New expert system for enhanced oil recovery screening in non-fractured oil reservoirs
Introduction
Enhanced oil recovery (EOR) screening techniques have been utilized in the past few decades to identify the most appropriate EOR method for a candidate reservoir based on proposed screening criteria. These criteria originated from field experience, experimental investigations, and simulation studies, thereby significantly reducing the application risks of these techniques.
Some useful technical recommendations were proposed by Taber and Martin [1] where the screening criteria were presented in tables and graphs. Taber et al. [2] proposed screening criteria for most EOR techniques by using available data and considering EOR mechanisms. However, the application of these recommendations in computer programming is difficult due to the wide overlapping ranges in the criteria of different processes.
Over the past few years, Artificial Intelligence techniques (AI) such as Artificial Neural Networks (ANN), fuzzy inference systems, and Bayesian Belief Networks (BBNs) have been successfully applied to a wide variety of complicated engineering problems [3], [4], [5], [6], [7], [8], [9], [10], [11], [12], [13], [14]. In particular, these methods have been considered as reliable decision-making tools in petroleum engineering. Since EOR screening is a great challenge for petroleum engineers, AI techniques have been utilized as an important tool in EOR method selection [15], [16], [17], [18], [19], [20], [21]. For instance, these techniques have been utilized in EOR project risk and economic analyses as well as EOR screening [15], [16]. Guerillot [17] utilized fuzzy logic to design a screening system that is capable of representing knowledge-based descriptions for EOR methods. The proposed model yielded satisfactory outcomes, particularly in thermal processes. However, this model failed in other EOR methods due to the lack of available data. Parkinson et al. [18] proposed a computer program based on an expert system to check the possibility of a few EOR techniques in terms of economic considerations. Also, Chung and Carroll [19] employed a fuzzy expert system to analyze the EOR project risk for a specific EOR method. Tapias et al. [20] utilized a neuro-fuzzy system to study EOR screening in the Colombian Petrolea field and to determine the potential hydrocarbon producing zone. Furthermore, a BBN method was recently applied in this research group to select the appropriate EOR method using field scale data from EOR projects [21].
In this study, we incorporated the fuzzy rules derived from previous successful field experience into a fuzzy inference system to screen four well-known EOR techniques in depleted non-fractured oil reservoirs. For a specific reservoir, the fuzzy system was employed to rank the success possibility of these EOR methods based on the reservoir and rock properties. In contrast to other AI techniques where the design and development relies mainly on rich data sets, the proposed fuzzy system is not influenced by either the scarcity of data in some ranges of screening parameters, or by the accumulation of data in other ranges. Furthermore, this method is easier to use than screening tables and graphs, since it considers the economic priority of methods as well as technical issues. Also, in this method, the solutions are obtained within a few milliseconds (0.82 seconds) of CPU time using an ordinary desktop type computer.
Section snippets
Background: fuzzy logic expert systems
In recent years, AI techniques such as ANNs and expert systems have been employed in the petroleum industry [22], [23], [24], [25], [26]. As it is schematically shown in Fig. 1, expert systems are programs that employ a knowledge base and a set of production rules to infer new facts from knowledge and input data. Human experience and knowledge are the original sources of the principles employed in the knowledge bases of these rule-based systems [27].
An expert system mainly comprises three key
Methodology
Expert systems are the most suitable and efficient techniques for EOR screening compared with other methods for the following reasons:
- •
Rules defined based on experts' knowledge are not strict. For instance, if an expert says that reservoir rock with permeability greater than 200 md is suitable for polymer flooding, a reservoir with rock permeability of 198 md cannot be excluded categorically.
- •
The experts' knowledge is not completely formalized which includes rather general rules for process
Results and discussion
Overall, we collected 620 field EOR experience to verify the performance of the proposed method, which comprised four different EOR methods, i.e., , HC miscible injection, polymer flooding, and steam injection. In the output, the program provided four normalized success possibilities for the four EOR methods. Then, the proposed EOR method with the highest success possibility was verified against the specified EOR method that had been applied successfully in the field. An error index
Conclusions
Fuzzy logic provides a framework to mathematically model and analyze inherently vague, incomplete, imprecise, and therefore subjective relationships. Fuzzy expert systems are powerful tools for decision making when there is a lack of information and data. Furthermore, the predictions are not affected by an unequal distribution of data, which is a major challenge in training ANN-based techniques. In this study, we incorporated expert experience into a fuzzy system to design rules by applying
Acknowledgement
The first author would like to thank Dr. Mohammad Mehdi Zerafat for his contribution in gathering field data.
References (33)
- et al.
An experiment in linguistic synthesis with a fuzzy logic controller
Int. J. Man-Mach. Stud.
(1975) - et al.
Structure identification of fuzzy model
Fuzzy Sets Syst.
(1988) - et al.
