Beruflich Dokumente
Kultur Dokumente
Review
During the last two decades, Fuzzy Logic (FL) Systems have been increasingly applied to the research
area of petroleum engineering. Hydraulic Fracturing (HF) as an important discipline in this area and
stimulation of oil and gas wells is an important tool for natural gas and oil exploitation, whose success
relies on proper selection of target well and target formation. To date, however, no paper has attempted
to summarize and present a critique of the existing FL literature. This paper, therefore, aims to review
the FL literature that has been conducted in candidate-well selection for HF. Selecting a target
formation(s) among a vast numbers of zones/sub-layers within huge numbers of hydrocarbon-
producing wells in a reservoir is considered a difficult task, particularly if the selection goes through a
group of parameters having different domains, attributes and features. In fact, this process had been
recognized to be complex, nonlinear and adherent with uncertainty. It is proved that methods such as
FL could reduce the uncertainty thus permit superior selection of candidates well for HF treatment. The
comprehensive review provided in this paper offers new directions for FL and its application in HF
candidate-well selection.
INTRODUCTION
During the past decade, FL has shown itself to be an and Holditch, 1995; Yang, 2009; Yin and Wu, 2009). FL
appropriate alternative for engineering judgment to deal techniques, as dened in this paper, refer to fuzzy
with the uncertainties encountered in decision-making concepts, which include fuzzy set and fuzzy logic.
processes. FL has been successfully applied in many To date, nevertheless, no paper has attempted to
different areas of petroleum engineering and earth summarize and present a critique of the existing FL
sciences including petrophysics (Finol et al., 2001), literature. The aim of this paper is to provide an overview
reservoir characterization (Quenes, 2000), drilling of the application of FL techniques in HF candidate-well
(Garrouch and Lababidi, 2001), permeability and rock selection. In fact, FL established itself as a reliable
type estimation (Kadkhodaie et al., 2006), rock methodology for dealing with any sort of uncertainty,
engineering systems (Khademi et al., 2010), petroleum especially in HF candidate-well selection, design and
separation (Liao et al., 2008), stimulation (Xiong and execution. In this section, candidate-well selection, HF
Holditch, 1999) and HF candidate-well selection (Xiong and the needs for them will be explained briefly so as to
make it understandable to colleagues from a broad range
of scientific disciplines. Also, it will be discussed why FL
is of particular importance for helping extend the
*Corresponding author. E-mail: Mansoor353@yahoo.com. productive life of the reservoirs and related assets in oil
4050 Int. J. Phys. Sci.
Economides and Martin (2007); Mohaghegh et al. (2000); Fuzzy Logic, Artificial Neural Network, Genetic Algorithm,
Oberwinkler and Economides (2003); Reeves et al. (2000); Grieser Self-Questioning Matrices, Pattern Recognition, and Self-
et al. (2004) Organizing Maps
Xiong and Holditch (1995); Yin and Wu (2009); Yang (2009) Fuzzy Logic
1. ANN and FL are the two dominant AI methods that had in answering the question "is there a need for FL?",
been applied successfully in this filed. believes that, today, close to four decades after its
2. The nature of candidate-well selection is non-linear conception, fuzzy logic is a precise logic of imprecision
because it consists of several input parameters, which and approximate reasoning, which shows itself to be
are qualitatively and quantitatively different with each more effective than an attempt at the
other. formalization/mechanization of human reasoning
3. FL enables a convenient framework to combine and capabilities. Fuzzy sets theory, as a soft computing
analyze these data even independently of their source or technique, has established itself as a new methodology
characteristics. for dealing with any sort of ambiguity and uncertainty.
