Neural network fuzzy control for enhancing the stability performance of quad-rotor helicopter

Recently, the quad-rotor helicopter has gained increasing attention owing to its very good flexibility, its ability to execute various flight missions even in harsh environments. The quad-rotor helicopter can implement different fight attitudes, which is attributed to the effective control of the motor speed about four propellers. In order to make the quad-rotor helicopter can better finish flight mission, the performance of flight stability then becomes particularly important. A neural network fuzzy control algorithm is proposed in this paper so as to guarantee the stability performance of the quad-rotor helicopter. The proposed algorithm is based on the neural network, which keeps the self-organization and self-learning ability, besides this, it utilizes the strong impression ability of constitutive knowledge as to the fuzzy logic. The proposed control scheme aims to implement good abilities such as describing qualitative knowledge, strong learning mechanism and direct processing about quantitative data of the quad-rotor helicopter. In the practical flight process of the quad-rotor helicopter, while the deviation of position and attitude information become larger, fuzzy control is adopted so as to shorten the overshoot and adjustment time. On the other hand, if the deviation of position and attitude become relatively smaller, neural network PID control will be used so as to reduce the error. Experimental results show that the proposed neural network fuzzy control algorithm exhibits good performance in the flight process of the quad-rotor helicopter.