Artificial Neural Network Predictions of Fatigue Life of Steel Bars Based on Hysteretic Energy: Fid-Bau Portal

Fachinformationsdienst BAUdigital

Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik

Artificial Neural Network Predictions of Fatigue Life of Steel Bars Based on Hysteretic Energy

Abdalla, Jamal A. / Hawileh, Rami A.

The fatigue life of steel reinforcing bars depends on the energy dissipated during cyclic loading. Steel bars play a major role in energy dissipation in reinforced concrete structures under low-cycle fatigue loading during earthquakes. In this study, seven artificial neural network (ANN) models were developed to predict the fatigue life of steel bars based on energy dissipated in the first cycle ( $W_{1}$ ), average cycles ( $W_{A}$ ), and total energy dissipated in all cycles ( $W_{T}$ ). The ANN-predicted number of reversals to fatigue failure ( ${2 N}_{f}$ ) were comparable to the experimentally measured values and also to the values predicted using nonlinear regression (NLR) models. The best overall ANN result was obtained when $W_{1}$ , $W_{A}$ , and $W_{T}$ were used together as input for the ANN with correlation coefficient $r = 0.985$ , normalized mean square error $(NMSE) = 0.0517$ , and mean absolute percent error $(MAPE) = 10.8 %$ . When $W_{A}$ was used as a single input, the predicted ${2 N}_{f}$ are also relatively accurate. In conclusion, the developed ANN models can be used to reliably predict fatigue life of steel reinforcing bars based on energy as input parameters.

Zugriff

Zugriff prüfen

Verfügbarkeit in meiner Bibliothek prüfen

Bestellung bei Subito €

Seitennavigation

Dokumentinformationen

Ähnliche Titel

Exportieren, teilen und zitieren

Artificial Neural Network Predictions of Fatigue Life of Steel Bars Based on Hysteretic Energy

Abdalla, Jamal A. / Hawileh, Rami A.

The fatigue life of steel reinforcing bars depends on the energy dissipated during cyclic loading. Steel bars play a major role in energy dissipation in reinforced concrete structures under low-cycle fatigue loading during earthquakes. In this study, seven artificial neural network (ANN) models were developed to predict the fatigue life of steel bars based on energy dissipated in the first cycle ( $W_{1}$ ), average cycles ( $W_{A}$ ), and total energy dissipated in all cycles ( $W_{T}$ ). The ANN-predicted number of reversals to fatigue failure ( ${2 N}_{f}$ ) were comparable to the experimentally measured values and also to the values predicted using nonlinear regression (NLR) models. The best overall ANN result was obtained when $W_{1}$ , $W_{A}$ , and $W_{T}$ were used together as input for the ANN with correlation coefficient $r = 0.985$ , normalized mean square error $(NMSE) = 0.0517$ , and mean absolute percent error $(MAPE) = 10.8 %$ . When $W_{A}$ was used as a single input, the predicted ${2 N}_{f}$ are also relatively accurate. In conclusion, the developed ANN models can be used to reliably predict fatigue life of steel reinforcing bars based on energy as input parameters.

Artificial Neural Network Predictions of Fatigue Life of Steel Bars Based on Hysteretic Energy

Abdalla, Jamal A. / Hawileh, Rami A.

The fatigue life of steel reinforcing bars depends on the energy dissipated during cyclic loading. Steel bars play a major role in energy dissipation in reinforced concrete structures under low-cycle fatigue loading during earthquakes. In this study, seven artificial neural network (ANN) models were developed to predict the fatigue life of steel bars based on energy dissipated in the first cycle ( $W_{1}$ ), average cycles ( $W_{A}$ ), and total energy dissipated in all cycles ( $W_{T}$ ). The ANN-predicted number of reversals to fatigue failure ( ${2 N}_{f}$ ) were comparable to the experimentally measured values and also to the values predicted using nonlinear regression (NLR) models. The best overall ANN result was obtained when $W_{1}$ , $W_{A}$ , and $W_{T}$ were used together as input for the ANN with correlation coefficient $r = 0.985$ , normalized mean square error $(NMSE) = 0.0517$ , and mean absolute percent error $(MAPE) = 10.8 %$ . When $W_{A}$ was used as a single input, the predicted ${2 N}_{f}$ are also relatively accurate. In conclusion, the developed ANN models can be used to reliably predict fatigue life of steel reinforcing bars based on energy as input parameters.

Zugriff

Zugriff prüfen

Verfügbarkeit in meiner Bibliothek prüfen

Bestellung bei Subito €

Seitennavigation

Dokumentinformationen

Ähnliche Titel

Exportieren, teilen und zitieren

Dokumentinformationen

Titel:

Artificial Neural Network Predictions of Fatigue Life of Steel Bars Based on Hysteretic Energy

Beteiligte:

Abdalla, Jamal A. (Autor:in) / Hawileh, Rami A. (Autor:in)

Erschienen in:

Journal of Computing in Civil Engineering ; 27 ; 489-496

Erscheinungsdatum:

15.08.2013

Format / Umfang:

82013-01-01 pages

ISSN:

0887-3801 , 1943-5487

DOI:

https://doi.org/10.1061/(ASCE)CP.1943-5487.0000185

Medientyp:

Aufsatz (Zeitschrift)

Format:

Elektronische Ressource

Sprache:

Englisch

Ähnliche Titel

Artificial Neural Network Predictions of Fatigue Life of Steel Bars Based on Hysteretic Energy

Abdalla, Jamal A. | Online Contents | 2013

Artificial Neural Network Predictions of Fatigue Life of Steel Bars Based on Hysteretic Energy

Abdalla, J.A. / Hawileh, R.A. | British Library Conference Proceedings | 2013

Artificial Neural Network Predictions of Fatigue Life of Steel Bars Based on Hysteretic Energy

Abdalla, J.A. / Hawileh, R.A. | British Library Online Contents | 2013

Bayesian Fatigue Life Prediction of Corroded Steel Reinforcing Bars

Wei Wang / Jie Chen / Bo Diao et al. | DOAJ | 2021

Freier Zugriff

Study on Hysteretic Energy Dissipation of SMA Wires, Bars and Plates

Zhang, J.G. / Liu, Y.M. / Zhang, J.J. et al. | British Library Conference Proceedings | 2011