4. The major disadvantage of ANN method is that it Soft computing, as introduced by Zadeh (1992), includes
needs large input/output observation for training or approaches to human reasoning, which try to make use
learning procedures and does not account for of the human tolerance for incompleteness, uncertainty,
uncertainty. Two former key issues had been the impetus imprecision, vagueness, and fuzziness in decision-
behind deep investigation on three main works that making problems (Jang et al., 1997).
utilized FL-based method in HF candidate-well selection. FL can be used in order to reduce the uncertainty in the
In this way, this paper will look at a cutting-edge data collected and can model vagueness in data and/or
procedure to fill the research gap between recent relationship in a formal way. This technique is able to
developments in FL to decrease the uncertainty existed manipulate fuzzy qualitative data in terms of linguistic
in HF candidate-well selection. variables. In FL, unlike standard conditional logic, the
truth of any statement is a matter of degree. For example,
for the rule if (skin is high) then (candidate is very good),
FUZZY LOGIC both variables, high and very good, map to range of
values. Fuzzy systems rely on membership functions to
FL is an extension of conventional Boolean logic explain to the model how to calculate the correct value
developed to handle the concept of partial truth truth between zero and one. The degree to which any fuzzy
values between completely true and completely false. statement is true is denoted by a value between zero and
It was introduced by Dr. Lotfi Zadeh of UC/Berkeley in the one. In fuzzy inference system, there are 5 steps such as
1960s as a means to model uncertainty (Zadeh, 1965). fuzzy inputs, combination of inputs with AND (OR)
Zadeh says that rather than regarding fuzzy theory as a method, implication, aggregation of all outputs and
single theory, we should regard the process of defuzzification (Tinkir, 2011). A typical fuzzy system
fuzzification as a methodology to generalize any specific consists of a rule base, membership functions and an
theory from a crisp (discrete) to a continuous (Fuzzy) inference procedure, as presented in Figure 2. The
form. According to Zadeh (2006), uncertainty is an membership function A(x) describes the membership of
unavoidable attribute of information. By using the rules of the elements x of the base set X in the fuzzy set A,
probability, scientists were capable of dealing with such whereby for A(x) a large class of functions can be taken.
uncertainties in information. With fuzzy set theory coming Reasonable functions are often piecewise linear
into existence, it is performed better by FL. Zadeh (2008), functions, such as triangular or trapezoidal functions.
Zoveidavianpoor et al. 4053
Table 2 shows the standard operation in FL problems of applications. The shaded region in trapezoidal functions usually considered as linear
system. Whilst the operations according to Figure 3 shows the membership function of the functions. As shown in Figure 3, the two fuzzy
Intersection and Union are based on min/max fuzzy set AB, which results from the intersection sets have presented as triangular membership
operations, the complement is an algebraic of fuzzy sets A and B. Here A and B are the functions. Normally, a membership function
(arithmetical) one. Union and intersection can also membership functions for the fuzzy sets A and B, selected by trial and error to be representing the
be defined in an algebraic manner but giving respectively. For example, A could be a base set. There are five basic membership
different results as indicated in Table 2. membership function for the fuzzy set of skin functions. These functions along with their
Selection of operators solely depends on the value or water saturation. Triangular or descriptions are represented in Table 3.
4054 Int. J. Phys. Sci.
Figure 3. Membership function for fuzzy set AB realized by function min (A,
B).
0, xa
( x a)
1
, x ( a, b) 0.8
(b a )
Membership Grades
Triangular Function ( x, a, b, c) 0.6
(c x ) , x (b, c)
(c b ) 0.4
0, xc 0.2
0
0 20 40 60 80 100
0, xa
( x a ) /(b a), x (a, b)
A
Trapezoidal function
1, x (b, c)
(d x) / d c), x (c, d )
Table 3. Contd.
