A fuzzy neural network approach to model hydraulic component from input/output data

Wei Xiang, Sai Cheong Fok, Fook Fak Yap

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

The knowledge of dynamics of hydraulic components are vital for the virtual prototyping of fluid power systems. This paper proposes a fuzzy neural network approach to model the behavior of a hydraulic component from its input-output data. The main advantage of this approach is that the network structure can be determined based on the analysis of the input variables to output response, without trial and error, network pruning or network growing techniques. The process involves resolving the significant inputs through an analysis of their effects with respect to the output. The number of fuzzy rules is determined based on partitioning of the input-output space. The number of significant inputs and the number of fuzzy rules together define the fuzzy neural network structure. A hydraulic pressure relief valve is used to demonstrate the proposed approach. The results indicate that the structure of the fuzzy neural network determined based on the proposed approach can effectively model the dynamics of the relief valve. This work constitutes initial effort towards determining the structure of neural networks based on the analysis of input-output data.

Original languageEnglish
Pages (from-to)37-47
Number of pages11
JournalInternational Journal of Fluid Power
Volume2
Issue number1
DOIs
Publication statusPublished - Jan 1 2001
Externally publishedYes

Fingerprint

Hydraulic models
Fuzzy neural networks
hydraulics
Pressure relief valves
Hydraulics
Fuzzy rules
output
relief valves
Neural networks
fluid power
Fluids

Keywords

  • Fluid power system
  • Fuzzy neural network (FNN)
  • Virtual prototyping

ASJC Scopus subject areas

  • Mechanical Engineering
  • Physics and Astronomy(all)

Cite this

A fuzzy neural network approach to model hydraulic component from input/output data. / Xiang, Wei; Fok, Sai Cheong; Yap, Fook Fak.

In: International Journal of Fluid Power, Vol. 2, No. 1, 01.01.2001, p. 37-47.

Research output: Contribution to journalArticle

@article{ccc3ba5432524e13b7dc99e8f57725ed,
title = "A fuzzy neural network approach to model hydraulic component from input/output data",
abstract = "The knowledge of dynamics of hydraulic components are vital for the virtual prototyping of fluid power systems. This paper proposes a fuzzy neural network approach to model the behavior of a hydraulic component from its input-output data. The main advantage of this approach is that the network structure can be determined based on the analysis of the input variables to output response, without trial and error, network pruning or network growing techniques. The process involves resolving the significant inputs through an analysis of their effects with respect to the output. The number of fuzzy rules is determined based on partitioning of the input-output space. The number of significant inputs and the number of fuzzy rules together define the fuzzy neural network structure. A hydraulic pressure relief valve is used to demonstrate the proposed approach. The results indicate that the structure of the fuzzy neural network determined based on the proposed approach can effectively model the dynamics of the relief valve. This work constitutes initial effort towards determining the structure of neural networks based on the analysis of input-output data.",
keywords = "Fluid power system, Fuzzy neural network (FNN), Virtual prototyping",
author = "Wei Xiang and Fok, {Sai Cheong} and Yap, {Fook Fak}",
year = "2001",
month = "1",
day = "1",
doi = "10.1080/14399776.2001.10781101",
language = "English",
volume = "2",
pages = "37--47",
journal = "International Journal of Fluid Power",
issn = "1439-9776",
publisher = "Taylor and Francis",
number = "1",

}

TY - JOUR

T1 - A fuzzy neural network approach to model hydraulic component from input/output data

AU - Xiang, Wei

AU - Fok, Sai Cheong

AU - Yap, Fook Fak

PY - 2001/1/1

Y1 - 2001/1/1

N2 - The knowledge of dynamics of hydraulic components are vital for the virtual prototyping of fluid power systems. This paper proposes a fuzzy neural network approach to model the behavior of a hydraulic component from its input-output data. The main advantage of this approach is that the network structure can be determined based on the analysis of the input variables to output response, without trial and error, network pruning or network growing techniques. The process involves resolving the significant inputs through an analysis of their effects with respect to the output. The number of fuzzy rules is determined based on partitioning of the input-output space. The number of significant inputs and the number of fuzzy rules together define the fuzzy neural network structure. A hydraulic pressure relief valve is used to demonstrate the proposed approach. The results indicate that the structure of the fuzzy neural network determined based on the proposed approach can effectively model the dynamics of the relief valve. This work constitutes initial effort towards determining the structure of neural networks based on the analysis of input-output data.

AB - The knowledge of dynamics of hydraulic components are vital for the virtual prototyping of fluid power systems. This paper proposes a fuzzy neural network approach to model the behavior of a hydraulic component from its input-output data. The main advantage of this approach is that the network structure can be determined based on the analysis of the input variables to output response, without trial and error, network pruning or network growing techniques. The process involves resolving the significant inputs through an analysis of their effects with respect to the output. The number of fuzzy rules is determined based on partitioning of the input-output space. The number of significant inputs and the number of fuzzy rules together define the fuzzy neural network structure. A hydraulic pressure relief valve is used to demonstrate the proposed approach. The results indicate that the structure of the fuzzy neural network determined based on the proposed approach can effectively model the dynamics of the relief valve. This work constitutes initial effort towards determining the structure of neural networks based on the analysis of input-output data.

KW - Fluid power system

KW - Fuzzy neural network (FNN)

KW - Virtual prototyping

UR - http://www.scopus.com/inward/record.url?scp=2642573031&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2642573031&partnerID=8YFLogxK

U2 - 10.1080/14399776.2001.10781101

DO - 10.1080/14399776.2001.10781101

M3 - Article

VL - 2

SP - 37

EP - 47

JO - International Journal of Fluid Power

JF - International Journal of Fluid Power

SN - 1439-9776

IS - 1

ER -