Comparative analysis of filtering methods for measurement data from complex well configurations

About the authors:

David Yu. Shengeliya, Postgraduate Student, Department of Software, School of Computer Science, University of Tyumen, Tyumen, Russia; d.y.shengeliya@utmn.ru, https://orcid.org/0009-0004-5222-9672

Igor V. Kovalenko, Cand. Sci (Tech.), Product Development Manager, Gazpromneft Science & Technology Center, Tyumen, Russia; kovalenko.iv@gazpromneft-ntc.ru

Irina G. Zakharova, Cand. Sci. (Phys.-Math.), Professor, Department of Software, School of Computer Science, University of Tyumen, Tyumen, Russia; i.g.zakharova@utmn.ru, https://orcid.org/0000-0002-4211-7675

Abstract:

This article presents a comparative analysis of various filtering methods for synthetic measurements that simulate data from well test analysis (WTA).
The main objective of this work is to identify the most effective filtering methods for noisy WTA data, with the aim of preserving useful information and facilitating the subsequent interpretation of the results.
The initial dataset consisted of 200 synthetic pressure drawdown (PDD) and pressure buildup (PBU) curves with varying levels of artificially introduced noise. Both classical filtering methods (Kalman filter, Savitzky–Golay filter, one-dimensional Gaussian filtering) and numerical methods based on neural networks (autoencoders) and machine learning (support vector machines) were considered for data filtering.
The comparative analysis demonstrated that the performance of different filtering methods depends on the type of curve (PDD or PBU) and the well characteristics. The best results in terms of signal-to-noise ratio (SNR) and root mean square error (RMSE) were achieved using modern autoencoder-based methods.
The conclusion is that the choice of an optimal filtering method requires a detailed analysis of the specific problem and the characteristics of the input data. A combination of different filtering methods is proposed to improve the quality of processing and interpretation of WTA data for complex well designs.
The obtained results have practical significance, as they can simplify the segmentation of PDD and PBU curves, which is necessary for the correct identification of various operating periods of the well during the investigation process.

References:

Asalkhuzina, G. F., Davletbaev, A. Ya., Khabibullin, I. L., & Akhmetova, R. R. (2020). On the selection of suitable operate durations for injection tests in low permeability reservoirs. Tyumen State University Herald. Physical and Mathematical Modeling. Oil, Gas, Energy, 6(1), 135–149. https://doi.org/10.21684/2411-7978-2020-6-1-135-149 [In Russian]

Brilliant, L. S., Dulkarnaev, M. R., Danko, M. Yu., Elisheva, A. O., Nabiev, D. Kh., Khutornaya, A. I., & Malkov, I. N. (2022). Oil production management based on neural network optimization of well operation at the pilot project site of the Vatyeganskoe field (Territorial Production Enterprise Povkhneftegaz). Georesources, 24(1), 3–15. https://doi.org/10.18599/grs.2022.1.1 [In Russian]

Bukhmastova, S. V., Fakhreeva, R. R., Pityuk, Yu. A., Davletbaev, A. Ya., Azarova, T. P., Farger, D. V., & Yakupov, R. F. (2020). Approbation of MLR and CRMIP methods in research of well interference. Oil Industry Journal, (8), 58–62. https://doi.org/10.24887/0028-2448-2020-8-58-62 [In Russian]

Esipov, D. V., Kuranakov, D. S., Lapin, V. N., & Cherny, S. G. (2014). Mathematical models of hydraulic fracturing. Computational Technologies, 19(2), 33–61. [In Russian]

Zaikin, A. A., & Kareev, I. A. (2020). Modeling fluid flows in oil fields using the Kalman filter. Itogi nauki i tekhniki. Seriya “Sovremennaya matematika i ee prilozheniya. Tematicheskie obzory”, 175, 27–35. https://doi.org/10.36535/0233-6723-2020-175-27-35 [In Russian]

