New method for generation of artificial earthquake record by new model in compression and Artificial Neural Networks

Authors

Abstract

In this paper, a new method for generation of artificial earthquake record from the target spectra is proposed. This method uses new model in compression named MFCC analysis and MLFF Artificial Neural Networks and wavelet analysis. This procedure uses the learning capabilities of neural network to expand the knowledge of the inverse recording from response spectra to earthquake accelerogram. In the first step, wavelet analysis is used to decompose earthquake accelerograms to several levels in which each level covers a special range of frequencies, and then for every level a neural network is trained to learn to relate the response spectra to wavelet coefficients. Mel-Frequency Cepstral Coefficient (MFCC) compress signals for better training of neural networks. Finally, the generated accelerogram using inverse discrete wavelet transform is obtained. Some example is presented to demonstrate the effectiveness of the proposed method.

Keywords

References

  1.  

    1.MacCann, W.M. and Shah, H.C. (1979), "Determining strong-motion duration of earthquake", Bulletin of the Seismological Society of America, Vol.69, pp. 1253-1265.

    2.Ahmadi, G. and Fan, F.G. (1990), "Nonstationary Kanai-Tajimi models for E1 Centro 1940 and Mexico City 1985 earthquake ",  Probabilistic Engineering Mechanics, Vol. 5, pp. 171-181.

    3.باقری عبدالله،(1384) "تولید شتابنگاشت مصنوعی با استفاده از الگوی کانای– تجیمی و آنالیز ویولت"، پایان نامه کارشناسی ارشد، دانشکده عمران، دانشگاه علم و صنعت ایران.

    4.Ghodrati Amiri, G., Raeisi Dehkordi, M. and Bagheri, A. (2005), "Generation of artificial earthquake records with a nonstationary Kanai-Tajimi model and wavelet transform", Proceedings of the International Symposium on Innovation & Sustainability of Structures in Civil Enginieering Including Seismic Engineering(ISISS'2005),  Nanjing, China, November 20-22.

    5.Olafsson, S. and Ragnar, S. (1995), "Application of ARMA models to estimate earthquake ground motion and structural response", Earthquake Engineering & Structural Dynamics, Vol. 24, pp. 951-956.

    6.Yeh, C.H. and Wen, Y.K. (1990), "Modeling of nonstationary ground motion and analysis of inelastic structural response", Structural Safety, Vol. 8, pp. 281–98.

    7.Ghaboussi, J. and Lin, C.J. (1998), "New method of generation spectra compatible accelerograms using neural network", Earthquake Engineering & Structural Dynamics, Vol. 27, pp. 377-396.

    8.Newland, D.E. (1994), "Random Vibration, Spectral and Wavelet Analysis" 3rd Edition, Longman Singapore, Publishers.

    9.Ghodrati Amiri, G., Ashtari, P. and Rahami, H. (2006), "New development of artificial record generation by wavelet theory" Structural Engineering and Mechanics, Vol. 22, pp. 185-195.

    1. G. Navarro, Wavelet Trees for All, Proceedings of 23rd Annual Symposium on Combinatorial Pattern Matching (CPM), 2012
    2. MATLAB Reference Guide, the Math Works, Inc., 2007.
      1. منهاج محمدباقر. هوش محاسباتی: شبکه‌های عصبی، جلد اول. انتشارات دانشگاه صنعتی امیر‌کبیر، 1377.
      2. رمضی ح. داده های پایه شتابنگاشت های شبکه شتابنگاری کشور. مرکز تحقیقات ساختمان و مسکن، نشریه شماره 256 . تهران، ایران 1376.
    3. Bryan Pellom, "Advanced Topics in speech processing and speech recognition", LSA 352, summer 2007.
    4. Seismosignal Software. Autumn, Seismosoft Inc., 2002.
    5. M. Fadavi Amiri, A. Akbari and G. Ghodrati Amiri” New Method for Generation of Artificial Earthquake Record ", Proceedings of the 14th World Conference on Earthquake Engineering, October 12-17, 2008, Beijing-China.
Journal of Modeling in Engineering
Volume 14, Issue 46
September 2016
Pages 75-85

Files

History

  • Receive Date: 17 July 2014
  • Revise Date: 27 October 2014
  • Accept Date: 27 October 2014

Share

How to cite

Statistics