Neural — Adaptive control based on backstepping and feedback linearization for electro hydraulic servo system

Abstract

In this study Neural Adaptive based on backstepping and feedback linearization is used for velocity control and recognition of an electro hydraulic servo system (EHSS) in the presence of flow nonlinearities, internal friction and noise. This controller consists of three parts: PID controller, nonlinear controller (i.e. Backstepping or Feedback Linearization) and neural network controller. The backstepping or feedback linearization controller is utilized to avert the system state in a region where the neural network can be accurately trained to achieve optimal control. The combination of controllers is used for producing a stable system which adapts to optimize performance. It is shown that this technique can be successfully used to stabilize any chosen operating point of the system with noise and without interference. All derived results are validated by computer simulation of a nonlinear mathematical model of the system. The controllers which introduced have a big range to control the system. We compare both Neural Adaptive based on backstepping and Neural Adaptive based on feedback linearization controllers result with feedback linearization, backstepping and PID controller.