Affiliation:
1. China University of Petroleum at Beijing
2. CNPC Engineering Technology R&D Company Limited
3. King Fahd University of Petroleum and Minerals
Abstract
AbstractBased on a genetic algorithm and field production data, this paper reasonably optimizes the fracture parameters of multistage fractured horizontal wells (MFHWs). First, a mathematical model of MFHWs in shale gas reservoir is proposed under the conditions of variable production and variable pressure. Then, the main factors affecting well production are determined by sensitive analysis. Finally, the production prediction model based on a genetic algorithm (GA) is used to optimize the fracture parameters of the Fuling shale gas reservoir. The results show that in the study area, the number of fractures in typical wells is 10, and the fracture half-length is 90m, and the fracture conductivity is 15.24mD.m. The effective fracture half-length is the main parameter affecting production, so the effective fracture half-length and effective fracture number should be increased reasonably, and the support concentration should be increased properly. What's more, the optimal solution of fracture half-length is 160m, and the optimal solution of fracture number is 8, and the optimal solution of fracture conductivity is 20 mD·m. This paper provides a new idea based a genetic algorithm for optimizing fracture parameters of shale gas wells in the Fuling area.
Reference22 articles.
1. Balashov D , EgirovD, BelozerovB, . 2019. Prediction of wells productive characteristics with the use of unsupervised machine learning algorithms. Presented at the SPE Russian Petroleum Technology Conference, Moscow, Russia, October. SPE 196857-MS. https://doi.org/10.2118/196857-MS
2. Bukhamseen N Y , ErtekinT. 2017. Validating Hydraulic Fracturing Properties in Reservoir Simulation Using Artificial Neural Networks. Presented at the SPE Kingdom of Saudi Arabia Annual Technical Symposium and Exhibition, Dammam, Saudi Arabia, April. SPE 188093-MS. https://doi.org/10.2118/188093-MS
3. Production Predicting Technology of Shale Gas Fracturing Horizontal Well in Chang-ning Area Based on the GA-BP Neural Network Model;Chen;Science Technology and Engineering,2020
4. Chen P , RahmanM. 2015. A novel approach to predict interaction between hydraulic fracture and natural fracture using artificial neural networks. Presented at the SPE/IATMI Asia Pacific Oil & Gas Conference and Exhibition, Nusa Dua, Bali, Indonesia, October. SPE 176143-MS. https://doi.org/10.2118/176143-MS
5. A well-test based study for parameter estimations of artificial fracture networks in the Jimusar shale reservoir in Xinjiang;Chen;Petroleum Science Bulletin,2019