Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 8, Issue 4, 2024

Reservoir Sensitivity Forecasting Method Based on Hybrid Improved CNN and BiGRU Unit

Download as PDF

DOI: 10.23977/acss.2024.080404 | Downloads: 8 | Views: 60

Author(s)

Weizhi Ni 1, Yi Wang 1, Xuewen Chen 1

Affiliation(s)

1 Computer Science and Engineering Department, Sichuan University of Science and Engineering, Yibin, China

Corresponding Author

Yi Wang

ABSTRACT

Reservoir sensitivity evaluation is used to evaluate the degree of damage to various operating fluids and production parameters of the reservoir in the production process of oil and gas wells. The neural network is widely used in reservoir sensitivity forecasting because of its nonlinear solid fitting and generalisation ability. Although many neural network models have been applied to reservoir sensitivity forecasting, there is still room for improvement in the accuracy of the models. Therefore, to improve the prediction accuracy of the forecasting model, this study will introduce a novel convolutional neural network model (WOA-CNN-BiGRU) integrated with a whale optimisation algorithm and bidirectional gated recurrent unit to forecast the sensitivity of low permeability reservoir. The experiment used relevant datasets to test the model strictly, and the previous BPNN, Elman, and RBF models were compared. The result shows that the percentage error of the WOA-CNN-BiGRU model was as low as 2.6%, which was lower than other forecasting models. The results show that the accuracy of the WOA-CNN-BiGRU model is not only higher than that of engineering measurement methods but also higher than that of other existing models, which has a good potential for application in the industry of reservoir sensitivity forecasting.

KEYWORDS

Reservoir damage, data analysis, forecasting model, optimization algorithm, neural network

CITE THIS PAPER

Weizhi Ni, Yi Wang, Xuewen Chen, Reservoir Sensitivity Forecasting Method Based on Hybrid Improved CNN and BiGRU Unit. Advances in Computer, Signals and Systems (2024) Vol. 8: 20-31. DOI: http://dx.doi.org/10.23977/acss.2024.080404.

REFERENCES

[1] W. He and Z. Liu, Numerical simulation of formation damage by drilling fluid in low permeability sandstone reservoirs, Journal Of Petroleum Exploration And Production 11(4) (2021), 1865–1871.
[2] X. Li, Q. Zhang, P. Liu, T. Li, G. Liu, Z. Liu and H. Zhao, Investigation on the microscopic damage mechanism of fracturing fluids to low-permeability sandstone oil reservoir by nuclear magnetic resonance, Journal of Petroleum Science and Engineering 209 (2022), 109821.
[3] Wang, L., Zhang, H., Peng, X., Wang, P., Zhao, N., Chu, S., Wang, X., And Kong, L. (2019). Water-sensitive damage mechanism and the injection water source optimization of low permeability sandy conglomerate reservoirs. Petroleum Exploration and Development, 46(6):1218– 1230. 
[4] Yang, F. (2023). Sensitivity evaluation and stimulation optimization of ultralow permeability sandstone reservoir. ACS OMEGA, 8(40):37176–37185. 
[5] Zhang, L., Zhou, F., Zhang, S., Wang, Y., Wang, J., and Wang, J. (2019). Investigation of watersensitivity damage for tight low-permeability sandstone reservoirs. ACS OMEGA, 4(6):11197–11204.
[6] Yan, G. (2020). A new method for fast prediction of reservoir sensitivit. Yunnan Chemical Technology,47(101-102).
[7] SHENG Kemin, J. G. (2023). Prediction of four kinds of sensibility damages to hydrocarbon reservoirs based on random forest algorithm. Drilling Fluid Completion Fluid, 40(423-430).
[8] Chen, F., Bai, B., Wang, Z.-W., Zhou, L., Xu, Y.-X., and An, C.-Q. (2021). Prediction of reservoir damage caused by fracturing fluid based on bp neural network. In 2021 International Conference on Artificial Intelligence and Electromechanical Automation (AIEA), pages 298–301.
[9] Fei Chen, Chaohui Yan, B. Z. (2022). Study on damage mechanism of fracturing fluid reservoir and rbf neural network prediction. Applied Mathematics, Modeling and Computer Simulation, pages 779-784.
[10] Qiaozhi, Wang, Y. S. A. J. B. G. (2020). Prediction of reservoir sensitivity in offshore oil field by radial basis function neural network. Chemical Engineering Management, pages 85–86.
[11] Wang, J. (2020). The research of prediction on formation sensitivity based on mpga-elman neural network. China University Of Petroleum.
[12] Yufei Wang, Tao Fang, H. C. Y. L. S. Z. (2022). Numerical simulation and prediction of stress sensitivity of fractured reservoir. Journal of Shengli College China University of Petroleum.
[13] Mirjalili, S. and Lewis, A. (2016). The whale optimization algorithm. Advances in Engineering Software, 95:51–67.
[14] Xin, L., Jiang-ping, L., Qing, H., and Peng-wei, H. (2023). Optimization of prediction model for milk fat content based on improved whale optimization algorithm. Spectroscopy And Spectral Analysis, 43(9):2779–2784.
[15] Tair, M., Bacanin, N., Zivkovic, M., and Venkatachalam, K. (2022). A chaotic oppositional whale optimisation algorithm with firefly search for medical diagnostics. CMC-COMPUTERS MATERIALS & CONTINUA, 72(1):959–982.
[16] Si, Q. and Li, C. (2023). Indoor robot path planning using an improved whale optimization algorithm.SENSORS, 23(8).
[17] Brodzicki, A., Piekarski, M., and Jaworek-Korjakowska, J. (2021). The whale optimization algorithm approach for deep neural networks. SENSORS, 21(23).
[18] Li, K., Xi, Y., Su, Z., Zhu, J., and Wang, B. (2021). Research on reservoir lithology prediction method based on convolutional recurrent neural network. COMPUTERS & ELECTRICAL ENGINEERING, 95.
[19] Almufadi, N. and Qamar, A. M. (2022). Deep convolutional neural network based churn prediction for telecommunication industry. COMPUTER SYSTEMS SCIENCE AND ENGINEERING, 43(3):1255–1270.
[20] Lu, F., Liang, Y., Wang, X., Gao, T., Chen, Q., Liu, Y., Zhou, Y., Yuan, Y., and Liu, Y. (2022). Prediction of amorphous forming ability based on artificial neural network and convolutional neural network. COMPUTATIONAL MATERIALS SCIENCE, 210.
[21] Dong, S., Wang, L., Zeng, L., Du, X., Ji, C., Hao, J., Yang, X., and Li, H. (2023). Fracture identification in reservoirs using well log data by window sliding recurrent neural network. GEOENERGY SCIENCE AND ENGINEERING, 230. 
[22] Zhang, C., Song, X., Su, Y., and Li, G. (2022). Real-time prediction of rate of penetration by combining attention-based gated recurrent unit network and fully connected neural networks. Journal Of Petroleum Science And Engineering, 213. 
[23] Li, X., Ma, X., Xiao, F., Xiao, C., Wang, F., and Zhang, S. (2022b). Time-series production forecasting method based on the integration of bidirectional gated recurrent unit (bi-gru) network and sparrow search algorithm (ssa). JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING, 208(A).
[24] Li, X., Ma, X., Xiao, F., Xiao, C., Wang, F., and Zhang, S. (2023). Multistep ahead multiphase production prediction of fractured wells using bidirectional gated recurrent unit and multitask learning.SPE JOURNAL.
[25] Hu, J., Shen, L., Albanie, S., Sun, G., and Wu, E. (2020). Squeeze-and-excitation networks.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,28(1):381-400.
[26] Zhou, Y. and Wong, L. N. Y. (2023). Automatic, point-wise rock image enhancement by novel unsupervised deep learning: Dataset establishment and model development. ROCK MECHANICS AND ROCK ENGINEERING.
[27] Ding, K., Xue, L., Ran, X., Wang, J., and Yan, Q. (2023). Cnn2d-senet-based prospecting prediction method: A case study from the cu deposits in the zhunuo mineral concentrate area in tb. MINERALS, 13(6).
[28] Navarro, M. A., Oliva, D., Ramos-Michel, A., Zaldivar, D., Morales-Castaneda, B., Perez-Cisneros, M., Valdivia, A., and Chen, H. (2022). An improved multi-population whale optimization algorithm. INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 13(9):2447–2478.
[29] Wei, F., Li, J., and Zhang, Y. (2023). Improved neighborhood search whale optimization algorithm and its engineering application. SOFT COMPUTING, 27(23):17687–17709.
[30] Liu, L. and Zhang, R. (2022). Multistrategy improved whale optimization algorithm and its application. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2022.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 19516
Visits: 297446

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.