An adaptive decoupling control for three-axis gyro stabilized platform based on neural networks

• Dynamic model of three-axis GSP has been derived based on the Newton–Euler equation.
• The disturbances and uncertainties are estimated by neural networks.
• Better decoupling effect and disturbance rejecting ability are proved by experiments with the proposed method.

In order to improve the tracking and stabilization performance of three-axis gyro stabilized platform, an adaptive decoupling control based on neural networks is developed. The dynamic model of three-axis GSP is developed based on traditional Newton–Euler method. The nonlinearity and coupling system is full-state-linearized using feedback linearization, and neural networks are used to compensate for the disturbances and uncertainties. The stability of the proposed scheme is analyzed by the Lyapunov criterion. Comparative simulations and experiments results show the effectiveness of the proposed control approach compared with the conventional control.