How to improve fuzzy-neural system modeling by means of qualitative simulation

R. Bellazzi, R. Guglielmann, L. Ironi

Research output: Contribution to journalArticle

Abstract

The main problem in efficiently building robust fuzzy-neural models of nonlinear systems lies in the difficulty to define a "meaningful" fuzzy rule-base. Our approach to the solution of such a problem is based on a hybrid method which integrates fuzzy systems with qualitative models. We introduce qualitative models to exploit the available, although incomplete, a priori physical knowledge on the system with the goal to infer, through qualitative simulation, all of its possible behaviors. We show here that a rule-base, which captures all of the distinctions in the system states, is automatically generated by encoding the knowledge of the system dynamics described by the outcomes of its qualitative simulation. Such a rule-base properly initializes a fuzzy identifier, which is then tuned to a set of experimental data. Our method has shown good performance when applied both as a predictor and as a simulator.

Original languageEnglish
Pages (from-to)249-253
Number of pages5
JournalIEEE Transactions on Neural Networks
Volume11
Issue number1
DOIs
Publication statusPublished - Jan 2000

Fingerprint

Qualitative Simulation
System Modeling
Rule Base
Fuzzy Rule Base
Fuzzy rules
Fuzzy systems
Hybrid Method
System Dynamics
Fuzzy Systems
Nonlinear systems
Predictors
Dynamical systems
Simulator
Encoding
Nonlinear Systems
Simulators
Integrate
Experimental Data
Model
Knowledge

Keywords

  • Fuzzy systems
  • Identification
  • Neural networks
  • Qualitative simulation

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Theoretical Computer Science
  • Electrical and Electronic Engineering
  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Hardware and Architecture

Cite this

How to improve fuzzy-neural system modeling by means of qualitative simulation. / Bellazzi, R.; Guglielmann, R.; Ironi, L.

In: IEEE Transactions on Neural Networks, Vol. 11, No. 1, 01.2000, p. 249-253.

Research output: Contribution to journalArticle

@article{86b58a996fdc40a0b92d982bdb29852f,
title = "How to improve fuzzy-neural system modeling by means of qualitative simulation",
abstract = "The main problem in efficiently building robust fuzzy-neural models of nonlinear systems lies in the difficulty to define a {"}meaningful{"} fuzzy rule-base. Our approach to the solution of such a problem is based on a hybrid method which integrates fuzzy systems with qualitative models. We introduce qualitative models to exploit the available, although incomplete, a priori physical knowledge on the system with the goal to infer, through qualitative simulation, all of its possible behaviors. We show here that a rule-base, which captures all of the distinctions in the system states, is automatically generated by encoding the knowledge of the system dynamics described by the outcomes of its qualitative simulation. Such a rule-base properly initializes a fuzzy identifier, which is then tuned to a set of experimental data. Our method has shown good performance when applied both as a predictor and as a simulator.",
keywords = "Fuzzy systems, Identification, Neural networks, Qualitative simulation",
author = "R. Bellazzi and R. Guglielmann and L. Ironi",
year = "2000",
month = "1",
doi = "10.1109/72.822528",
language = "English",
volume = "11",
pages = "249--253",
journal = "IEEE Transactions on Neural Networks",
issn = "1045-9227",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

TY - JOUR

T1 - How to improve fuzzy-neural system modeling by means of qualitative simulation

AU - Bellazzi, R.

AU - Guglielmann, R.

AU - Ironi, L.

PY - 2000/1

Y1 - 2000/1

N2 - The main problem in efficiently building robust fuzzy-neural models of nonlinear systems lies in the difficulty to define a "meaningful" fuzzy rule-base. Our approach to the solution of such a problem is based on a hybrid method which integrates fuzzy systems with qualitative models. We introduce qualitative models to exploit the available, although incomplete, a priori physical knowledge on the system with the goal to infer, through qualitative simulation, all of its possible behaviors. We show here that a rule-base, which captures all of the distinctions in the system states, is automatically generated by encoding the knowledge of the system dynamics described by the outcomes of its qualitative simulation. Such a rule-base properly initializes a fuzzy identifier, which is then tuned to a set of experimental data. Our method has shown good performance when applied both as a predictor and as a simulator.

AB - The main problem in efficiently building robust fuzzy-neural models of nonlinear systems lies in the difficulty to define a "meaningful" fuzzy rule-base. Our approach to the solution of such a problem is based on a hybrid method which integrates fuzzy systems with qualitative models. We introduce qualitative models to exploit the available, although incomplete, a priori physical knowledge on the system with the goal to infer, through qualitative simulation, all of its possible behaviors. We show here that a rule-base, which captures all of the distinctions in the system states, is automatically generated by encoding the knowledge of the system dynamics described by the outcomes of its qualitative simulation. Such a rule-base properly initializes a fuzzy identifier, which is then tuned to a set of experimental data. Our method has shown good performance when applied both as a predictor and as a simulator.

KW - Fuzzy systems

KW - Identification

KW - Neural networks

KW - Qualitative simulation

UR - http://www.scopus.com/inward/record.url?scp=0033640722&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033640722&partnerID=8YFLogxK

U2 - 10.1109/72.822528

DO - 10.1109/72.822528

M3 - Article

C2 - 18249757

AN - SCOPUS:0033640722

VL - 11

SP - 249

EP - 253

JO - IEEE Transactions on Neural Networks

JF - IEEE Transactions on Neural Networks

SN - 1045-9227

IS - 1

ER -