Estimation of fracture aperture from petrophysical logs using teaching–learningbased optimization algorithm into a fuzzy inference system
 1.1k Downloads
Abstract
Aperture, which refers to the opening size of a fracture, is a critical parameter controlling rock mass permeability. Moreover, distribution of permeability within the reservoir is commonly affected by natural fracture occurrences. In a waterbased mud environment, boreholeimaging tools are able to identify both location and aperture size of the intersected fractures, whereas in oilbased environment, due to invasion of resistive mud into the fractures, this technique is impractical. Recently, some artificial intelligence techniques facilitated reliable estimations of reservoir parameters. In this paper, a teaching–learningbased optimization algorithm (TLBO) trained an initial fuzzy inference system to estimate hydraulic aperture of detected fractures using well logs responses. Comparing the results with real measurements revealed that the model can provide reliable estimations in both conductive and resistive mud environments, wherever the aperture size is unknown. TLBO, besides of its easier application, outperformed earlier optimization algorithms, which were used to evaluate the method effectiveness.
Keywords
Aperture size Fracture permeability Fuzzy logic Image logs TLBOIntroduction
Natural fractures can affect essential reservoir characteristics tremendously. As a fluid conduit, natural open fractures can control the reservoir permeability (Boro et al. 2014). Conventional techniques of oil recovery may drain fractured reservoirs inefficiently, leading to early breakthrough in the secondary recovery (Alvarado and Manrique 2010; Speight 2016). In these cases, where production substantially takes place through fracture networks, aperture size is one of the basic parameters controlling reservoir permeability (Nelson 2001; Tiab and Donaldson 2015).
During fracture characterization, the aperture size is commonly characterized with the image logs. In conductive mud environments, imaging tools can determine fracture aperture on the order of microns (Tiab and Donaldson 2015), whereas in oilbased mud environments, due to the invasion of resistive mud into the fracture planes, the imaging tools such as OilBase Micro Imager (OBMI) display the same appearance for both the open and healed fractures (Bishop 2015). In addition, the vast majority of natural fractures have an aperture size less than the OBMI tool pixel width (Cheung et al. 2001). Statistics have shown that the most frequent range of aperture size is between 10 and 40 microns (GolfRacht 1982). Therefore, the presence of a quick and costeffective method to estimate aperture size of detected fractures can be useful, wherever the aperture size is unknown.
Nakashima and Kikuchi (2007) performed a quantitative estimation of fracture apertures, of a size higher than 0.2 mm, using NMR logging data. They showed that there is a linear relationship between fracture aperture size and bulkfluid porosity. Wu (2013) proposed a workflow to determine the relationship between aperture size and a fracture indicator value by using measurements from multiaxial electromagnetic induction well logging instruments. Ramandi et al. (2016) used Xray microcomputed tomography to measure fracture apertures in a fractured coal sample from digital images. Shalaby and Islam (2017) have shown that fractured zones can be detected by using conventional well logs.
Recently, artificial intelligence techniques were utilized successfully for prediction of different reservoir parameters (Ahmadi 2011; Wang et al. 2013; Anifowose et al. 2017). El Ouahed et al. (2005) developed a 2D fracture network map and fracture intensity map in Hassi Messaoud oil field by using fuzzy logic and artificial neural network. Ja’fari et al. (2012) suggested a model to estimate fracture intensity from conventional well logs by employing the adaptive neurofuzzy inference system. Accordingly, a fuzzy system maps input space to an output space using a set of fuzzy rules.
In this paper, a new method is introduced to estimate aperture size from well log data. The proposed method is an integration of fuzzy inference system and teaching–learningbased optimization algorithm (TLBO), in which the TLBO is utilized to train an initial fuzzy structure. TLBO is one of the most recent algorithms (Rao et al. 2011), which stands out as a powerful technique for optimization problems (Satapathy and Naik 2015; Kothavade and Deshpande 2016).
In order to evaluate the method effectiveness, various optimization algorithms available in the literature were employed to train the same fuzzy structure. Comparing the results indicated that the hybrid TLBOFuzzy Inference System (TLBOFIS) provides a higher level of accuracy. Finally, by estimating aperture size of detected fractures in both conductive and resistive mud environments, validation of the model was verified.