There are two types of Fuzzy Sets and Systems reason that an Interval T2 FS is sometimes called a first-
(FSSs); Type-1 (T1) and Type-2 (T2). In T1 FSS, the order uncertainty fuzzy set model, whereas a general T2
membership grade is a number in the range [0, 1]. T2 FS is sometimes referred to as a second-order
FSS is an answer to the question of what to do when uncertainty fuzzy set model.
there is uncertainty about the value of the membership
function itself. In T2 FS, the membership grade is itself a
fuzzy set in [0, 1]. As a result, a T2 FSS is governed by IMPLICATIONS FOR THE FUTURE RESEARCH
fuzzy membership functions that are three-dimensional DIRECTIONS
and include a mark of uncertainty. T2 itself has two
categories named (1) General T2 FSS, and (2) Interval Gas Research Institute (GRI) believes that candidate-well
T2 FSS. Because of using sophisticated mathematical selection phase is where the greatest industry benefit
concepts, the application of the first category is not resides (Ely et al., 2000). Selecting a target formation(s)
popular and hence little publications are available. On the among a vast numbers of zones/sub-layers within huge
other hand, utilization of the later is widespread among numbers of hydrocarbon producing wells in a reservoir, is
literature. For an Interval T2 FS that third-dimension considered a difficult task, particularly if the selection
value is the same (for example, 1) everywhere, which goes through a group of parameters having different
means that no new information is contained in the third domains, attributes and features. The trend of candidate-
dimension of an Interval T2 FS. Therefore, for such a set, well selection process for HF treatment had recognized to
the third dimension is ignored, and only the Footprint of be complex, nonlinear, un-equilibrium, and adherent with
Uncertainty (FOU) is used to describe it. It is for this ambiguity and uncertainty. Therefore, utilization of
4056 Int. J. Phys. Sci.
modern and right problem-solving tool such as T2 FSS to was correlated to weighting factor, which is different in all
handle such uncertainties should be considered a great proposed methods. As can be seen from Table 6, there
concern to the petroleum industry. Indeed, new are noticeable differences between their allocated
requirements force the previous methods to advance and weighing factors, which could finally affect the candidate-
novel techniques expected to meet the requirements and well selection process result. Secondly, this
remove the existing weakness. In highlighting this need, heterogeneity in the relative importance of the fuzzy
the question has been answered about why T2 FSS variable, which makes the weighting factor, is not the only
should be used. By reviewing its application in the noticeable problem; the number of the variables is
industry, the second question raised; what are the different in each work; 9, 12 and 7 for Xiong, Yang, and
industry motivations to use this method? Despite of the Yin and Wu, respectively. This may be justifying, because
application in several areas of science and engineering, the structure of the fuzzy, ifthen rules, is determined
yet, they application in petroleum industry have not been priori subjectively from other sources such as experts
fully developed and a few papers available (Olatunji et knowledge. However, these rules varied among the
al., 2011a, b). A review of industrial applications of T2 experts and even for the same expert at different times.
FSS in solving complicated problems (Dereli et al., 2011) Third, by applying inaccurate rules and incorrect
indicates that there have been different reasons for functions, the achievement will be possible imprecise
authors to use type-2 FSS applications. Those reasons conclusions. For example, ignoring the effects of fluidity
are illustrated in Table 4. in the system (Yin and Wu, 2009), low weight and priority
for skin factor (Yang, 2009), and participation a variable
such as wellbore condition in the system, which could be
DISCUSSION affect the system results in a mature filed by decreasing
the number of selected parameters (Xiong and Holditch,
The nature of candidate-well selection is non-linear 1995). Table 5 shows the fuzzy system application in the
because it consists of several input parameters, which mentioned studies. The major steps toward establishing the
are qualitatively and quantitatively different. This is the fuzzy system in each of the study are presented. Finally, as
privilege of fuzzy set theory that enables a convenient it is obvious in Table 5, the basic steps of the proposed
framework to combine and analyze these data even works are all similar and in contrast with the current
independently of their source or characteristics. Two of development in fuzzy logic system (Jang et al., 1997), a
the major concepts associated with FL, Fuzzy significant new trend should be used to managing
membership functions and linguistic variables, can be uncertainty in which the current FL systems (T1 FSS) in
especially adapted to suit applications to solve the literature of HF candidate-well selection could not handle.
