A steam injection distribution optimization method for SAGD oil field using LSTM and dynamic programming. (April 2021)

• Record Type: Journal Article
• Authors: Yang, Changlin; Wang, Xin
• Is Part Of: ISA transactions. Volume 110(2021)
• Page Start: 198
• Page End: 212
• Publication Date: 2021-04
• Subjects: Steam assisted gravity drainage -- Time series prediction -- Long short-term memory -- Dynamic programming -- Web-based geographical information system; Engineering instruments -- Periodicals; Engineering instruments; Periodicals; Electronic journals; 629.805
• DOI: 10.1016/j.isatra.2020.10.029
• Languages: English
• ISSNs: 0019-0578

Abstract

Abstract: Steam injection distribution optimization refers to the process of distributing steam injection in steam assisted gravity drainage (SAGD) oil field to maximize the total oil production. A novel optimization method that integrates long short-term memory (LSTM) neural network and dynamic programming is presented in this paper to solve the steam injection distribution optimization problem for the first time. In the proposed method, LSTM is used to construct the prediction model to predict oil production of the wells. With the prediction result, dynamic programming optimizes steam injection distribution in the oil field to maximize total oil production. Convergence stability and computational complexity of the dynamic programming method have been analyzed and presented in this research. A web-based geographical information system called Petroleum Explorer is also developed based on the proposed method. Experiments on two pads of a real-world SAGD project demonstrate that LSTM model gives better prediction result than other five existing models and production improvement of the proposed method is highly related to parameter setting of the optimization process Highlights: An optimization method is proposed for steam assisted gravity drainage oil field. Long Short-Term Memory models are constructed to predict future oil production. Dynamic programming is used to optimize the steam injection distribution problem. A web-based system is developed to implement the experiments of the method. Oil production of two case studies can be improved by 12.25% and 24.07% separately.