Methodology
Fuzzy inference system
Fuzzy set theory was first introduced by Zadeh (1965) as a method for handling data uncertainty. Unlike the Boolean logic, where variables take only a true or false value (1 or 0), fuzzy logic deals with the degree of truth and variables may have any value between 0 and 1. Capability of fuzzy sets to express gradual transitions from membership to nonmembership provides a powerful representation of measurement uncertainties (Klir and Yuan 1995).
There are three types of fuzzy inference systems: Mamdani (Mamdani and Assilian 1975), Tsukamoto (Tsukamoto1979), and Takagi–Sugeno–Kang (Sugeno 1985). Sugeno system is a more compact and computationally efficient model, in which its output membership functions are either constant or linear (Matlab Users Guide 2013). Considering x and y as the input values and z as the crisp output, a typical rule in the Sugeno model has the form of:
If x is A and y is B, then z = f(x,y)
where A and B are fuzzy sets and f(x,y) is a function in consequent. Once the fuzzy structure initialized, the membership function parameters can be trained by employing optimization algorithms.
Teaching–learningbased optimization algorithm (TLBO)
Local search of the TLBO occurs during the learner phase. This phase uses accepted function values at the end of teacher phase as its own input. In this phase, learners enhance their knowledge by interacting randomly with themselves. A learner enhances knowledge of other learners, when he or she has more knowledge than they do.
The TLBO is a populationbased evolutionary algorithm, which uses a population of solutions to proceed to the global solution (Ganesh and Reddy 2014). It is interesting to note that the TLBO does not require any algorithmspecific parameter. Common controlling parameters, such as the population size and number of iterations, are sufficient for its performance (Rao 2015). This ability of TLBO makes it an efficient tool, over the other algorithms, especially when dealing with multiobjective optimization problems (Zuperl and Cus 2016; Rai 2017).
Hybrid TLBOFuzzy Inference System (TLBOFIS)
Data preparation
Here, Electrical Micro Imaging (EMI) logs along with the conventional well logs from the same intervals were the used data for initializing fuzzy model. These data were acquired from five wells drilled into two different hydrocarbon fields. The study area lies in the Zagros Basin in the Fars Province of Iran. The first field contains three wells with recorded well logs ranging in depths between 3050 and 3500 m. In the second field, which includes the other two wells, studied depths range between 2500 and 2850 m. Lithology of the logged intervals consists of anhydrite, bedded dolomite, limestone, and shale, assigned to the PermoTriassic Dehram Group.
EMI is a waterbased formationimaging tool, which performs a qualitative microresistivity reading around the borehole. Six imaging pads of the EMI, in contrast to fourarm tools, provide more accurate hole volumes and diameter computations (Changxiong 2004).
By processing available image logs, a total number of 132 conductive fractures were detected and their hydraulic aperture sizes were calculated. In the first studied hydrocarbon field, fractures show a NEESWW dominant strike, southeast azimuth, and dip inclination ranging between 75° and 85°. Fracture orientations in the second hydrocarbon field are disordered. Nevertheless, NE–SW strike, mean azimuth of 110° and mean dip of 78°, is dominant.
In the literature, various empirical models were proposed in order to relate the mechanical and hydraulic apertures (Renshaw 1995; Zimmerman and Bodvarsson 1996; Li and Jiang 2013). The CIFLogGeoMatrix computes the average hydraulic aperture as the cubic mean value of fracture trace aperture.

LLD measures formation deep resistivity and, among other well logs, has the highest correlation with aperture size. Generally, wider apertures show lower resistivities (Fig. 5).

NPHI tracks hydrogen concentration in the formation and shows a linear relationship with measured aperture sizes, as illustrated in Fig. 5.

DT displays travel time of elastic wave through the formation rock. Generally, void spaces reduce the speed of the sound (Serra 2008). Bigger apertures accompany with slower velocity records.

RHOB is a record of formation bulk density and is related to the rock porosity. As seen in Fig. 5, lower densities imply bigger aperture sizes.
Final data sets, consisting of measured hydraulic aperture and well log responses, were merged and divided into two groups: a group including 98 sets for training the model and another group with 34 sets for testing.
Initializing fuzzy inference system
In order to generate the initial fuzzy inference system and define membership functions, a fuzzy clustering technique may be used. Subtractive clustering and Fuzzy CMeans are two basic methods of fuzzy clustering. Here, a subtractive clustering method was employed to determine the fuzzy rules. In a set of data, subtractive clustering defines the number of clusters and cluster centers and returns a fuzzy structure that contains fuzzy if–then rules. This method eliminates the need of specifying grid resolution, in which the agreement between the accuracy and computational complexity must be regarded (Bataineh et al. 2011).
