Design of the base isolation system with artificial neural network models

This work presents the application of the artificial neural networks (ANN) for modeling and designing Seismic-Isolation (SI) systems consisting of Natural Rubber Bearings and Viscous Fluid Dampers subject to Near-Field (NF) earthquake ground motion. Four lumped-mass stick models representing a realistic five, ten, fifteen, and 20-story base-isolated buildings are used. The key response parameters selected to represent the behavior of SI system are the Damper Force (PDF), Total Maximum Displacement (DTM), the Peak the Top Story Acceleration Ratio (TSAR) of the isolated structure compared to the fixed-base structure and the maximum amplified drift ratio (δmax). Twenty-four NF earthquake records representing two seismic hazard levels are used. The commercial analysis program SAP2000 was used to perform the Time-History Analysis (THA) of the MDOF system (stick model representing a realistic N-story base-isolated building) subject to all 24 records. Different combinations of damping coefficients (c) and damping exponents (ą) are investigated under the 24 earthquake records to develop the database of feasible combinations for the SI system. The total number of considered THA combinations is 751680 and were used for training and testing the neural network. Mathematical models for the key response parameters are established via ANN and produced acceptable results with significantly less computation. The results of this study show that ANN models can be a powerful tool to be included in the design process of Seismic-Isolation (SI) systems, especially at the preliminary stages.

[1]  Samer Barakat,et al.  Multiple regression modeling of natural rubber seismic-isolation systems with supplemental viscous damping for near-field ground motion , 2013 .

[2]  Naci Caglar,et al.  Neural networks in 3-dimensional dynamic analysis of reinforced concrete buildings , 2008 .

[3]  H. Worthington.  Seismic Design for Nuclear Power Plants , 1971 .

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

[5]  D. R. Baughman,et al.  Neural Networks in Bioprocessing and Chemical Engineering , 1992 .

[6]  R. S. Jangid,et al.  Base isolation for near‐fault motions , 2001 .

[7]  Xu Wang,et al.  Spiking neural network-based target tracking control for autonomous mobile robots , 2015, Neural Computing and Applications.

[8]  Jin-Hoon Jeong,et al.  Effect of lead rubber bearing characteristics on the response of seismic-isolated bridges , 2008 .

[9]  Mahmut Bilgehan,et al.  A comparative study for the concrete compressive strength estimation using neural network and neuro-fuzzy modelling approaches , 2011 .

[10]  K. N. G. Fuller,et al.  Design and Testing of High Damping Rubber Earthquake Bearings for Retrofit Project in Armenia , 2000 .

[11]  Aslam Muhammad,et al.  An efficient model based on artificial bee colony optimization algorithm with Neural Networks for electric load forecasting , 2014, Neural Computing and Applications.

[12]  Ahmad Taher Azar,et al.  Linguistic Hedges Fuzzy Feature Selection for Differential Diagnosis of Erythemato-Squamous Diseases , 2012, SOFA.

[13]  Mônica Batista Leite,et al.  Prediction of compressive strength of concrete containing construction and demolition waste using artificial neural networks , 2013 .

[14]  Murat Ceylan,et al.  Determining Earthquake Performances of Existing Reinforced Concrete Buildings by Using ANN , 2015 .

[15]  Armando Cisternas,et al.  Earthquake hazard and seismic risk reduction , 2000 .

[16]  A. T. C. Goh,et al.  Back-propagation neural networks for modeling complex systems , 1995, Artif. Intell. Eng..

[17]  Paki Turgut,et al.  Artificial Neural Network Approach to Predict Compressive Strength of Concrete through Ultrasonic Pulse Velocity , 2010 .

[18]  J. Olden,et al.  A new R2-based metric to shed greater insight on variable importance in artificial neural networks , 2015 .

[19]  Robert Jankowski,et al.  Nonlinear Rate Dependent Model of High Damping Rubber Bearing , 2003 .

[20]  Ravindra Nagar,et al.  Modeling slump of ready mix concrete using genetic algorithms assisted training of Artificial Neural Networks , 2015, Expert Syst. Appl..

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

[22]  A. Arias.  A measure of earthquake intensity , 1970 .