complex nature of HF candidate-well selection. In fact, Consider a fuzzy set (very low, low, medium, high, and
the former enable one to perform quantitative calculations very high) for a fuzzy variable such as porosity. As can
in fuzzy decision making, while the concept of linguistic be seen from Table 6, different boundaries were
variables serves the purpose of providing a means of associated with it. It is worthy to note that these
approximate characterization of phenomena that are too differences are logical, because the nature and
complex to be amendable to description in conventional characteristics of reservoir are dissimilar from region to
quantitative terms. region. Therefore, its clear that there are uncertainties
In addition to the four major key points of utilization of and we need a model to capture them.
AI methods that highlighted the advantages of FL-based T1 FL System was previously developed and
approaches in Previous Research Section, we chose implemented to overcome the difficulties that were
particularly three main cutting-edge works because they presented in conventional methods in HF candidate-well
utilized FL method in HF candidate-well selection, that is, selection (Xiong and Holditch, 1995; Yang, 2009; Yin and
Xiong and Holditch (1995), Yang (2009) and Yin and Wu Wu, 2009). However, T1 FSS is not capable of fully
(2009). Table 5 lists the applied steps in their FL system. capturing the linguistic uncertainties in the terms used
There are some problems associated with the current and inconsistency of the expert's decision-making.
fuzzy systems applied in the field of HF candidate-well Actually, uncertainty involved in any problem-solving
selection. The first problem is the structure identification situation is a result of some information deficiency. There
of the relation R that links the inputs to the output. In exist many different causes of uncertainty such as (a)
fuzzy system modeling, the structure represented by lack of information, (b) abundance of information, (c)
means of fuzzy is, if-then rules. None of mentioned conflicting evidence, (d) ambiguity, (e) measurement and
literatures had shown or even discussed the rule base (f) belief (Zimmermann, 2000). In general, these various
section of their created FL system. This important step information deficiencies may result in different types of
Zoveidavianpoor et al. 4057
Authors Xiong and Holditch (1995) Yang (2009) Yin and Wu (2009)
Fuzzy Variables (9) Influential Factors (12) Factor Volumes (7)
Permeability/Viscosity Ratio [0.25] Formation pressure [0.13] Skin factor [0.3]
Skin factor [0.2] Permeability [0.13] Permeability [0.15]
Net pay thickness [0.1] Recovery percent of reserves [0.13] Fluidity [0.15]
Water saturation [0.1] Water saturation [0.13] Water cut [0.1]
Formation pressure gradient [0.1] Reservoir thickness [0.12] Reservoir pressure [0.1]
Fuzzy
Wellbore condition [0.1] Skin factor [0.1] Fractured width [0.1]
Variables
Drainage area [0.05] Effective porosity [0.07] Fracturing effects [0.1]
Formation depth [0.05] Production rate of the well [0.05]
Porosity [0.05] Recovery percent of reserves [0.05]
Flow coefficient [0.03]
Vertical heterogeneous coefficient [0.03]
Producing pressure drop [0.02]
Constants m & n Upper limit (dup) & Lower limit (ddown) Index Parameters a & b
d up d down d iju d ijd
m a aij
Constants 2 2
d up d down (d iju d ijd ) 2
n b bij
2 ln 2 4 ln 2
F11 F12 F13 F14 r11, r12, ..., r1N r11 r12 ... r1m
r , r ,..., r
r r ... r2 m
R ... ... ... ... R1 21 22 2N
Matrix name
R uij ( d i ) 21 22
F F F F r31, r32 ,..., r3 N ... ... ... ...
