A study on generalized neural network system for recognizing nonlinear behaviour of structures

T. Mazda; H. Otsuka; W. Yabuki; M. Tsuruta

A study on generalized neural network system for recognizing nonlinear behaviour of structures

T. Mazda, H. Otsuka, W. Yabuki, M. Tsuruta

Structural Analysis and Earthquake Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

Multiple layered neural network to simulate the non-linear hysteretic behavior like Ramberg-Osgood model, modified bilinear model and Takeda model is described. Based on the pattern recognition ability of neural network, non-linear hysteretic behavior is modeled by the network directly without replacing it with a mathematical model. Thus, the effectiveness and applicability of the network in numerical analysis are evaluated. It is found that neural network transmits the signals from the input layer to the output layer by way of the hidden layers when the input signals is received, and output layer by way o the hidden layers when the input signals is received, and output the output signals finally.

Original language	English
Title of host publication	Proceedings of the Third International Conference on Engineering Computational Technology
Editors	B.H.V. Topping, Z. Bittnar, B.H.V. Topping, Z. Bittnar
Pages	209-210
Number of pages	2
Publication status	Published - Dec 1 2002
Event	Proceedings of the Third International Conference on Engineering Computational Technology - Prague, Czech Republic Duration: Sept 4 2002 → Sept 6 2002

Publication series

Name	Proceedings of the Third International Conference on Engineering Computational Technology

Other

Other	Proceedings of the Third International Conference on Engineering Computational Technology
Country/Territory	Czech Republic
City	Prague
Period	9/4/02 → 9/6/02

All Science Journal Classification (ASJC) codes

Engineering(all)

Cite this

Mazda, T., Otsuka, H., Yabuki, W., & Tsuruta, M. (2002). A study on generalized neural network system for recognizing nonlinear behaviour of structures. In B. H. V. Topping, Z. Bittnar, B. H. V. Topping, & Z. Bittnar (Eds.), Proceedings of the Third International Conference on Engineering Computational Technology (pp. 209-210). (Proceedings of the Third International Conference on Engineering Computational Technology).

A study on generalized neural network system for recognizing nonlinear behaviour of structures. / Mazda, T.; Otsuka, H.; Yabuki, W. et al.
Proceedings of the Third International Conference on Engineering Computational Technology. ed. / B.H.V. Topping; Z. Bittnar; B.H.V. Topping; Z. Bittnar. 2002. p. 209-210 (Proceedings of the Third International Conference on Engineering Computational Technology).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Mazda, T, Otsuka, H, Yabuki, W & Tsuruta, M 2002, A study on generalized neural network system for recognizing nonlinear behaviour of structures. in BHV Topping, Z Bittnar, BHV Topping & Z Bittnar (eds), Proceedings of the Third International Conference on Engineering Computational Technology. Proceedings of the Third International Conference on Engineering Computational Technology, pp. 209-210, Proceedings of the Third International Conference on Engineering Computational Technology, Prague, Czech Republic, 9/4/02.

Mazda T, Otsuka H, Yabuki W, Tsuruta M. A study on generalized neural network system for recognizing nonlinear behaviour of structures. In Topping BHV, Bittnar Z, Topping BHV, Bittnar Z, editors, Proceedings of the Third International Conference on Engineering Computational Technology. 2002. p. 209-210. (Proceedings of the Third International Conference on Engineering Computational Technology).

Mazda, T. ; Otsuka, H. ; Yabuki, W. et al. / A study on generalized neural network system for recognizing nonlinear behaviour of structures. Proceedings of the Third International Conference on Engineering Computational Technology. editor / B.H.V. Topping ; Z. Bittnar ; B.H.V. Topping ; Z. Bittnar. 2002. pp. 209-210 (Proceedings of the Third International Conference on Engineering Computational Technology).

@inproceedings{4e6508858f3744a0b331dbef56d6cca3,

title = "A study on generalized neural network system for recognizing nonlinear behaviour of structures",

abstract = "Multiple layered neural network to simulate the non-linear hysteretic behavior like Ramberg-Osgood model, modified bilinear model and Takeda model is described. Based on the pattern recognition ability of neural network, non-linear hysteretic behavior is modeled by the network directly without replacing it with a mathematical model. Thus, the effectiveness and applicability of the network in numerical analysis are evaluated. It is found that neural network transmits the signals from the input layer to the output layer by way of the hidden layers when the input signals is received, and output layer by way o the hidden layers when the input signals is received, and output the output signals finally.",

author = "T. Mazda and H. Otsuka and W. Yabuki and M. Tsuruta",

year = "2002",

month = dec,

day = "1",

language = "English",

isbn = "0948749857",

series = "Proceedings of the Third International Conference on Engineering Computational Technology",

pages = "209--210",

editor = "B.H.V. Topping and Z. Bittnar and B.H.V. Topping and Z. Bittnar",

booktitle = "Proceedings of the Third International Conference on Engineering Computational Technology",

note = "Proceedings of the Third International Conference on Engineering Computational Technology ; Conference date: 04-09-2002 Through 06-09-2002",

}

TY - GEN

T1 - A study on generalized neural network system for recognizing nonlinear behaviour of structures

AU - Mazda, T.

AU - Otsuka, H.

AU - Yabuki, W.

AU - Tsuruta, M.

PY - 2002/12/1

Y1 - 2002/12/1

N2 - Multiple layered neural network to simulate the non-linear hysteretic behavior like Ramberg-Osgood model, modified bilinear model and Takeda model is described. Based on the pattern recognition ability of neural network, non-linear hysteretic behavior is modeled by the network directly without replacing it with a mathematical model. Thus, the effectiveness and applicability of the network in numerical analysis are evaluated. It is found that neural network transmits the signals from the input layer to the output layer by way of the hidden layers when the input signals is received, and output layer by way o the hidden layers when the input signals is received, and output the output signals finally.

AB - Multiple layered neural network to simulate the non-linear hysteretic behavior like Ramberg-Osgood model, modified bilinear model and Takeda model is described. Based on the pattern recognition ability of neural network, non-linear hysteretic behavior is modeled by the network directly without replacing it with a mathematical model. Thus, the effectiveness and applicability of the network in numerical analysis are evaluated. It is found that neural network transmits the signals from the input layer to the output layer by way of the hidden layers when the input signals is received, and output layer by way o the hidden layers when the input signals is received, and output the output signals finally.

UR - http://www.scopus.com/inward/record.url?scp=0036929717&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036929717&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0036929717

SN - 0948749857

T3 - Proceedings of the Third International Conference on Engineering Computational Technology

SP - 209

EP - 210

BT - Proceedings of the Third International Conference on Engineering Computational Technology

A2 - Topping, B.H.V.

A2 - Bittnar, Z.

A2 - Topping, B.H.V.

A2 - Bittnar, Z.

T2 - Proceedings of the Third International Conference on Engineering Computational Technology

Y2 - 4 September 2002 through 6 September 2002

ER -

A study on generalized neural network system for recognizing nonlinear behaviour of structures

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this