Hybrid Evolutionary-Neural Network Approach in Generation of Artificial Accelerograms Using Principal Component Analysis and Wavelet-Packet Transform

A novel hybrid evolutionary neural network method to generate multiple spectrum-compatible artificial earthquake accelerograms (SCAEAs) is presented. Genetic algorithm is employed to optimize the weight values of networks. In order to improve the training efficiency, principal component analysis along with some other reduction techniques are used. The proposed evolutionary neural network develops an inverse mapping from compacted and reduced spectrum coefficients to the metamorphosed accelerogram's wavelet packet coefficients. As compared to the traditional methods, our algorithm is capable of generating an ensemble of dissimilar 10, 20, 30, and 40 s SCAEAs with better spectrum-compatibility and diversity, and proper computational efforts.

[1]  Vitelmo V. Bertero,et al.  Earthquake Engineering: From Engineering Seismology To Performance-Based Engineering , 2020 .

[2]  S. Mallat.  A wavelet tour of signal processing , 1998 .

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

[4]  W. J. Hall,et al.  Earthquake spectra and design , 1982 .

[5]  Sujit K. Ghosh,et al.  Essential Wavelets for Statistical Applications and Data Analysis , 2001, Technometrics.

[6]  Goodarz Ahmadi,et al.  Generation of artificial earthquake records with a nonstationary Kanai–Tajimi model , 2001 .

[7]  Jamshid Ghaboussi,et al.  Generating multiple spectrum compatible accelerograms using stochastic neural networks , 2001 .

[8]  Abdollah Bagheri,et al.  New method for generation of artificial ground motion by a nonstationary Kanai-Tajimi model and wavelet transform , 2007 .

[9]  S. Pourzeynali,et al.  Active control of high rise building structures using fuzzy logic and genetic algorithms , 2007 .

[10]  Jian Fan,et al.  Texture Classification by Wavelet Packet Signatures , 1993, MVA.

[11]  Vinay K. Gupta,et al.  WAVELET-BASED GENERATION OF SPECTRUM COMPATIBLE TIME-HISTORIES , 2002 .

[12]  Danilo P. Mandic,et al.  Recurrent Neural Networks for Prediction , 2001 .

[13]  Benoît Vaillant,et al.  A genetic local tuning algorithm for a class of combinatorial networks design problems , 2001, IEEE Communications Letters.

[14]  W. Silva,et al.  Stochastic Modeling of California Ground Motions , 2000 .

[15]  R. Ogden,et al.  Essential Wavelets for Statistical Applications and Data Analysis , 1996 .

[16]  G. Ghodrati Amiri,et al.  Generation of Multiple Earthquake Accelerograms Compatible with Spectrum Via the Wavelet Packet Transform and Stochastic Neural Networks , 2009 .

[17]  M. Zuo,et al.  Gearbox fault detection using Hilbert and wavelet packet transform , 2006 .

[18]  Luis E. Suarez,et al.  Applications of the wavelet transform in the generation and analysis of spectrum-compatible records , 2007 .

[19]  S. Rajasekaran,et al.  GENERATION OF ARTIFICIAL EARTHQUAKE MOTION RECORDS USING WAVELETS AND PRINCIPAL COMPONENT ANALYSIS , 2006 .

[20]  Vinay K. Gupta,et al.  Wavelet‐based characterization of design ground motions , 2002 .

[21]  G. Ghodrati Amiri,et al.  New development of artificial record generation by wavelet theory , 2006 .

[22]  F. Sabetta,et al.  Estimation of response spectra and simulation of nonstationary earthquake ground motions , 1996, Bulletin of the Seismological Society of America.

[23]  JONATHAN HANCOCK,et al.  AN IMPROVED METHOD OF MATCHING RESPONSE SPECTRA OF RECORDED EARTHQUAKE GROUND MOTION USING WAVELETS , 2006 .

[24]  J. Iyama,et al.  Application of wavelets to analysis and simulation of earthquake motions , 1999 .

[25]  Anil K. Chopra,et al.  Dynamics of Structures: Theory and Applications to Earthquake Engineering , 1995 .

[26]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[27]  Jenq-Neng Hwang,et al.  Handbook of Neural Network Signal Processing , 2000, IEEE Transactions on Neural Networks.

[28]  Zhang Yu-shan,et al.  Artificial ground motion compatible with specified ground shaking peaks and target response spectrum , 2006 .

[29]  Armen Der Kiureghian,et al.  A stochastic ground motion model with separable temporal and spectral nonstationarities , 2008 .

[30]  Markus Brameier,et al.  On linear genetic programming , 2005 .

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

[32]  Patrick van der Smagt,et al.  Introduction to neural networks , 1995, The Lancet.

[33]  Jamshid Ghaboussi,et al.  Biologically inspired soft computing methods in structural mechanics and engineering , 2001 .

[34]  Farzad Naeim,et al.  The Seismic Design Handbook , 1989 .

[35]  Jamshid Ghaboussi,et al.  Soft computing with neural networks for engineering applications: Fundamental issues and adaptive approaches , 1998 .

[36]  Goodarz Ahmadi,et al.  Nonstationary Kanai-Tajimi models for El Centro 1940 and Mexico City 1985 earthquakes , 1990 .

[37]  Nikolaos P. Politis.  Advanced Time-Frequency Analysis Applications in Earthquake Engineering , 2004 .

[38]  Haresh C. Shah,et al.  Determining strong-motion duration of earthquakes , 1979 .