Reconstruction of acoustic full waveforms using artificial neural networks

• Autorzy: Jarzyna J. , Wawrzyniak K. , Olesiński K.
• Języki publikacji: EN

Abstrakty

EN

A successful application of Artificial Neural Network (ANN) to reconstructing acoustic waveforms is presented. During processing the acoustic full waveforms the authors met incorrectly recorded signals. Greater amplitudes of the second waveform (recorded by the far receiver) disable, among others, the proper determination of attenuation of elastic waves in rock formation. To reconstruct the second waveform on the basis of the first one (recorded by the near receiver) two feed-forward neural networks with different number of neurons in hidden layer were used. The networks were trained using Conjugate Gradient and Back Propagation methods, using different sets of training coefficients ? and momentum ?. The training, verifying and testing sets were formed by pairs of acoustic waveforms recorded by Long Spaced Sonic device. The amplitudes of P waves taken from signals recorded by the near receiver were used as the input, whereas the output data came from the far receiver wavetrains. The artificial neural networks were trained on the two data sets: the first one - pairs of recorded waveforms, and the second one - pairs of waveforms with corrected time shift of the far signals in relation to the near ones. Data correction substantially improved network operation: from about 21% signals reconstructed faultlessly (when the best ANN was trained on the recorded data set) to about 59% (trained on the corrected one).

Słowa kluczowe

EN

well logging; acoustic wavetrains; artificial neural network

• Wydawca: Instytut Geofizyki PAN
• Czasopismo: Acta Geophysica Polonica
• Rocznik: 2004
• Tom: Vol. 52, nr 3
• Strony: 319--336
• Opis fizyczny: Bibliogr. 11 poz.

Twórcy

autor

Jarzyna J.

• Faculty of Geology, Geophysics and Environmental Protection, Department of Geophysics, AGH University of Science and Technology, Aleja Mickiewicza 30, 30-059 Kraków

autor

Wawrzyniak K.

• Faculty of Geology, Geophysics and Environmental Protection, Department of Geophysics, AGH University of Science and Technology, Aleja Mickiewicza 30, 30-059 Kraków

autor

Olesiński K.

• Petrobaltic-Oil and Gas Exploration-Production Company Ltd. ul. Stary Dwór 9, 80-958 Gdańsk, Poland

Bibliografia

• 1. Bała, M., and J. Jarzyna, 2001, Acoustic full wavetrains in shallow boreholes, Proc. 7th Meeting EEGS, Birmingham, 2-6. Sept. 2000, SEIS15P, 2 p.
• 2. De, G.S., D.F. Winterstein and M.A. Meadows, 1994, Comparison of P- and S-wave velocities and Q'sfrom VSP and sonic log data, Geophysics 59, 1512-1529.
• 3. Jarzyna, J., M. Bała and A. Cichy, 2001, Interpretation of acoustic waveforms - FALAwin programs, Arbor, Kraków (in Polish), 60 p.
• 4. Masters, T., 1993, Advanced algorithms for neural networks, John Wiley and Sons Inc., New York-Chichester.
• 5. Masters, T., 1996, Neural networks in practice, Wyd. Nauk.-Techn., Warszawa (in Polish).
• 6. Osowski, S., 1996, Artificial neural networks - algorithms, Wyd. Nauk.-Techn., Warszawa (in Polish).
• 7. Paillet, F.L., and J.E. White, 1982, Acoustic modes of propagation in the borehole and their relationships to rock properties, Geophysics 47, 8,1215-1228.
• 8. Statistica Neural Networks™ (1999), wersja 4.0.
• 9. Świątnicki, Z., and R. Wantoch-Rekowski, 1998, Artificial neural networks in military applications, Bellona, Warszawa (in Polish).
• 10. Tadeusiewicz, R., 1993, Artificial Neural Networks, Akad. Oficyna Wydawnicza, Warszawa (in Polish).
• 11. Wawrzyniak, K., 2002, Improving of acoustic full wave forms using artificial neural network 64th EAGE Conference and Exhibition, Fortezza Da Basso, Florence, Italy, 27-30 2002; P144.