A Method of Neural Networks Controller Design for Electric Steering Actuator

To overcome the effect of nonlinear disturbance, the electric steering actuator controller design method based on neural networks is introduced. Firstly, the actuator control system is designed according to the requirement of flight control systems. Then, considering the dynamics of actuators, the nonlinear mathematical model of actuators is built, and the controller is designed with proportion-integral–differential and neural network control method. Finally, two control methods are contrasted. The simulation result demonstrates that NN controller can do it better in removing the influence of uncertainty and disturbance to achieve satisfying control effect.

[1]  Mohammed Y. Hassan,et al.  Comparison between Neural Network based PI and PID controllers , 2010, 2010 7th International Multi- Conference on Systems, Signals and Devices.

[2]  F.C. Sun,et al.  Actuator Nonlinearities Compensation Using RBF Neural Networks in Robot Control System , 2006, The Proceedings of the Multiconference on "Computational Engineering in Systems Applications".

[3]  Eugênio B. Castelan,et al.  Neural Dynamic Control of a Nonholonomic Mobile Robot Incorporating the Actuator Dynamics , 2008, 2008 International Conference on Computational Intelligence for Modelling Control & Automation.

[4]  M. Ohka,et al.  Parallel Type Two-axial Actuator Controlled by a Multi-layered Neural Network , 2007, 2007 International Symposium on Micro-NanoMechatronics and Human Science.

[5]  Zhiyong Tang,et al.  Model reference adaptive PID control of hydraulic parallel robot based on RBF neural network , 2007, 2007 IEEE International Conference on Robotics and Biomimetics (ROBIO).