Construction of generalized neural network system for recognizing several non-linear behaviors

Taiji Matsuda, Hisanori Otsuka, Wataru Yabuki, Kensuke Iwamoto

Research output: Contribution to journalArticle

Abstract

Generally, in formulating a spring-mass model for hysteric behavior of materials and members with inelastic characteristic, a mathematical model based on load-deformation experimental results is considered. The model must approximate the inelastic hysteresis of the material. However, assumption of material's behavior using mathematical models is crucial, since it may cause serious errors if inappropriate model is applied for a particular situation. This paper describes multiple layered neural network to simulate the non-linear hysteretic behavior like Ramberg-Osgood model, modified bilinear model and Takeda model. In this study, based on the pattern recognition ability of neural nnnetwork, non-linear hysteretic behavior was modeled by the network directly without replacing it with a mathematical model. The effectiveness and applicability of the network in numerical analysis were evaluated. Generalized multiple layered neural network to evaluate non-linear hysteretic curve was constructed. The network can recognize well the three types of hysteretic curve. The network is available as a subroutine of non-linear spring in dynamic response analysis.

Original languageEnglish
Pages (from-to)143-151
Number of pages9
JournalAmerican Society of Mechanical Engineers, Pressure Vessels and Piping Division (Publication) PVP
Volume466
DOIs
Publication statusPublished - 2003
Externally publishedYes

Fingerprint

Neural networks
Mathematical models
Subroutines
Pattern recognition
Dynamic response
Hysteresis
Numerical analysis

All Science Journal Classification (ASJC) codes

  • Mechanical Engineering

Cite this

Construction of generalized neural network system for recognizing several non-linear behaviors. / Matsuda, Taiji; Otsuka, Hisanori; Yabuki, Wataru; Iwamoto, Kensuke.

In: American Society of Mechanical Engineers, Pressure Vessels and Piping Division (Publication) PVP, Vol. 466, 2003, p. 143-151.

Research output: Contribution to journalArticle

@article{ee5437505a164388bb161305e2680251,
title = "Construction of generalized neural network system for recognizing several non-linear behaviors",
abstract = "Generally, in formulating a spring-mass model for hysteric behavior of materials and members with inelastic characteristic, a mathematical model based on load-deformation experimental results is considered. The model must approximate the inelastic hysteresis of the material. However, assumption of material's behavior using mathematical models is crucial, since it may cause serious errors if inappropriate model is applied for a particular situation. This paper describes multiple layered neural network to simulate the non-linear hysteretic behavior like Ramberg-Osgood model, modified bilinear model and Takeda model. In this study, based on the pattern recognition ability of neural nnnetwork, non-linear hysteretic behavior was modeled by the network directly without replacing it with a mathematical model. The effectiveness and applicability of the network in numerical analysis were evaluated. Generalized multiple layered neural network to evaluate non-linear hysteretic curve was constructed. The network can recognize well the three types of hysteretic curve. The network is available as a subroutine of non-linear spring in dynamic response analysis.",
author = "Taiji Matsuda and Hisanori Otsuka and Wataru Yabuki and Kensuke Iwamoto",
year = "2003",
doi = "10.1115/PVP2003-2114",
language = "English",
volume = "466",
pages = "143--151",
journal = "American Society of Mechanical Engineers, Pressure Vessels and Piping Division (Publication) PVP",
issn = "0277-027X",
publisher = "American Society of Mechanical Engineers(ASME)",

}

TY - JOUR

T1 - Construction of generalized neural network system for recognizing several non-linear behaviors

AU - Matsuda, Taiji

AU - Otsuka, Hisanori

AU - Yabuki, Wataru

AU - Iwamoto, Kensuke

PY - 2003

Y1 - 2003

N2 - Generally, in formulating a spring-mass model for hysteric behavior of materials and members with inelastic characteristic, a mathematical model based on load-deformation experimental results is considered. The model must approximate the inelastic hysteresis of the material. However, assumption of material's behavior using mathematical models is crucial, since it may cause serious errors if inappropriate model is applied for a particular situation. This paper describes multiple layered neural network to simulate the non-linear hysteretic behavior like Ramberg-Osgood model, modified bilinear model and Takeda model. In this study, based on the pattern recognition ability of neural nnnetwork, non-linear hysteretic behavior was modeled by the network directly without replacing it with a mathematical model. The effectiveness and applicability of the network in numerical analysis were evaluated. Generalized multiple layered neural network to evaluate non-linear hysteretic curve was constructed. The network can recognize well the three types of hysteretic curve. The network is available as a subroutine of non-linear spring in dynamic response analysis.

AB - Generally, in formulating a spring-mass model for hysteric behavior of materials and members with inelastic characteristic, a mathematical model based on load-deformation experimental results is considered. The model must approximate the inelastic hysteresis of the material. However, assumption of material's behavior using mathematical models is crucial, since it may cause serious errors if inappropriate model is applied for a particular situation. This paper describes multiple layered neural network to simulate the non-linear hysteretic behavior like Ramberg-Osgood model, modified bilinear model and Takeda model. In this study, based on the pattern recognition ability of neural nnnetwork, non-linear hysteretic behavior was modeled by the network directly without replacing it with a mathematical model. The effectiveness and applicability of the network in numerical analysis were evaluated. Generalized multiple layered neural network to evaluate non-linear hysteretic curve was constructed. The network can recognize well the three types of hysteretic curve. The network is available as a subroutine of non-linear spring in dynamic response analysis.

UR - http://www.scopus.com/inward/record.url?scp=0242442533&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0242442533&partnerID=8YFLogxK

U2 - 10.1115/PVP2003-2114

DO - 10.1115/PVP2003-2114

M3 - Article

AN - SCOPUS:0242442533

VL - 466

SP - 143

EP - 151

JO - American Society of Mechanical Engineers, Pressure Vessels and Piping Division (Publication) PVP

JF - American Society of Mechanical Engineers, Pressure Vessels and Piping Division (Publication) PVP

SN - 0277-027X

ER -