Neuro-Controller Design by Using the Multifeedback Layer Neural Network and the Particle Swarm Optimization

Ramazan Çoban ,İnayet Özge Aksu

doi:10.17559/tv-20161025220853

Abstract

Neuro-Controller Design by Using the Multifeedback Layer Neural Network and the Particle Swarm Optimization

Highlights

In recent years, special attention has been devoted to neural network methodologies for model and control of nonlinear dynamic systems in various areas [1,2,3,4]
In the present study, a novel neuro-controller is suggested for hard disk drive (HDD) systems in addition to nonlinear dynamic systems using the MultifeedbackLayer Neural Network (MFLNN) proposed in recent years
In neuro-controller design problems, since the derivative based train methods such as the back-propagation and Levenberg-Marquart (LM) methods necessitate the reference values of the neural network’s output or Jacobian of the dynamic system for the duration of the train, the connection weights of the MFLNN employed in the present work are updated using the Particle Swarm Optimization (PSO) algorithm that does not need such information

Summary

Introduction

Special attention has been devoted to neural network methodologies for model and control of nonlinear dynamic systems in various areas [1,2,3,4]. Recurrent fuzzy neural networks were successfully employed in control and model of dynamic systems in [58]. Some kinds of Recurrent Neural Networks (RNNs) were implemented into nonlinear dynamic systems for the purposes of control or model in [9,10,11]. Various computational optimization methods can be utilized to train artificial neural network controllers. A Takagi–Sugeno–Kang based recurrent fuzzy neural network trained by the GA was suggested for control of nonlinear dynamical systems by Juang [12]. The PSO was employed to optimize the fuzzy neural network connection weights. The particle swarm optimization was utilized for optimization of the connection weights of the neural network controller. The results obtained in these research works were compared with those achieved by using gradient-based algorithm

Methods

Results

Conclusion