91 92 93 94 rn1 rn 2 ... rnm
r41, r42 ,..., r4 N
i 1 K 1
4058 Int. J. Phys. Sci.
Fuzzy Variables Xiong and Holditch, 1995 Yang, 2009 Yin and Wu, 2009
Permeability (mD) >1 0-0.3 0 - 30
Skin < 5.5 5-25 4-5
Water Saturation (%) > 37.5 0 - 40 75 - 80
Porosity (%) 6 - 26 0 -10 N/A
Net Pay Thickness (ft) > 100 33-164 10 -16
Drainage Area (acre) > 110 N/A N/A
Formation pressure (psi) 2000-3000 1450 - 1741 1450 - 2030
Formation Depth (ft) < 10000 N/A N/A
uncertainty (Klir and Wierman, 1999). IT2 FS can handle be a critical issue for selecting HF candidate selection. In
such uncertainties in a better way because they provide this paper, the independent nature of domains involved in
more parameters and more degrees of freedom HF candidate-well selection procedure highlighted the
(Hameed, 2009). IT2 FL system offer better capabilities underlying problem of making predictions based on
to handle linguistic uncertainties by modeling the existed approaches for which a large degree of
uncertainties using T2 Membership Functions and uncertainty exists. However, it is impossible to develop a
provide diagnosticians with decision-making flexibilities. precise mathematical model that can predict the right
The development of a new methodology for HF candidate. For such systems where only ambiguous and
candidate-well selection via utilization of T2 FL system imprecise information may be available, FL provides a
forms a proposed new research trend in this paper, which way to understand system behavior by allowing us to
will provide the capability to handle linguistic uncertainties interpolate approximately between observed input and
better than previous studies. Finally, because there is output situations.
uncertainty regarding the value of the membership The weaknesses of the other AI methods (large
function, and variables associated with each set in HF input/output observation and no uncertainty capturing) in
candidate-well selection, more sophisticated types of contrast with the advantage of FL that enables a
fuzzy sets, T2 FSS is recommended at the end of this convenient framework to combine and analyze these
paper. data even independently of their source or
characteristics, had been the impetus behind deep
investigation on the main works that utilized FL-based
CONCLUSIONS method in HF candidate-well selection. In this way, this
paper will look at a cutting-edge procedure to fill the
The process of selection wells and layers for HF is the research gap between recent developments in FL to
process through which a service oil company or an decrease the uncertainty existed in HF candidate-well
operator determines the best fit from a dozen of well and selection. Certainly, a reliable methodology is needed to
formation candidates whose impact on the operation handle uncertainty. After conducting a comprehensive
performance can be very strong. As a consequence, the literature review on the applications of AI and specially FL
role of selecting target wells and target layer within this technique in HF candidate-well selection research, a
industry is critical. Typically a company will utilize research area has been identied for further study. It is
different types of data and information in different recommended that T2 FSS can be incessantly adopted in
domains and attributes having different format and the research area of candidate-well selection because
configuration such as petrophysical well logs, drilling, they can assist in developing models to make decisions
production, and reservoir files, rock mechanical data, and which are often viewed as complicated, and uncertain.
etc. to screen and ultimately select a candidate(s).
Considering the complex, nonlinear, and imprecise
nature of data in this process, decision makers are ACKNOWLEDGEMENT
beginning to add other methods to the selection process
in order to handle uncertainty and further assist in The authors of this paper would like to express their
determining the best fit for a treatment. It becomes gratitude to Universiti Teknologi Malaysia due to the
obvious that the ability to manage uncertainty turns out to administrative and financial supports during this study.
Zoveidavianpoor et al. 4059
REFERENCES 54-58.
Mohaghegh SD (2005). Recent developments in application of artificial
Conway MW, McMechan DE, McGowen JM, Brown D, Chisholm PT, intelligence in petroleum engineering. J. Pet. Technol. 57(4):86-91.
Venditto JJ (1985). Expanding recoverable reserves through Mohaghegh SD, Reeves S, Hill D (2000). Development of an intelligent
refracturing. Paper SPE 14376 presented at the SPE annual system approach for restimulation candidate selection. Paper SPE
technical conference and exhibition. 22-25 September. Las Vegas, 59767 presented at the SPE/CERI gas technology symposium, 3-5
Nevada, USA. p. 8. April. Calgary, Canada. p. 11.
