Predicting dynamic formation pressure using artificial intelligence methods

Abstract

Determining formation pressure in the well extraction zones is a key task in monitoring the development of hydrocarbon fields. Direct measurements of formation pressure require prolonged well shutdowns, resulting in underproduction and the possibility of technical problems with the subsequent start-up of wells. The impossibility of simultaneous shutdown of all wells of the pool makes it difficult to assess the real energy state of the deposit. This article presents research aimed at developing an indirect method for determining the formation pressure without shutting down the wells for investigation, which enables to determine its value at any time. As a mathematical basis, two artificial intelligence methods are used – multidimensional regression analysis and a neural network. The technique based on the construction of multiple regression equations shows sufficient performance, but high sensitivity to the input data. This technique enables to study the process of formation pressure establishment during different periods of deposit development. Its application is expedient in case of regular actual determinations of indicators used as input data. The technique based on the artificial neural network enables to reliably determine formation pressure even with a minimal set of input data and is implemented as a specially designed software product. The relevant task of continuing the research is to evaluate promising prognostic features of artificial intelligence methods for assessing the energy state of deposits in hydrocarbon extraction zones.

Application of GMDH model to predict pore pressure

“…teaching-learning-based optimization algorithms (TLBO) (Choubineh et al, 2017;Ponomareva et al, 2022); firefly algorithm (FF) (Ghorbani et al, 2017c;Rao and Krishna, 2019;Zakharov et al, 2022); multilayer perceptron's (MLP), ANN and genetic optimization Cross plot for PP prediction by GS-GMDH based on two wells F 1 and F 2 data points (1511 data points).…”

Gas–Liquid Flow Pattern and Hydrate Risk in Wellbore during the Deep-Water Gas-Well Cleanup Process

“…In 1985, Holder and John (1985) used the three-layer sphere model to describe the interaction between guest molecules and water molecules, taking into account the influence of spherical asymmetry effect of actual gas molecules, the deviation between Langmuir constant and ideal value, and so forth, and proposed an improved equation of state for hydrate phase equilibrium. Different from the VdW-P model, in 1996, Chen and Guo et al (1966, 1998) based on the kinetic mechanism of hydrate formation and considering the non-stoichiometry of hydrate formation, , deduced the fugacity formula of guest molecules using statistical thermodynamics, and established a new prediction model for hydrate phase equilibrium conditions, which has improved the prediction accuracy compared with the VdW-P model. , In 2000, Javanmardi and Moshfeghian (2000) proposed a hydrate phase equilibrium prediction method without flash calculation based on the Parrish Prausnitz model . This model has a wide range of applications and can accurately predict the formation conditions of gas hydrate in one or more electrolyte solutions.…”

“…Different from the VdW-P model, in 1996, Chen and Guo et al (1966, 1998) based on the kinetic mechanism of hydrate formation and considering the non-stoichiometry of hydrate formation, 15 , 16 deduced the fugacity formula of guest molecules using statistical thermodynamics, and established a new prediction model for hydrate phase equilibrium conditions, which has improved the prediction accuracy compared with the VdW-P model. 17 , 18 In 2000, Javanmardi and Moshfeghian (2000) proposed a hydrate phase equilibrium prediction method without flash calculation based on the Parrish Prausnitz model. 19 This model has a wide range of applications and can accurately predict the formation conditions of gas hydrate in one or more electrolyte solutions.…”

Reproduction of reservoir pressure by machine learning methods and study of its influence on the cracks formation process in hydraulic fracturing

“…When developing models for determining reservoir pressure using artificial intelligence methods (random forest and neural network), such parameters as fluid flow rates, as well as the operating factors of each well, were used as input data. In calculating reservoir pressures, a method was used that showed the best match between the calculated and actual values of the desired value [43].…”