Intelligent filtering of field data
https://doi.org/10.31660/0445-0108-2024-5-132-147
Abstract
In the oil and gas industry, the measured parameters during oil and gas production are often affected by noise, which contributes to complex and non-monotonic dynamics. This makes manual analysis and interpretation extremely difficult.
Therefore, this article aims to develop an algorithm capable of identifying and removing noise (signal changes without a clear cause) in the production parameters of well operation.
The article examines data smoothing methods, including moving average, exponential smoothing, Kalman filter, Wiener filter, Savitzky-Golay filter, Fourier transform, and wavelet transform. The authors identified advantages and limitations. An alternative approach is proposed, combining machine learning methods with standard data filtering tools. The developed algorithm restores the true dynamics of well performance metrics and filters out and smooths noise related to technical malfunctions. The novelty of the algorithm lies in using an LSTM neural network to extract the trend component from noisy dynamics, taking into account events occurring at the well itself as well as events happening at surrounding wells.
Keywords
2.8.4. Development and operation of oil and gas fields (technical sciences)
About the Authors
R. Y. PonomarevRussian Federation
Roman Y. Ponomarev, Manager
Tyumen
A. A. Leshchenko
Russian Federation
Anton A. Leshchenko, Chef Specialist
Tyumen
R. R. Ziazev
Russian Federation
Ramil R. Ziazev, Deputy Head of the Department
Tyumen
M. M. Galiullin
Russian Federation
Marat M. Galiullin, Director of Field Development of Khanty-Mansiysk Autonomous Okrug
Tyumen
R. R. Migmanov
Russian Federation
Ruslan R. Migmanov, Chef Specialist
Tyumen
M. I. Ivlev
Russian Federation
Mikhail I. Ivlev, Chef Specialist
Tyumen
References
1. Ivanov, A. V., & Stepanov, S. V. (2017). Mathematical modeling of non-stationary operation of an oil well, taking into account the imbalance of phase permeability. Bulletin of the Tyumen State University. Physical and mathematical modeling. Oil, gas, energy, 3(3), pp. 70-82. (In Russian).
2. Stepanov, S. V. (2008). Development and operation of oil fields, Numerical research of capillary pressure and compressibility effect on the drowning dynamics. Oil industry, (8), pp. 72-74. (In Russian).
3. Kopyrkin, K. (2001). Dynamic moving averages. Modern trading, (5-6), pp. 8-12. (In Russian).
4. Kalman, R. E. (1960). A new approach to linear filtering and prediction problems. Journal of Basic Engineering, 82(1), pp. 35-45. (In English). DOI: 10.1115/1.3662552
5. Wiener N. (1950). The extrapolation, interpolation and smoothing of stationary time series. Journal of the Royal Statistical Society. Series A (General), 113(3), pp. 413-414. (In English). DOI: 10.2307/2981007
6. Kalambet, Yu. A., Maltsev, S. A., & Kozmin, Yu. P. (2015). Confidence intervals for weighted least squares technique and calibration strategy. Industrial laboratopy. Materials diagnostics, 81(1-1), pp. 69-76. (In Russian).
7. Enke, C. G., & Nieman, T. A. (1976). Signal-to-noise ratio enhancement by least-squares polynomial smoothing. Analytical Chemistry, 48(8), pp. 705A-712A. (In English). DOI: 10.1021/ac50002a007
8. Savitzky, A., & Golay, M. J. E. (1964). Smoothing and differentiation of data by simplified least squares procedures. Analytical chemistry, 36(8), pp. 1627-1639. (In English). DOI: 10.1021/ac60214a047
9. Kondratieva, T. N. (2017). Forecasting the trends in financial time series using the LSTM neural network. Naukovedenie, 9(4). (In Russian). Available at: http://naukovedenie.ru/PDF/56TVN417.pdf
10. Samoilov, D. Yu. (2019). An information-measuring and control system for the intensification of oil production and the determination of the water content of well products. Avtoref. diss. … kand. techn. nauk. Ufa, 22 p. (In Russian).
Review
For citations:
Ponomarev R.Y., Leshchenko A.A., Ziazev R.R., Galiullin M.M., Migmanov R.R., Ivlev M.I. Intelligent filtering of field data. Oil and Gas Studies. 2024;(5):132-147. (In Russ.) https://doi.org/10.31660/0445-0108-2024-5-132-147