Real-Time Neural Network-based Self-Tuning Control of a Nonlinear Electro-Hydraulic Servomotor

J.I. Canelon, A.G. Ortega (Venezuela), L.S. Shieh (USA), J.I. Bastidas (Venezuela), Y. Zhang, and C.M. Akujuobi (USA)


Self-tuning control, Neural networks, Kalman innovation model, Electro-hydraulic servomotor


This paper describes the real-time implementation of a neural network-based approach, for self-tuning control of the angular position of a nonlinear electro-hydraulic servomotor. According to the approach, a neural network (NN) autoregressive moving-average model with exogenous input (ARMAX) model of the system is identified and continuously updated, using an online training algorithm. Then, an optimal linear ARMAX model is determined from the identified NN-ARMAX model. A Kalman innovation model in the observable block companion form is directly constructed using the parameters in the linear ARMAX model. Control design is accomplished by solving an optimal discrete-time linear quadratic tracking problem, using the Kalman innovation model in the observable block companion form. The state-feedback control law is implemented using the Kalman estimated state, which is calculated from the identified parameters, without estimating the noise covariance properties. Results show that the neural network-based self-tuning approach can be successfully implemented for real-time control of a real system with fast dynamics.

Important Links:

Go Back