Earthquake Hazard Safety Assessment of Existing Buildings Using Optimized Multi-Layer Perceptron Neural Network

The latest earthquakes have proven that several existing buildings, particularly in developing countries, are not secured from damages of earthquake. A variety of statistical and machine-learning approaches have been proposed to identify vulnerable buildings for the prioritization of retrofitting. The present work aims to investigate earthquake susceptibility through the combination of six building performance variables that can be used to obtain an optimal prediction of the damage state of reinforced concrete buildings using artificial neural network (ANN). In this regard, a multi-layer perceptron network is trained and optimized using a database of 484 damaged buildings from the Duzce earthquake in Turkey. The results demonstrate the feasibility and effectiveness of the selected ANN approach to classify concrete structural damage that can be used as a preliminary assessment technique to identify vulnerable buildings in disaster risk-management programs.

[1]  Devrim Özhendekci,et al.  Rapid Seismic Vulnerability Assessment of Low- to Mid-Rise Reinforced Concrete Buildings Using Bingöl's Regional Data , 2012 .

[2]  Ercan Işık,et al.  Consistency of the rapid assessment method for reinforced concrete buildings , 2016 .

[3]  J. L. Ródenas,et al.  Proposal for new values of behaviour modifiers for seismic vulnerability evaluation of reinforced concrete buildings applied to Lorca (Spain) using damage data from the 2011 earthquake , 2017, Bulletin of Earthquake Engineering.

[4]  Mehmet Inel,et al.  Seismic risk assessment of buildings in urban areas: a case study for Denizli, Turkey , 2008 .

[5]  M. Hakan Arslan,et al.  An evaluation of effective design parameters on earthquake performance of RC buildings using neural networks , 2010 .

[6]  P. Kapetana,et al.  Seismic Assessment οf Buildings By Rapid VisualScreening Procedures , 2007 .

[7]  Zekâi Sen.  Rapid visual earthquake hazard evaluation of existing buildings by fuzzy logic modeling , 2010, Expert Syst. Appl..

[8]  Wulfram Gerstner,et al.  Universality in neural networks: the importance of the ‘mean firing rate’ , 1992, Biological Cybernetics.

[9]  Artur Zbiciak,et al.  The Influence of Input Data Standardization Method on Prediction Accuracy of Artificial Neural Networks , 2016 .

[10]  Solomon Tesfamariam,et al.  Risk-Based Seismic Evaluation of Reinforced Concrete Buildings , 2008 .

[11]  Tin Kam Ho,et al.  Machine Learning Made Easy: A Review of Scikit-learn Package in Python Programming Language , 2019, Journal of Educational and Behavioral Statistics.

[12]  Murat Ceylan,et al.  AN ANN APPROACHES ON ESTIMATING EARTHQUAKE PERFORMANCES OF EXISTING RC BUILDINGS , 2012 .

[13]  Konstantinos Morfidis,et al.  Seismic parameters' combinations for the optimum prediction of the damage state of R/C buildings using neural networks , 2017, Adv. Eng. Softw..

[14]  Mohammadreza Yadollahi,et al.  Seismic Vulnerability Functional Method for Rapid Visual Screening of Existing Buildings , 2012 .

[15]  Giuseppina Uva,et al.  A practical approach for estimating the floor deformability in existing RC buildings: evaluation of the effects in the structural response and seismic fragility , 2019, Bulletin of Earthquake Engineering.

[16]  Ahmet Yakut,et al.  A Screening Procedure for Seismic Risk Assessment in Urban Building Stocks , 2007 .

[17]  Radhikesh P. Nanda,et al.  Rapid visual screening procedure of existing building based on statistical analysis , 2018, International Journal of Disaster Risk Reduction.

[18]  Guney Ozcebe,et al.  Prediction of potential damage due to severe earthquakes , 2004 .

[19]  Ahmet Yakut,et al.  Seismic vulnerability assessment using regional empirical data , 2006 .

[20]  Hojjat Adeli,et al.  Perceptron Learning in Engineering Design , 2008 .

[21]  Mehul Shah,et al.  A Proposed Rapid Visual Screening Procedure for Seismic Evaluation of RC-Frame Buildings in India , 2010 .

[22]  Naci Caglar,et al.  Neural network based model for seismic assessment of existing RC buildings , 2013 .

[23]  Gavin C. Cawley,et al.  On Over-fitting in Model Selection and Subsequent Selection Bias in Performance Evaluation , 2010, J. Mach. Learn. Res..

[24]  Solomon Tesfamariam,et al.  Seismic Vulnerability Assessment of Reinforced Concrete Buildings Using Hierarchical Fuzzy Rule Base Modeling , 2010 .

[25]  Solomon Tesfamariam,et al.  Earthquake induced damage classification for reinforced concrete buildings , 2010 .

[26]  Hakan Ozbasaran,et al.  Earthquake failures of cantilever projections buildings , 2007 .

[27]  Romà Tauler,et al.  Introduction to the Data Analysis Relevance in the Omic Era , 2018 .

[29]  Alex H. Barbat,et al.  A probabilistic approach for seismic risk assessment based on vulnerability functions. Application to Barcelona , 2018, Bulletin of Earthquake Engineering.

[30]  Polat Gülkan,et al.  Buildings Subjected to Recurring Earthquakes: A Tale of Three Cities , 2011 .

[31]  Fumio Yamazaki,et al.  Neural networks for quick earthquake damage estimation , 1995 .

[32]  Ehsan Harirchian,et al.  Improved Rapid Visual Earthquake Hazard Safety Evaluation of Existing Buildings Using a Type-2 Fuzzy Logic Model , 2020 .

[33]  Murat Saatcioglu,et al.  Dynamic analysis of buildings for earthquake-resistant design , 2003 .