Kovalenko, I. V. (2023). Hydrodynamic simulation of horizontal wells by multi-stage hydraulic fracturing of a formation taking into account pressure losses due to streamline convergence. Oilfield Engineering, (2), 26–28. https://doi.org/10.33285/0207-2351-2023-2(650)-26-28 [In Russian]

Suleimanov, B. A., Dyshin, O. A., & Isaev, R. Zh. (2014). Interpretation of pressure built-up curves on the basis of analysis of bottomhole pressure detrministic moments. Oilfield Engineering, (1), 12–23. [In Russian]

Ansari, H. R., & Gholami, A. (2015). An improved support vector regression model for estimation of saturation pressure of crude oils. Fluid Phase Equilibria, 402, 124–132. https://doi.org/10.1016/j.fluid.2015.05.037

Apio, A., Dambros, J. W., Farenzena, M., & Trierweiler, J. O. (2019). Comparison of Kalman filter-based approaches for permanent downhole gauge pressure estimation in offshore oil production. Journal of Petroleum Science and Engineering, 182, Article 106254. https://doi.org/10.1016/j.petrol.2019.106254

Aung, Z., Mikhaylov, I. S., & Thu Aung, Y. (2020). Application of support vector system for solving problems of classification and forecasting of oil wells. In 2020 IEEE Conference of Russian young researchers in electrical and electronic engineering (EIConRus) (pp. 568–572). https://doi.org/10.1109/EIConRus49466.2020.9039343

Awad, M., & Khanna, R. (2015). Support vector regression. In Efficient learning machines (pp. 67–80). Apress. https://doi.org/10.1007/978-1-4302-5990-9_4

Jiang, J., Ren, H., & Zhang, M. (2022). A convolutional autoencoder method for simultaneous seismic data reconstruction and denoising. IEEE Geoscience and Remote Sensing Letters, 19, Article 7503405. https://doi.org/10.1109/LGRS.2021.3073560

Khoukhi, A., Oloso, M., Elshafei, M., Abdulraheem, A., & Al-Majed, A. (2011). Support vector regression and functional networks for viscosity and gas/oil ratio curves estimation. International Journal of Computational Intelligence and Applications, 10(03), 269–293. https://doi.org/10.1142/S1469026811003100

Kuester, J., Gross, W., & Middelmann, W. (2021). 1D-convolutional autoencoder based hyperspectral data compression. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLIII-B1-2021, 15–21. https://doi.org/10.5194/isprs-
archives-XLIII-B1-2021-15-2021

Lei, J., Fan, Y., Li, Y., & Xu, T. (2020). Data analysis of hydraulic fracturing pressure in unconventional oil and gas fields. IOP Conference Series: Earth and Environmental Science, 558(2), Article 022057. https://doi.org/10.1088/1755-1315/558/2/022057

Nikoofard, A., Aarsnes, U. J. F., Johansen, T. A., & Kaasa, G.-O. (2015). Estimation of states and parameters of a drift-flux model with unscented Kalman filter. IFAC-PapersOnLine, 48(6), 165–170. https://doi.org/10.1016/j.ifacol.2015.08.026

Osman, M. S., & Stewart, G. (1997, March 15–18). Pressure data filtering and horizontal well test analysis case study [Conference paper SPE-37802-MS]. Middle East Oil Show and Conference, Bahrain. https://doi.org/10.2118/37802-MS

Unneland, T., Manin, Y., & Kuchuk, F. (1998). Permanent gauge pressure and rate measurements for reservoir description and well monitoring: Field cases. SPE Reservoir Evaluation & Engineering, 1(3), 168–176. https://doi.org/10.2118/38658-PA

Vaferi, B., Eslamloueyan, R., & Ayatollahi, Sh. (2011). Automatic recognition of oil reservoir models from well testing data by using multi-layer perceptron networks. Journal of Petroleum Science and Engineering, 77(3–4), 254–262. https://doi.org/10.1016/j.petrol.2011.03.002