CMAC Based Hybrid Control System for Solving Electrohydraulic System Nonlinearities

CMAC Based Hybrid Control System for Solving Electrohydraulic System Nonlinearities

Amro Shafik (Banha Faculty of Engineering, Banha University, Banha, Egypt), Magdy Abdelhameed (Ain Shams University, Cairo, Egypt), and Ahmed Kassem (Banha Faculty of Engineering, Banha University, Banha, Egypt)
DOI: 10.4018/ijmmme.2014040104
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Automation based electrohydraulic servo systems have a wide range of applications in nowadays industry. However, they still suffer from several nonlinearities like deadband in electrohydraulic valves, hysteresis, stick-slip friction in valves and cylinders. In addition, all hydraulic system parameters have uncertainties in their values due to the change of temperature while working. This paper addresses these problems by designing a suitable intelligent control system that has the ability to deal with the system nonlinearities and parameters uncertainties using a fast and online learning algorithm. A novel hybrid control system based on Cerebellar Model Articulation Controller (CMAC) neural network is presented. The proposed controller is composed of two parallel controllers. The first is a conventional Proportional-Velocity (PV) servo type controller which is used to decrease the large initial error of the closed-loop system. The second is a CMAC neural network which is used as an intelligent controller to overcome nonlinear characteristics of the electrohydraulic system. A fourth order model for the electrohydraulic system is introduced. PV controller parameters are tuned to get optimal values. Simulation and experimental results show a good tracking performance obtained using the proposed controller. The controller shows its robustness in two working environments. The first is by adding different inertia loads and the second is working with noisy level input signals.
Article Preview
Top

Introduction

Automation based electrohydraulic systems are most common in nowadays industry because they overcome the problems of pneumatic systems such as the high compressibility of air which gives poor dynamics and low power used. Important properties like durability, high power to weight ratio, controllability, accuracy and reliability are also provided when using electrohydraulic systems. Electrohydraulic systems are those hydraulic systems which use valves actuated by electrical power. Three most common types of electrically operated valves are on/off solenoid, proportional, and servo valves. Those types of valves suffer from some nonlinear effects like deadbands and solenoid hysteresis. The performance of electrohydraulic valves greatly affects the complete hydraulic circuit performance; therefore if some methods are introduced to enhance the dynamic performance of valves, this will increase the overall performance of those automated systems.

Position control of electrohydraulic actuators is an important topic that covered by researchers. Indirect adaptive nonlinear backstepping control strategy showed a good tracking performance (Kaddissi et al., 2011). A model reference adaptive control technique based on sliding-mode term was applied by Yang et al. (2012) for velocity and position control. A switching position controller based on a standard feedback linearization showed its robustness (Mintsa et al., 2012). A combination of H∞, integral-block, and sliding-mode techniques was proposed by Loukianov et al. (2009) to track a chaotic reference trajectory. An optimal fuzzy PID controller, which was optimized by genetic algorithm, was developed by Nazir and Wang (2008) to reduce the tracking error of a nonlinear servo system. Force control for electrohydraulic systems is another competitive field. The force tracking control could be done by using PI controller with a limited feedback controller to reject the load disturbances (Sam & Hudha, 2006). A nonlinear quantitative feedback theory (QFT) was applied by Karpenko and Sepehri (2012) for an electrohydraulic load emulator to compensate the effect of load dynamics on the force transfer function. A model predictive control algorithm which takes the input and output constraints into consideration was used for force control of an electrohydraulic actuator (Marusak & Kuntanapreeda, 2011).

The dynamic performance can be enhanced by either using a different actuating hardware such as piezoelectric actuators (Yun et al., 2006; Bang et al., 2003) which don’t suffer from hysteresis problem, or by applying a software technology through using an intelligent nonlinear control algorithm. Different control algorithms were applied in order to overcome the electrohydraulic system nonlinearities. A discrete-time sliding-mode control scheme was used to overcome the effect of varying friction parameters (Lin et al., 2013). The effect of nonlinearities and control input constraints was compensated for electrohydraulic active suspensions by a T-S model based fuzzy state feedback controller (Du & Zhang, 2009). The supply pressure uncertainty was discussed by Mintsa et al. (2012) through using feedback linearization technique. A feedforward compensator and adaptive fuzzy PID controller were designed to control a marine electrohydraulic load simulator (Xiangyong et al., 2006). A B-spline neural network could be used to compensate the uncertainties, and work based on variable structure controller (VSC) which improved the tracking performance (Duan et al., 2008).

The Cerebellar Model Articulation Controller (CMAC) is a type of neural networks based on a model of the mammalian cerebellum. It is also known as the Cerebellar Model Arithmetic Computer. It is a type of associative memory. The theory of cerebellar function was firstly introduced in 1975 by Albus (1975). He stated that CMAC is a memory management technique which causes similar inputs to tend to generalize that leads to produce similar outputs, and dissimilar inputs result in outputs which are independent. Also, he clarified that CMAC computes control functions by referring to a table rather than by solution of analytical equations or by conventional analog servo techniques.

Complete Article List

Search this Journal:
Reset
Volume 14: 1 Issue (2025)
Volume 13: 1 Issue (2024)
Volume 12: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 11: 4 Issues (2021)
Volume 10: 4 Issues (2020)
Volume 9: 4 Issues (2019)
Volume 8: 4 Issues (2018)
Volume 7: 4 Issues (2017)
Volume 6: 4 Issues (2016)
Volume 5: 4 Issues (2015)
Volume 4: 4 Issues (2014)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing