Single Well Production Prediction Model of Gas Reservoir Based on CNN-BILSTM-AM DOI Creative Commons

Daihong Gu,

Rongchen Zheng, Peng Cheng

et al.

Energies, Journal Year: 2024, Volume and Issue: 17(22), P. 5674 - 5674

Published: Nov. 13, 2024

In the prediction of single-well production in gas reservoirs, traditional empirical formula reservoirs generally shows poor accuracy. process machine learning training and prediction, problems small data volume dirty are often encountered. order to overcome above problems, a model based on CNN-BILSTM-AM is proposed. The built by long-term short-term memory neural networks, convolutional networks attention modules. input includes previous period its influencing factors. At same time, fitting error value reservoir introduced predict future data. loss function used evaluate deviation between predicted real data, Bayesian hyperparameter optimization algorithm optimize structure comprehensively improve generalization ability model. Three single wells Daniudi D28 well area were selected as database, was production. results show that compared with network (CNN) model, long (LSTM) bidirectional (BILSTM) test set three experimental reduced 6.2425%, 4.9522% 3.0750% average. It basis coupling meets high-precision requirements for which great significance guide efficient development oil fields ensure safety China’s energy strategy.

Language: Английский

An enhancement method for chloride diffusion coefficient long-term prediction based on Hilbert dynamic probabilistic interpolation and BO-LSTM DOI
Renjie Wu, Yuzhou Wang,

Khant Swe Hein

et al.

Measurement, Journal Year: 2025, Volume and Issue: unknown, P. 116820 - 116820

Published: Jan. 1, 2025

Language: Английский

Citations

1
Parameters optimization of PEMFC model based on gazelle optimization algorithm DOI
Sofiane Haddad, M. Benghanem,

Belqees Hassan

et al.

International Journal of Hydrogen Energy, Journal Year: 2024, Volume and Issue: 87, P. 214 - 226

Published: Sept. 7, 2024

Language: Английский

Citations

4
Early Warning of College Students’ Ideological and Political Course Performance Using an Optimization Algorithm DOI Creative Commons
Yuehua Chen

Journal of Advanced Computational Intelligence and Intelligent Informatics, Journal Year: 2025, Volume and Issue: 29(2), P. 389 - 395

Published: March 19, 2025

With the reform of teaching methods, hybrid online and offline modes have been used increasingly in college courses. In this setting, factors affecting academic performance are more complex, making it challenging to predict students’ performance. Therefore, there is an urgent need for higher-performance prediction algorithms. This study briefly analyzed learning ideological political Then, features students courses were extracted using Super Star platform system. Feature selection was carried out based on information gain rate, while training set balanced synthetic minority oversampling technique (SMOTE). Moreover, seagull optimization algorithm (SOA) applied optimize hyperparameters eXtreme Gradient Boosting (XGBoost) develop SOA-XGBoost early warning Experiments performed collected datasets. It found that effect improved significantly following SMOTE processing. The F1-value reached 0.955 area under curve value 0.976. SOA exhibited superior hyperparameter compared with other algorithms such as grid search. also achieved best results These confirm effectiveness proposed performance, method can be widely practice.

Language: Английский

Citations

0
Advances in membrane-assisted reactors: An integrative review for modeling and experiments DOI
Md Abdullah Al Masud, Nhan H. Khuu, Oishi Sanyal

et al.

Separation and Purification Technology, Journal Year: 2025, Volume and Issue: unknown, P. 133095 - 133095

Published: April 1, 2025

Language: Английский

Citations

0
Synergistic intensification of palladium-based membrane reactors for hydrogen production: A review DOI
Weiwei Yang, Xin-Yuan Tang, Xu Ma

et al.

Energy Conversion and Management, Journal Year: 2024, Volume and Issue: 325, P. 119424 - 119424

Published: Dec. 24, 2024

Language: Английский

Citations

1
Mapping flood risk using a workflow including deep learning and MCDM– Application to southern Iran DOI
Hamid Gholami,

Aliakbar Mohammadifar,

Shahram Golzari

et al.

Urban Climate, Journal Year: 2024, Volume and Issue: 59, P. 102272 - 102272

Published: Dec. 27, 2024

Language: Английский

Citations

1
Single Well Production Prediction Model of Gas Reservoir Based on CNN-BILSTM-AM DOI Creative Commons

Daihong Gu,

Rongchen Zheng, Peng Cheng

et al.

Energies, Journal Year: 2024, Volume and Issue: 17(22), P. 5674 - 5674

Published: Nov. 13, 2024

In the prediction of single-well production in gas reservoirs, traditional empirical formula reservoirs generally shows poor accuracy. process machine learning training and prediction, problems small data volume dirty are often encountered. order to overcome above problems, a model based on CNN-BILSTM-AM is proposed. The built by long-term short-term memory neural networks, convolutional networks attention modules. input includes previous period its influencing factors. At same time, fitting error value reservoir introduced predict future data. loss function used evaluate deviation between predicted real data, Bayesian hyperparameter optimization algorithm optimize structure comprehensively improve generalization ability model. Three single wells Daniudi D28 well area were selected as database, was production. results show that compared with network (CNN) model, long (LSTM) bidirectional (BILSTM) test set three experimental reduced 6.2425%, 4.9522% 3.0750% average. It basis coupling meets high-precision requirements for which great significance guide efficient development oil fields ensure safety China’s energy strategy.

Language: Английский

Citations

0