A neural network model of electric differential system for electric vehicle

This paper describes a neural network model for an electrical differential system for electric vehicle. When a vehicle drives along curved road lane, the speed of the inner wheel has to be different from that of the outer wheel in order to prevent the vehicle vibrating and traveling an unsteady path. Because each wheel of this electrical vehicle has an independent driving force, an electrical differential system is required to replace a gear differential system. However, it is difficult to analysis the nonlinear behavior of the differential system in relation to the vehicle speed and steering angle, as well as vehicle structure. Therefore, a neural network is used to learn the relationships. To realize the neural network model, the speed data was acquired for the inner wheel and outer wheel, using an experimental electric vehicle at various speeds and steering angles. With this information, the differential system can be controlled using a neural network model of the nonlinear relationships.