Controller design for industrial hydraulic actuator using artificial neural network

Abstract

Electro-hydraulic actuators are widely used in motion control application. Its valve needs to be controlled to determine direction of the actuator. Mathematical modeling is a description of a system in terms of equations. It can be divided into two parts, which is physical modeling and system identification. The objective of this study was to determine the mathematical modeling of Industrial Hydraulic Actuator by using System Identification technique by estimating model using System Identification Toolbox in MATLAB. Then, an ANN controller is designed in order to control the displacement of the hydraulic actuator. Finally the controller is validated by implementing in the real time experiments. Experimental works were done to collect input and output data for model estimation and ARX model was chosen as model structure of the system. The best model was accepted based on the best fit criterion and residuals analysis of autocorrelation and cross correlation of the system input and output. Then, PIDNN controller was designed for the model through simulation in SIMULINK. The neural network weights and controller’s parameters is tuning by The Particles Swarm Optimization (PSO) method. The simulation work was verified by applying the controller to the real system to achieve the best performance of the system. The result showed that the output of the system with PIDNN controller in simulation mode and experimental works was improved and almost similar. The designed PIDNN with PSO tuning method controller can be applied to the electro-hydraulic system either in simulation or real-time mode. The others automatic tuning method controller could be developed in future work to increase the reliability of the PIDNN controller. Besides, the hydraulic actuator system with non linear model could be modeled.