In subtractive clustering, cluster radius determines the range of influence of a cluster. The optimum clustering radius can be determined by trial and error. As discussed, the teaching–learningbased optimization algorithm is needless of any algorithmspecific parameter. However, common controlling parameters such as the population size and number of iterations can be modified in order to enhance the model accuracy. TLBO considers the number of learners as the population size (Rao 2015).
Optimizing the fuzzy system using TLBO
Results and discussion
Correlation coefficients (R), RMSE, and number of fuzzy rules achieved by each clustering radius
Clustering radius  Fuzzy rules  RMSE  R 

0.1  92  0.0056  0.7999 
0.2  65  0.0052  0.8041 
0.3  39  0.0049  0.8357 
0.4  11  0.0050  0.8200 
0.5  7  0.0044  0.8668 
0.6  6  0.0044  0.8735 
0.7  4  0.0050  0.8546 
0.8  2  0.0045  0.8665 
0.9  2  0.0048  0.8581 
1  2  0.0055  0.7816 
Algorithmspecific parameters and the highest accuracy achieved by each method, in test data
Used method  RMSE  R  Algorithmspecific parameters 

ABCFIS  0.0055  0.7902  Number of onlooker bees = 800 
Trial limit (L) = 600  
Acceleration coefficient upper bound (a) = 1  
ACOFIS  0.0059  0.0804  Sample size = 400 
Intensification factor (q) = 0 .5  
Deviation–distance ratio (zeta) = 1  
ANFIS  0.0061  0.7556  Optimization method = hybrid 
GAFIS  0.0048  0.8414  Crossover percentage (pc) = 0.5 
Number of parents (nc) = 400  
Mutation percentage (pm) = 0.6  
Number of mutants (nm) = 480  
Mutation rate (mu) = 0.25  
Selection pressure (beta) = 6  
Gamma = 0.8  
TLBOFIS  0.0044  0.8735  Needless 
In the next step, a new wellbore from a different hydrocarbon field (the third field) was selected to evaluate the model performance in an oilbased environment. The field was located in Fars Province in southern territories of Iran. Mud system used for drilling was oil based, with an oil–water ratio of 70/30. The studied well contained both the OBMI and UBI image logs and a full set of conventional well logs. The RCAL and SCAL core test data, also, were available for recovered cores from a 50m interval. The cored interval lies in the Upper Dalan Formation (of Upper Permian age) with a lithology consisting of carbonate and anhydrite.
Conclusion
Aperture size is a key parameter to indicate the influence of natural fractures on reservoir performance, and borehole imaging is the basic method for its measurement. In oilbased mud environment, however, image logs are unable to specify this parameter. In this paper, a novel method was introduced to estimate hydraulic aperture of detected fractures using conventional well logs. Required well logs are usually available in most of the drilled wells. The proposed method utilized the TLBO algorithm, in order to optimize an initial Sugeno fuzzy inference system. The TLBO does not need of any algorithmspecific parameter, and this feature makes it a useful tool for optimization problems. Examination of the developed model, in both conductive and resistive mud environments, confirmed that the estimated values are in a good agreement with real measurements. The proposed hybrid method, as an easygoing tool, may also be employed to estimate other reservoir parameters.
Notes
Acknowledgements
The authors would like to appreciate Dr. Ali KadkhodaieIlkhchi and Christian Klimczak for helping during the research.
