Identification and control using MLP, Elman, NARXSP and radial basis function networks: a comparative analysis

Authors:
Bharat Bhushan;Madhusudan Singh;Yase Hage
Affiliations:
Department of Electrical Engineering, Delhi Technological University, New Delhi, India;Department of Electrical Engineering, Delhi Technological University, New Delhi, India;Department of Computer Engineering, Delhi Technological University, New Delhi, India
Venue:
Artificial Intelligence Review
Year:
2012

Citing 3
Cited 0

Approximation capabilities of multilayer feedforward networks

Neural Networks
Knowledge-based artificial neural networks for process modelling and control

Knowledge-based artificial neural networks for process modelling and control
Fast learning in networks of locally-tuned processing units

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes four neural networks multilayer perceptron (MLP) network, Elman network, NARXSP network and radial basis function (RBF) network. Neural networks are applied for identification and control of DC servo motor and benchmark nonlinear system. Number of epochs required and time taken to train the controller are shown in the form of bar plots for four neural networks. Levenberg-Marquardt algorithm is used for training the controller using neural network toolbox in MATLAB. Each neural network controller is run ten times. Their performances are compared for each run in terms of number of epochs required and time taken to train each controller for tracking a reference trajectory.