SDTC Neural Network Traction Control of an Electric Vehicle without Differential Gears

Abstract

This paper proposes a sensorless direct torque control (SDTC) neural network traction control approach of an electric vehicle (EV) without differential gears (electrical differential system). The EV is in this case propelled by two induction motor (one for each wheel). Indeed, using two electric in-wheel motors give the possibility to have a torque and speed control in each wheel. This control level improves the EV stability and the safety. The proposed traction control system uses the vehicle speed that is different from wheels speed characterized by slip in the driving mode, as an input. In terms of the analysis and the simulations carried out, the conclusion can be drawn that the proposed system is feasible. Simulation results on a test vehicle propelled by two 37-kW induction motors showed that the proposed SDTC neural network approach operates satisfactorily.

Authors

1. 1Larbi Ben M'hidi University of Oum El Bouaghi
2. 2Université de Bretagne Occidentale
3. 3Centre National de la Recherche Scientifique; Laboratoire de Génie Électrique et Électronique de Paris
4. 4University of Batna 1
5. 5University of Biskra