A neural network based methodology to predict site-specific spectral acceleration values

A general neural network based methodology that has the potential to replace the computationally-intensive site-specific seismic analysis of structures is proposed in this paper. The basic framework of the methodology consists of a feed forward back propagation neural network algorithm with one hidden layer to represent the seismic potential of a region and soil amplification effects. The methodology is implemented and verified with parameters corresponding to Delhi city in India. For this purpose, strong ground motions are generated at bedrock level for a chosen site in Delhi due to earthquakes considered to originate from the central seismic gap of the Himalayan belt using necessary geological as well as geotechnical data. Surface level ground motions and corresponding site-specific response spectra are obtained by using a one-dimensional equivalent linear wave propagation model. Spectral acceleration values are considered as a target parameter to verify the performance of the methodology. Numerical studies carried out to validate the proposed methodology show that the errors in predicted spectral acceleration values are within acceptable limits for design purposes. The methodology is general in the sense that it can be applied to other seismically vulnerable regions and also can be updated by including more parameters depending on the state-of-the-art in the subject.

[1]  I. M. Idriss,et al.  Influence of Soil Conditions on Ground Motions During Earthquakes , 1969 .

[2]  A. K. Nagpal,et al.  Neural Network for Creep and Shrinkage Deflections in Reinforced Concrete Frames , 2004 .

[3]  G. Atkinson,et al.  FINSIM--a FORTRAN Program for Simulating Stochastic Acceleration Time Histories from Finite Faults , 1998 .

[4]  K. S. Rao,et al.  Liquefaction studies for seismic microzonation of Delhi region , 2007 .

[5]  F. Vaccari,et al.  Site-specific Microzonation Study in Delhi Metropolitan City by 2-D Modelling of SH and P-SV Waves , 2004 .

[6]  Julián M. Londoño,et al.  On the applicability of neural networks for soil dynamic amplification analysis , 2001 .

[7]  M. Tehranizadeh,et al.  APPLICATION OF ARTIFICIAL INTELLIGENCE FOR CONSTRUCTION OF DESIGN SPECTRA , 2004 .

[8]  C. Hsein Juang,et al.  Appraising cone penetration test based liquefaction resistance evaluation methods: artificial neural network approach , 1999 .

[9]  Rebecca Bendick,et al.  Geodetic constraints on the translation and deformation of India: implications for future great Himalayan earthquakes , 1998 .

[10]  Hojjat Adeli,et al.  Neural Networks in Civil Engineering: 1989–2000 , 2001 .

[11]  Yoram Reich,et al.  Evaluating machine learning models for engineering problems , 1999, Artif. Intell. Eng..

[12]  Sang Whan Han,et al.  Neural-network-based models for generating artificial earthquakes and response spectra , 2002 .

[13]  T. Mammo,et al.  Site-specific ground motion simulation and seismic response analysis at the proposed bridge sites within the city of Addis Ababa, Ethiopia , 2005 .

[14]  Chang-Guk Sun,et al.  Geologic site conditions and site coefficients for estimating earthquake ground motions in the inland areas of Korea , 2005 .

[15]  G. Atkinson,et al.  Modeling finite-fault radiation from the ωn spectrum , 1997, Bulletin of the Seismological Society of America.

[16]  William K. Mohanty,et al.  Ground Motion in Delhi from Future Large/Great Earthquakes in the Central Seismic Gap of the Himalayan Arc , 2002 .

[17]  Jamshid Ghaboussi,et al.  New method of generating spectrum compatible accelerograms using neural networks , 1998 .

[18]  Nelson Lam,et al.  Analysis of long-distance earthquake tremors and base shear demand for buildings in Singapore , 2002 .

[19]  F. E. Heuze,et al.  Estimating site-specific strong earthquake motions , 2004 .

[20]  P. B. Schnabel.  SHAKE-A Computer Program for Earthquake Response Analysis of Horizontally Layered Sites , 1970 .

[21]  Duhee Park,et al.  Evaluation of seismic site factors in the Mississippi Embayment. II. Probabilistic seismic hazard analysis with nonlinear site effects , 2005 .

[22]  Kinya Miura,et al.  Equivalent linear method considering frequency dependent characteristics of stiffness and damping , 2002 .

[23]  Tienfuan Kerh,et al.  Neural network estimation of ground peak acceleration at stations along Taiwan high-speed rail system , 2005, Eng. Appl. Artif. Intell..

[24]  Adrian M. Chandler,et al.  Seismic displacement response spectrum estimated from the frame analogy soil amplification model , 2001 .

[25]  R. Dobry,et al.  Effect of Soil Plasticity on Cyclic Response , 1991 .