Optimal Control Method of Oil Well Production Based on Cropped Well Group Samples and Machine Learning
نویسندگان
چکیده
Most traditional injection-production optimization methods that treat the entire oil reservoir as a whole require re-optimization when facing new reservoirs, which is not only time-consuming but also does make full use of historical experience information. This study decomposes into independent basic production units to increase sample size and diversity utilizes image enhancement techniques augment number samples. Two frameworks based on convolutional neural networks (CNNs) are employed recommend optimal control strategies for inputted well groups. Framework 1 uses bottom hole pressure (BHP) variable trains CNN with BHP obtained by reinforcement learning algorithms labels. 2 saves corresponding revenue (NPV) during groups features NPV The in this framework capable directly outputting according strategies. particle swarm algorithm (PSO) used generate call predict development effects until PSO converges strategy. experimental results demonstrate CNN-based outperform PSO-based terms accuracy computational efficiency. achieves an output 87% predicting groups, while 78%. Both exhibit fast running times, each iteration taking less than s. provides more effective accurate method optimizing reservoirs decomposing using construct framework, great significance real-time wells fields.
منابع مشابه
Optimal Well Placement Improves Heavy Oil Production
Compared to vertical or lowinclination wells, horizontal wells can deliver higher production rates, higher recovery factors, and more efficient use of steam in thermally enhanced recovery projects for heavy oil. However, the shallow, thin, and friable sand reservoirs in Columbia’s Girasol field present several challenges to the accurate placement of horizontal wells. Schlumberger was contracted...
متن کاملOil Well Monitoring and Control Based on Wireless Sensor Networks
Most of the Oil Pumping Units (OPU) are manually monitored. This existing oil-pumping systems use a high power-consuming process, is incapable of OPU’s structural health monitoring. In this paper, a sensor network based intelligent control is proposed for power economy and efficient oil well health monitoring. The condition of the oil storage tanks can be monitored using sensors like level sens...
متن کاملPredicting the Oil Well Production Based on Multi Expression Programming
Predicting the oil well production is very important and also quite a complex mission for the petroleum engineering. Due to its complexity, the previous empirical methods could not perform well for different kind of wells, and intelligent methods are applied to solve this problem. In this paper the multi expression programming (MEP) method has been employed to build the prediction model for oil...
متن کاملMachine Learning in Modern Well Testing
Well testing is a crucial stage in the decision of setting up new wells on oil field. Decision makers rely on the metrics to evaluate the candidate wells’ potential. One important metric is permeability, measuring the ability of porous material to transmit fluids. High permeability often leads to high yielding. In a conventional well test, the well is controlled to produce at a constant flow ra...
متن کاملTwo-phase Simulation of Well Control Methods for Gas Kicks in Case of Water and Oil-based Muds
Kick occurrence is a possible event during a drilling process. It is required to be handled immediately using a well control method to avoid blowout, financial losses and damages to the drilling crew. Several methods including driller, wait and weight, and concurrent are applicable in the drilling industry to control a well during a kick incident. In this study, typical well control methods wer...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Energies
سال: 2023
ISSN: ['1996-1073']
DOI: https://doi.org/10.3390/en16124735