References
 Ahmadi MA (2011) Prediction of asphaltene precipitation using artificial neural network optimized by imperialist competitive algorithm. J Petrol Explor Prod Technol 1(2):99–106CrossRefGoogle Scholar
 Alvarado M, Manrique E (2010) Enhanced oil recovery: an update review. Energies 3:1529–1575CrossRefGoogle Scholar
 Anifowose FA, Labadin J, Abdulraheem A (2017) Hybrid intelligent systems in petroleum reservoir characterization and modeling: the journey so far and the challenges ahead. J Petrol Explor Prod Technol 7(1):251–263. doi: 10.1007/s1320201602573 CrossRefGoogle Scholar
 Bataineh KM, Najia M, Saqera M (2011) A comparison study between various fuzzy clustering algorithms. Jordan J Mech Ind Eng 5(4):335–343Google Scholar
 Bishop K (2015) Mechanical stratigraphy of the Vaca Muerta Formation, Neuquen Basin, Argentina. M.Sc. Thesis, Colorado School of Mines, USAGoogle Scholar
 Boro H, Rosero E, Bertotti G (2014) Fracturenetwork analysis of the Latemar Platform (northern Italy): integrating outcrop studies to constrain the hydraulic properties of fractures in reservoir models. Pet Geosci 20:79–92CrossRefGoogle Scholar
 Changxiong W (2004) EMI log evaluation report (Internal report). Geoscience Center, Ahwaz, IranGoogle Scholar
 Cheung P, Hayman A, Laronga R, Cook G, Flournoy G, Goetz Marshal M, Hansen S, Lamb M, Li B, Larsen M, Orgren M, Redden J (2001) A clear picture in oilbase muds. Oilfield Rev 13(4):2–27Google Scholar
 Dardashti AF, Ajalloeian R (2015) Evaluation of hydraulic aperture of the joints of Behesht Abad Dam foundation, Iran. Open J Geol 5:375–382CrossRefGoogle Scholar
 El Ouahed AK, Tiab D, Mazouzi A (2005) Application of artificial intelligence to characterize naturally fractured zones in Hassi Messaoud Oil Field, Algeria. J Petrol Sci Eng 49(3):122–141CrossRefGoogle Scholar
 Faivre O (1993) Fracture evaluation from quantitative azimuthal resistivity. In: Society of Petroleum Engineering, 68th annual technical conference and exhibition, Houston, Texas, pp 179–192Google Scholar
 Fossen H (2010) Structural geology. Cambridge University Press, CambridgeCrossRefGoogle Scholar
 Ganesh BS, Reddy AS (2014) Teaching learning based optimization for economic dispatch problem with valve point loading effect. Int J Educ Appl Res 4(1):9–15Google Scholar
 GolfRacht TD (1982) Fundamentals of Fractured Reservoir Engineering. Development in Petroleum Science, no 12, Elsevier Scientific Pub Co, AmsterdamGoogle Scholar
 Ishibashi T, Watanabe N, Hirano N, Okamoto A, Tsuchiya N (2012) Experimental and numerical evaluation of channeling flow in fractured type of geothermal reservoir. In: Proceedings of 37th workshop on geothermal reservoir engineering, Stanford University, Stanford, California, pp 759–766Google Scholar
 Ja’fari A, KadkhodaieIlkhchi A, Sharghi Y, Ghanavati K (2012) Fracture density estimation from petrophysical log data using the adaptive neurofuzzy inference system. J Geophys Eng 9:105–114. doi: 10.1088/17422132/9/1/013 CrossRefGoogle Scholar
 Jang JSR (1993) ANFIS: adaptivenetworkbased fuzzy inference system. IEEE Trans Syst Man Cybern 23(3):665–685CrossRefGoogle Scholar
 Klimczak C, Schultz RA, Parashar R, Reeves DM (2010) Cubic law with aperturelength correlation: implications for network scale fluid flow. Hydrogeol J 18:851–862CrossRefGoogle Scholar
 Klir GJ, Yuan B (1995) Fuzzy sets and fuzzy logic: theory and applications. Prentice Hall, Englewood CliffsGoogle Scholar
 Kothavade SV, Deshpande SP (2016) Teaching learning based optimization algorithm to solve assembly line balancing problem. Int J Curr Eng Technol 6(5):1558–1561Google Scholar
 Li B, Jiang Y (2013) Quantitative estimation of fluid flow mechanism in rock fracture taking into account the influences of JRC and Reynolds number. J MMIJ 129:479–484 (in Japanese) CrossRefGoogle Scholar
 Luthi SM, Souhaité P (1990) Fracture apertures from electrical borehole scans. J Geophys 55(7):821–833CrossRefGoogle Scholar
