Generating multiple spectrum compatible accelerograms using stochastic neural networks

A new neural-network-based methodology for generating artificial earthquake spectrum compatible accelerograms from response spectra was proposed in 1997, in which, the learning capabilities of neural networks were used to develop the knowledge of the inverse mapping from the response spectra to earthquake accelerograms. Recently, this methodology has been further extended and enhanced. This paper presents a new stochastic neural network that is capable of generating multiple earthquake accelerograms from a single-response spectrum. A new stochastic feature to the neural network has been combined with a new scheme for data compression using the replicator neural networks developed in the original method. A benefit of this extended methodology is gaining efficiency in compressing the earthquake accelerograms and extracting their characteristics. The proposed method produces a stochastic ensemble of earthquake accelerograms from any response spectra or design spectra. An example is presented that used 100 recorded accelerograms to train the neural network and several design spectra and response spectra to test this improved methodology. Copyright © 2001 John Wiley & Sons, Ltd.

[1]  Geoffrey E. Hinton,et al.  A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[2]  Andrzej Cichocki,et al.  Neural networks for optimization and signal processing , 1993 .

[3]  William T. Holmes,et al.  The 1997 NEHRP Recommended Provisions for Seismic Regulations for New Buildings and Other Structures , 2000 .

[4]  John Shawe-Taylor,et al.  Probabilistic Bit Stream Neural Chip: Theory , 1991 .

[5]  Pol D. Spanos,et al.  Simulation of Stationary Random Processes: Two-Stage MA to ARMA Approach , 1990 .

[6]  R. Narayana Iyengar,et al.  Generation of spectrum compatible accelerograms , 1979 .

[7]  John Shawe-Taylor,et al.  Learning in Stochastic Bit Stream Neural Networks , 1996, Neural Networks.

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

[9]  Erol Gelenbe,et al.  Random Neural Networks with Negative and Positive Signals and Product Form Solution , 1989, Neural Computation.

[10]  Mihailo D. Trifunac,et al.  Generation of artificial strong motion accelerograms , 1979 .

[11]  R. Haddon,et al.  Use of empirical Green's functions, spectral ratios, and kinematic source models for simulating strong ground motion , 1996, Bulletin of the Seismological Society of America.

[12]  George W. Housner,et al.  Generation of Artificial Earthquakes , 1964 .

[13]  Chu-Chieh Jay Lin.  A Neural Network-Based Methodology for Generating Spectrum -Compatible Earthquake Accelerograms , 2000 .

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

[15]  Jamshid Ghaboussi,et al.  Autoprogressive training of neural network constitutive models , 1998 .

[16]  Mohsin R. Khan.  Improved method of generation of artificial time‐histories, rich in all frequencies, from floor spectra , 1987 .

[17]  M. K. Kaul.  Spectrum-Consistent Time-History Generation , 1978 .

[18]  Gary C. Hart,et al.  Simulation of artificial earthquakes , 1973 .

[19]  S. Levy,et al.  Generation of artificial time-histories, rich in all frequencies, from given response spectra , 1976 .

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

[21]  Ahmet S. Cakmak,et al.  Simulation of earthquake ground motions using autoregressive moving average (ARMA) models , 1981 .

[22]  Nien-Chien Tsai.  Spectrum-Compatible Motions for Design Purposes , 1972 .

[23]  Masanori Izumi,et al.  A method of artificial generation of earthquake ground motion , 1989 .

[24]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.