Simulation of overall and local buckling behavior of cylindrical tubular members using fuzzy inference system
Adv. Eng. Softw.
(2012) - et al.
A hybrid hierarchical neural network-fuzzy expert system approach to chemical process fault diagnosis
J. Fuzzy Set Syst.
(1996) - et al.
Robust fuzzy logic control of mechanical systems
J. Fuzzy Set Syst.
(2003) - et al.
Robust adaptive sliding-mode control of condenser-cleaning mobile manipulator using fuzzy wavelet neural network
J. Fuzzy Set Syst.
(2014) - et al.
A fuzzy multiple linear regression based loss formula in electric distribution systems
J. Fuzzy Set Syst.
(2004) - et al.
Neuro-fuzzy adaptive control based on dynamic inversion for robotic manipulators
J. Fuzzy Set Syst.
(2003) - et al.
A new fracture prediction method by combining genetic algorithm with neural network in low-permeability reservoirs
J. Pet. Sci. Eng.
(2014) - et al.
Neural networks in mechanics of structures and materials – new results and prospects of applications
Comput. Struct.
(2001)
Safety and risk analysis of managed pressure drilling operation using Bayesian network
Saf. Sci.
Using an expert system to explore enhanced oil recovery methods
Comput. Electr. Eng.
Hydraulic fracture design and optimization of gas storage wells
J. Pet. Sci. Eng.
Intelligent systems application in candidate selection and treatment of gas storage wells
J. Pet. Sci. Eng.
An expert system for selecting and designing EOR processes
J. Pet. Sci. Eng.
An introduction to artificial intelligence applications in petroleum exploration and production
J. Pet. Sci. Eng.
Cited by (10)
Impact of newly implemented enhanced oil and gas recovery screening policy on current oil production and future energy supply in India
2021, Journal of Petroleum Science and EngineeringCitation Excerpt :The proposed method is hybridized with commercial EOR screening tool and it can effectively select best suitable EOR method for Iranian oil fields. Similarly, Eghbali et al. (2016) also proposed an EOR screening tool for choosing appropriate method for an oilfield. They used fuzzy logic system to screen suitable EOR method among polymer flooding, hydrocarbon gas injection, miscible CO2 injection and steam injection.
A hybrid FAHP-MCGP approach to sustainable assessment of candidate EOR methods for a given oil reservoir
2021, Journal of Petroleum Science and EngineeringCitation Excerpt :Al Adasani and Bai (2011) analyzed EOR projects from 1998 to 2010 and updated technical screening criteria provided by Taber et al. (1996). Recent studies have developed several approaches to select the most appropriate EOR method based on these technical screening criteria (i.e., Ahmadi and Bahadori, 2016; Eghbali et al., 2016; Esmaeilnezhad et al., 2013; Kamari et al., 2014; Khazali et al., 2019; Khojastehmehr et al., 2019; Lee et al., 2011; Mashayekhizadeh et al., 2014; Suleimanov et al., 2016). Emphasizing the inadequacy of the technical criteria in evaluation EOR methods, Taber et al. (1997) highlighted the role of economic measures in making the final decision.
A fuzzy logic approach for estimating recovery factors of miscible CO<inf>2</inf>-EOR projects in the United States
2020, Journal of Petroleum Science and EngineeringCitation Excerpt :Fuzzy logic has been used in different studies in geology and reservoir engineering spanning from prediction of reservoir properties from well logs (Lim, 2005) to prediction of minimum miscibility pressure (MMP) for gas injection processes (Ahmadi and Ebadi, 2014; Karkevandi-Talkhooncheh et al., 2017), and to prediction of elastic modulus of intact rocks (Rezaei, 2018). It has also been successfully used for selection of EOR opportunities (Alvarado et al., 2002), and for EOR screening in non-fractured reservoirs (Eghbali et al., 2016). However, it has never, to the best of the author's knowledge, been used as a prediction tool for estimation of miscible CO2-EOR recovery factors.
Group fuzzy comprehensive evaluation method under ignorance
2019, Expert Systems with ApplicationsCitation Excerpt :Recently, some researchers have noticed the problems of experts’ knowledge acquisition and representation techniques (Wagner, 2017), and the fuzzy expert system is introduced, in which uncertainty, imprecise and vague existing in experts’ knowledge and experience are considered. In the available literatures, the fuzzy expert system is developed on the basis of employing the bayesian belief network model, range overlaps and similarity method, TODIM method, triangular fuzzy number to deal with problems in variety areas (Berredjem & Benidir, 2018; Eghbali, Ayatollahi, & Boozarjomehry, 2016; Hajipour, Kazemi, & Mousavi, 2013; Salomon & Rangel, 2015). However, not only the group FCE method but also the existence of global or local ignorance in experts’ judgments have not been noticed yet in the literatures of expert system.
Application of fuzzy decision tree in EOR screening assessment
2019, Journal of Petroleum Science and Engineering