Dereli T, Baykasoglu A, Altun K, Durmusoglu A, Trksen B (2011). Moore LP, Ramakrishnan H (2006). Restimulation: candidate selection
Industrial applications of type-2 fuzzy sets and systems: A concise methodologies and treatment optimization. Paper SPE 102681
review. Comput. Ind. 62(2):125-137 presented at the SPE annual technical conference and exhibition. 24-
East L, Craig D (2006). Refracs reverse production dips: single- and 27 September. San Antonio, Texas, USA. p. 9.
multiple-zone wells see output gains after refracturing. E&P Mag. Oberwinkler C, Economides M (2003). The definite identification of
79(11):45-47. candidate wells for refracturing. Paper SPE 84211 presented at the
Economides MJ, Nolte KG (2000). Reservoir stimulation. 3rd Edition, SPE annual technical conference and exhibition. 5-8 October 2003.
John Wiley & Sons Ltd, London p. 856. Denver, Colorado, USA. p. 17.
Ely JW, Rothenberg M, Krupa A, McDougal F, Conway M, Reeves S Oberwinkler C, Rythammer G, Zabgl G, Economides MJ (2004). New
(2000). Restimulation program finds success in enhancing tools for fracture design optimization. Paper SPE 86467 presented at
recoverable reserves. Paper SPE 63241 presented at the SPE the SPE international symposium and exhibition on formation
Annual Technical Conference and Exhibition, 1-4 October. Dallas, damage control. 18-20 February. Lafayette, Louisiana, USA. p. 13.
USA. p. 12. Olatunji SO, Selamat A, Abdul Raheem AA (2011a). Modeling the
Emrich E, Shaw D, Reasoner S, Ponto D (2001). Codell restimulation permeability of carbonate reservoir using type-2 fuzzy logic systems.
evolve to 200% rate of return. Paper SPE 67211 presented at the Comput. Ind. 62(2):147-163.
SPE production and operations symposium. 24-27 March. Oklahoma Olatunji SO, Selamat A, Abdul Raheem AA (2011b). Predicting
City, Oklahoma, USA. p. 8. correlations properties of crude oil systems using type-2 fuzzy logic
Finol J, Guo YK, Jing DY (2001). A rule based fuzzy model for the systems. Expert Syst. Appl. 38(9):10911-10922.
prediction of petrophysical rock parameters. J. Pet. Sci. Eng. 29(2): Quenes A (2000). Practical application of fuzzy logic and neural
97-113. networks to fractured reservoir characterization. COMPUT GEOSCI.
Flores DQ (2009). Finding additional resources in a mature field: 26(8):953-962.
refracturing engineering workflow for a successful campaign in Reeves SR, Bastian PA, Spivey JP, Flumerfelt RW, Mohaghegh SD,
Vicksburg basin, south Texas. Abstract SPE 125260 presented at the Koperna GJ (2000). Benchmarking of restimulation candidate
SPE Tight Gas Completions Conference. 16-17 June. San Antonio, selection techniques in layered, tight gas sand formations using
Texas, USA. reservoir stimulation. Paper SPE 63096 presented at the SPE Annual
Garrouch AA, Lababidi HMS (2001). Development of an expert system Technical Conference and Exhibition. 1-4 October. Dallas, Texas,
for underbalanced drilling using fuzzy logic. J. Pet. Sci. Eng. 31(1): USA. p. 16.
23-39. Reeves SR, Hill DG, Tiner RL, Bastian PA, Conway MW, Mohaghegh
Grieser B, Shelley B, Johnson BJ, Fielder EO, Heinze JR, Werline JR SD (1999). Restimulation of tight gas sand wells in the Rocky
(2008). Data analysis of Barnett Shale completions. SPE J. 13(3): Mountain region. Paper SPE 55627 presented at the SPE Rocky
366-374. Mountain regional meeting. 15-18 May. Gillette, Wyoming, USA. p. 9.