 Mamdani EH, Assilian S (1975) An experimental in linguistic synthesis with a fuzzy logic control. Int J Man Mach Stud 7:1–13CrossRefGoogle Scholar
 Matlab User’s Guide (2013) Fuzzy logic toolbox. Matlab CDROM. The Mathworks, IncGoogle Scholar
 Nakashima Y, Kikuchi T (2007) Estimation of the apertures of watersaturated fractures by nuclear magnetic resonance well logging. Geophys Prospect 55(2):235–254CrossRefGoogle Scholar
 Nelson RA (2001) Geologic analysis of naturally fractured reservoirs, 2nd edn. ButterworthHeinemann, Gulf Professional Publishing, Oxford, p 332Google Scholar
 Rai DP (2017) Comments on “A note on multiobjective improved teachinglearning based optimization algorithm (MOITLBO)”. Int J Ind Eng Comput 8(2):179–190. doi: 10.5267/j.ijiec.2016.11.002 Google Scholar
 Ramandi HL, Armstrong RT, Mostaghimi P (2016) MicroCT image calibration to improve fracture aperture measurement. Case Stud Nondestruct Test Eval. doi: 10.1016/j.csndt.2016.03.001 (in press) Google Scholar
 Rao RV (2015) Review of applications of TLBO algorithm and a tutorial for beginners to solve the unconstrained and constrained optimization problems. Decis Sci Lett 5:1–30Google Scholar
 Rao RV, Savsani VJ, Vakharia DP (2011) Teaching–learningbased optimization: a novel method for constrained mechanical design optimization problems. ComputAided Des 43(3):303–315CrossRefGoogle Scholar
 Renshaw CE (1995) On the relationship between mechanical and hydraulic apertures in roughwalled fractures. J Geophys Res 100:24629–24636CrossRefGoogle Scholar
 Sarkar S, Toksoz MN, Burns D (2004) Fluid flow modeling in fractures. Massachusetts Institute of Technology, Earth, Atmospheric and Planetary Sciences, CambridgeGoogle Scholar
 Satapathy SC, Naik A (2015) A modified teachinglearningbased optimization (mTLBO) for global search. Recent Pat Comput Sci 6(1):60–72CrossRefGoogle Scholar
 Serra O (2008) Well logging handbook. Editions Technip, ParisGoogle Scholar
 Shalaby MR, Islam MA (2017) Fracture detection using conventional well logging in carbonate Matulla Formation, Geisum oil field, Southern Gulf of Suez, Egypt. J Petrol Explor Prod Technol. doi: 10.1007/s1320201703431 Google Scholar
 Speight JG (2016) Introduction to enhanced recovery methods for heavy oil and tar sands, 2nd edn. Gulf Professional Publishing, Elsevier, OxfordGoogle Scholar
 Sugeno M (1985) Industrial applications of fuzzy control. Elsevier Science Publisher, North HollandGoogle Scholar
 Tiab D, Donaldson EC (2015) Petrophysics: theory and practice of measuring reservoir rock and fluid transport properties, 4th edn. Gulf Professional Publishing, Elsevier, OxfordGoogle Scholar
 Tsukamoto Y (1979) An approach to fuzzy reasoning method. In: Gupta MM, Ragade RK, Yager RR (eds) Advances in fuzzy sets theory and applications. NorthHolland, Amsterdam, pp 137–149Google Scholar
 Wang B, Wang X, Chen Z (2013) A hybrid framework for reservoir characterization using fuzzy ranking and an artificial neural network. Comput Geosci 57:1–10CrossRefGoogle Scholar
 Watanabe N, Hirano N, Tsuchiya N (2008) Determination of aperture structure and fluid flow in a rock fracture by highresolution numerical modeling on the basis of a flowthrough experiment under confining pressure. Water Resour Res. doi: 10.1029/2006WR005411 Google Scholar
 Witherspoon PA, Wang JSY, Iwai K, Gale JE (1980) Validity of cubic law for fluid flow in a deformable rock fracture. Water Resour Res 16:1016–1024CrossRefGoogle Scholar
 Wu PT (2013) Fracture aperture estimation using multiaxial induction tool. Filed by Schlumberger Technology Corporation, Sugar Land, TX (US), as Appl. No. 13/784,153Google Scholar
 Zadeh LA (1965) Fuzzy sets. Inf Control 8:338–353CrossRefGoogle Scholar
 Zimmerman RW, Bodvarsson GS (1996) Hydraulic conductivity of rock fractures. Transp Porous Media 23:1–30CrossRefGoogle Scholar
 Zuperl U, Cus F (2016) End milling optimization using teachinglearningbased optimization algorithm with cutting force model. Proc Manuf Syst 11(2):57–62Google Scholar
Copyright information
Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.