Speed control of electric vehicle by using type-2 fuzzy neural network

The forces of drag, tire and road surface friction resistance, the drive motor characteristics, the hill climbing angle, and other non-linear dynamic factors affect the performance of electric vehicles (EV) tremendously. The proposed self-construction of type-2 fuzzy neural network (SCT2FNN) controller was based on the robust typical type-2 fuzzy neural network (T2FNN) controller. T2FNN with the self-construct parameter and online learning could estimate the angular velocity of the motor operation to control the EV. Hence, SCT2FNN with the self-construct parameter and online learning could promptly track the speed of EV. SCT2FNN also could estimate the torque control of DC motor. The simulation results showed that SCT2FNN controller was more efficient than PID controller, while the speed was controlled by considering the difference of the climbing slope.