural networks
Modell der Radaufhängung in Zweiradfahrzeugen unter Verwendung von neuronalen Netzen
1997
6 Seiten, 11 Bilder, 7 Quellen
Aufsatz (Konferenz)
Englisch
Suspension modeling in two-wheelers by artificial neural networks
Kraftfahrwesen | 1997
|The suspension of six-wheelers
Engineering Index Backfile | 1927
Springer Verlag | 2012
|Springer Verlag | 2012
|Springer Verlag | 2012
|