WIT Press

Comparative Study Of Fuzzy Logic And Neural Network Methods In Modeling Of Simulated Steady-state Data

Price

Free (open access)

Paper DOI

10.2495/AI960141

Volume

16

Pages

13

Published

1996

Size

130 kb

Author(s)

M. Järvensivu and V. Kanninen

Abstract

In this paper fuzzy logic and neural network methods were used to model simulated nonlinear steady-state data. Two different cases of training and checking data sets were generated: ideal data without noise and realistic data with added noise and other nonidealities. Both techniques were fitting the ideal case data almost perfectly. The fuzzy logic and neural network models were also able to roughly predict the realistic case data. 1. Introduction Both neural networks and fuzzy logic inference systems have been proved to have capabilities of universal approximators. Thus they can both be utilized in modeling of complicated nonlinear processes (Juditsky1, Wang2). Rotating disk filter is a complicated nonlinear process, w

Keywords