Abstract
Due to the heterogeneity and uncertainty of the reservoir, it is very challenging to select the best oil, gas, and water components to calculate the reservoir production, and it cannot meet the real-time requirements. By changing the production constraints of the well, a Radial Basis Neural Network Reservoir Model (RBNNRM) for a Multi-stage Fracturing Horizontal Well (MFHW) is proposed to predict the Bottom Hole Flowing Pressure (BHFP). First, a reservoir model of a multi-stage fractured horizontal well is established and laboratory self-developed production data analysis software is used to calculate the BHFP. Second, part of the obtained data are imported into the neural network model as training data. In the training process, according to the results obtained from the test data, the network parameters are constantly adjusted to obtain the most optimized network model. Third, the resulting neural network is tested using the remaining data. Finally, a field case of a multi-stage fracturing horizontal well is studied by using the presented RBNNRM neural network model. The results show that in most cases, the proposed model performs better than other models, with the highest accuracy and the lowest root mean square error. This proves that the RBNNRM can be effectively applied to the BHFP prediction of the MFHW. The experimental results also show that, compared with the traditional pressure calculation reservoir model, the use of the RBNNRM to calculate the BHFP can achieve a speedup of dozens of times, which can meet the needs of field calculations.
Highlights
Multiphase flow in oil and gas fields usually refers to the simultaneous flow of multiple fluids in an oil reservoir, which generally occurs during the production process of oil and gas fields.1,2 Due to the interaction between different fluids, the physical process of multiphase flow is very complex, which makes the process of oil and gas field exploitation increasingly complex and challenging
The marginal increase in prediction accuracy can increase the efficiency of producing petroleum resources with less time and effort. Based on all these reasons, this paper proposes a Radial Basis Neural Network Reservoir Model (BPNNRM) to predict the Bottom Hole Flowing Pressure (BHFP)
It can be seen from the table that the overall performance of the radial basis neural network (RBNN) is better than backpropagation neural network (BPNN), and the accuracy rate is even higher by 11%
Summary
Multiphase flow in oil and gas fields usually refers to the simultaneous flow of multiple fluids in an oil reservoir, which generally occurs during the production process of oil and gas fields. Due to the interaction between different fluids, the physical process of multiphase flow is very complex, which makes the process of oil and gas field exploitation increasingly complex and challenging. In order to deal with this complexity, a lot of research has been done, and mechanism models have been introduced to predict fluid and gas flow by changing pressure and temperature values. This phenomenon has led to many numerical simulation models being used to estimate the precise flow characteristics of oil, natural gas, and water in production.. The marginal increase in prediction accuracy can increase the efficiency of producing petroleum resources with less time and effort Based on all these reasons, this paper proposes a Radial Basis Neural Network Reservoir Model (BPNNRM) to predict the BHFP
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
