Disturbance estimation for the hydraulic drive system based on the state observer and neural network

Abstract

The hydraulic servo drive system has the ability to operate stably with high reliability in conditions of continuous operation and large capacity. Aside from these advantages, the system always has nonlinear and uncertain factors that affect and reduce the quality of the controller. These factors include the affected disturbances and the uncertainty of the system model. This paper proposes a method to identify the sum of nonlinear effects and disturbances for the hydraulic drive system, which uses the axial piston pump, based on the application of the Radial Basic Functions neural network (RBF) and state observer model. The simulation results show that the total disturbances and nonlinear effects can be accurately estimated in real time through the weight updating rule.

Keywords

• disturbance estimation
• parallel model
• rbf neural network
• state observer