RBF-Neural Network Adaptive PID Control for 3-Axis Stabilized Tracking System

The 3-axis stabilized tracking system is a vital part of the anti-aircraft system. To achieve the demand on swiftness, precision and stability, an adaptive PID control algorithm based on RBF-NN is introduced. In order to verify the feasibility of the method, several experiments were taken under the same conditions while using both the traditional PID and the adaptive RBF-NN PID. The steady state error is 0.003¿, and the maximum tracking error is 0.203¿ when the signal frequency is 0.1Hz and the amplitude is 20¿ .The results of experiments proved that the RBF-NN adaptive PID controller performs well in the actual 3-axis stabilized tracking control system.

[1]  Yang Ming.  Design of PID position tracing system based on predictive control , 2004 .

[2]  K.J. Tseng,et al.  Robust adaptive control of a 3-axis motion simulator for instruments testing , 2002, 2002 IEEE 33rd Annual IEEE Power Electronics Specialists Conference. Proceedings (Cat. No.02CH37289).

[3]  Ming-guang Zhang,et al.  Adaptive PID control based on RBF neural network identification , 2005, 17th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'05).

[4]  T.H. Lee,et al.  PID control incorporating RBF-neural network for servo mechanical systems , 2003, IECON'03. 29th Annual Conference of the IEEE Industrial Electronics Society (IEEE Cat. No.03CH37468).