Hameed IA (2009). Simplified architecture of a type-2 fuzzy controller Shelley RF (1999). Artificial neural networks identify restimulation
using four embedded type-1 fuzzy controllers and its application to a candidates in the Red Oak field. Paper SPE 52190 presented at the
greenhouse climate control system. Proceedings of the Institution of SPE mid-continent operations symposium. 28-31 March. Oklahoma
Mechanical Engineers, Part I: J. Syst. Control Eng. 223(5): 619-631 City, Oklahoma, USA. p. 7.
Jang JSR, Sun CT, Mizutani E (1997). Neuro-fuzzy and soft computing. Tinkir M (2011). A new approach for interval type-2 by using adaptive
A computational approach to learning and machine intelligence. network based fuzzy inference system. Int. J. Phys. Sci. 6(19):4502-
Prentice-Hall: Englewood Cliffs, New Jersey, p. 614. 4518.
Kadkhodaie IA, Rezaee MR, Moallemi SA (2006). A fuzzy logic Vincent MC (2011). Restimulation of Unconventional Reservoirs: When
approach for estimation of permeability and rock type from Are Refracs Beneficial? J. Can. Pet. Technol. 50(5):36-59.
conventional well log data: an example from the Kangan reservoir in Xiong H, Holditch SA (1995). Using a fuzzy expert system to choose
the Iran Offshore Gas Field. J. Geophys. Eng., 3(4):356-369. target well and formations for stimulation. In Braunschweig et al (eds)
Khademi HJ, Shahriar K, Rezai B, Bejari H (2010). Application of fuzzy Artificial intelligence in the petroleum industry: symbolic and
set theory to rock engineering classification systems: an illustration of computational applications. Editions Technip, Paris, pp. 361-379.
the rock mass excavability index, Rock Mech Rock Eng. 43(3):335- Yang E (2009). Selection of target wells and layers for fracturing with
350. fuzzy mathematics method. paper presented at the sixth international
Klir GJ, Wierman MJ (1999). Uncertainty-based information: elements conference on fuzzy systems and knowledge discovery, pp. 366-369.
of generalized information theory, Physica-Verlag Heidelberg, New Yin D, Wu T (2009). Optimizing well for fracturing by fuzzy analysis
York p. 185. method of applying computer. paper presented at the 1st IEEE
Liao RF, Chan CW, Hromek J, Huang GH, He L (2008). Fuzzy logic international conference on information science and engineering. pp.
control for a petroleum separation process. ENG APPL ARTIF 286-290.
INTEL. 21(6):835-845. Zadeh LA (1965). Fuzzy sets. Inform Control 8:338-353.
Malik K, Mohaghegh SD, Gaskari R (2006). An intelligent portfolio- Zadeh LA (1992). Fuzzy logic, neural networks, and soft computing.
management approach to gas storage field deliverability maintenance One-page course announcement of CS 294-4. The University of
and enhancement: part one- database development and model California at Berkeley.
building. Paper SPE 104571 presented at the SPE eastern regional Zadeh LA (2006). Generalized theory of uncertainty (GTU) principal
meeting. 11-13 October. Canton, Ohio, USA. p. 6. concepts and ideas. Comput Stat Data Anal. 51:15-46.
McVey DS, Mohaghegh S, Aminian K, Ameri S (1996). Identification of Zadeh LA (2008). Is there a need for fuzzy logic? Inf. Sci. 178:2751-
parameters influencing the response of gas storage wells to hydraulic 2779.
fracturing with the aid of a neural network. SPE Comput Appl. 8(2): Zimmermann HJ (2000). An application-oriented view of modeling
4060 Int. J. Phys. Sci.