Proceedings of the 2016 International Conference on Industrial Engineering and Operations Management

Kuala Lumpur, Malaysia, March 8-10, 2016

Application of Fuzzy Logic and Fuzzy Systems in Machining:

A Literature Review
S. Singhal*, Ranganth M.S., R. Batra, S. Nanda
Department of Mechanical, Production & Industrial and Automobile Engineering
Delhi Technological University
New Delhi, India
[email protected]

Abstract— Fuzzy Logic has found popularity in the academic community and widespread use in the industry due to ever increasing
complexities in systems, at the core of which lies vagueness, uncertainty and imprecision in information. The proposition of fuzzy set
theory, specifically Fuzzy Inference Systems (FIS) led to an explosion of its application in diverse fields including manufacturing
especially machining owing to their ability to handle numeric and linguistic information in the same framework. This literature review
focuses on the use of FIS in various aspects of machining including process selection, parametric optimization, decision making, etc.
The emphasis is first laid down on a review of various fuzzy tools and their evolution & application in past two decades. It is then
shifted to area specific applications of FIS and its combination with neural networks. This review provides an effective insight into the
world of intelligent and intuitive systems developed to mimic the human minds’ capabilities in an efficient manner. It concludes with
the fact that more emphasis can be laid on the use of fuzzy based systems in certain aspects of machining whereas application specific
adaption of the concepts seem less popular.

Keywords— fuzzy logic; fuzzy inference system; machining; set membership; ANN; Taguchi method

I. INTRODUCTION
The history and foundations of Artificial Intelligence can be traced back to a conference in 1956 held in Dartmouth College
where the term was originally coined. Since then it has emerged from being a mere theory to a concept with rampant
application in intelligent computing systems nowadays. Zadeh’s article on proving convexity of disjoint fuzzy sets in 1965
paved the way for their popularity and acceptability in the academia but still found very limited use in the industry. Fuzzy
systems are applied to artificial intelligence for representing the knowledge of experts or acquired through learning process.
Additionally, fuzzy systems provide a rich and robust method of building systems that include multiple conflicting,
cooperating, and collaborating knowledge. It is a method specifically developed to incorporate uncertainty by processing
information termed as grey (white for perfect information and black for complete absence of information) into a decision
making model.
Essentially, fuzzy logic allows for considering reasoning that is approximate rather than precise by use of linguistic
variables as both inputs and responses. Fuzzy based inference systems or FIS provide a much simplified platform where the
development and analysis of models require reduced development time than other approaches. This has resulted in its
widespread within the industry as well for a wide variety of applications. It considers variables to be included in a set based on
their degrees of membership, rather than absolute membership. Instead of precision and accuracy, fuzzy logic carries along a
level of tolerance for imprecision. Fuzzy logic attempts to mimic the human mind to effectively employ modes of reasoning
that are approximate rather than exact. By allowing for the inclusion of imprecision in memberships, fuzzy logic allows for the
detection of imprecise dependencies among concepts [1]. The approach differs from the use of crisp sets in which an element is
either a member of the set or not. Fuzzy sets, on the other hand, allow elements to be partially in a set. Each element is given a
degree of membership in a set. This membership value can range from 0 (not an element of the set) to 1 (a member of the set).
It is clear that if one only allows the extreme membership values of 0 and 1, then this would actually be equivalent to crisp sets.
A membership function is the relationship between the values of an element and its degree of membership in a set [2].
A fuzzy inference system (FIS) is a system that uses fuzzy set theory to map inputs to outputs (or responses). The most
popular and widely used FIS are Mamdani and Sugeno types. They comprise of a fuzzification interface, a rule database, a
decision making unit and defuzzification interface as shown in Fig. 1. The first two parts of the fuzzy inference process,
fuzzifying the inputs and applying the fuzzy operator, are the same in both the types. The main difference lies in the fact that
output membership functions in Sugeno type are either linear or constant. Although the Mamdani type system has gained
widespread acceptance owing to it being intuitive and well suited to human input, Sugeno type systems are still considered a
notch higher due to computational efficiency, suitability to mathematical analysis and guaranteed continuity of output surfaces
[3].

© IEOM Society International 1905

Proceedings of the 2016 International Conference on Industrial Engineering and Operations Management
Kuala Lumpur, Malaysia, March 8-10, 2016

INPUT OUTPUT
FUZZY RULES
(CRISP VALUE) (CRISP VALUE)

GREY
RELATIONAL FUZZIFIER DEFUZZIFIER MPCI
COEFFICIENTS

PROCESSING

Fig. 1. Flow chart representing Fuzzy Inference System

This research focuses on application of these intelligent systems to machining and attempts to find the reason behind its
widespread acceptance beginning with small history of evolution of artificial intelligence and fuzzy logic. It then gives a clear
picture regarding the background of the techniques prominently used and fuzzy logic as a whole. The study then clearly
demarcates the application of FIS and fuzzy techniques in a variety of industries and research purposes.
II. LITERATURE REVIEW
A. History
Long before the methodology of fuzzy logic had emerged, ancient Greek philosophy conceived the traditional notions of
set membership and logic. The efforts of Aristotle and the philosophers who preceded him were largely responsible for the
success of mathematics. The postulation of the so-called “Laws of Thought” was the result of their efforts to develop a concise
theory of logic, and later mathematics [4]. One of these laws is the “Law of the Excluded Middle” which states that every
proposition must either be true or false. But when the first interpretation of this law was proposed by Parminedes (around 400
B.C.), strong objections emerged; one of these was a proposal by Heraclitus that things can be simultaneously True and not
True. It was Plato who laid the foundation for what has become fuzzy logic, indicating that there could be a third region
(beyond True and False) where these opposites “toppled about”. Hegel, Marx, and Engels were among the modern
philosophers of those times who echoed thoughts of Plato. The first attempts for formulation of a multi-valued logic were
made around the end of the nineteenth century. But it was Pole Jan Lukasiewicz who first introduced a well-known system of
multi-valued logic of Aristotle in the 1920s. In his system of logic, Lukasiewicz defined a third truth value other than true and
false [5]. But in 1930s, some renowned mathematicians such as Brouwer, and von Neumann proposed the possibility of an
infinite number of truth values.
B. Background
Lotfi A. Zadeh, a professor for computer science at the University of California in Berkeley, pioneered Fuzzy Logic in
1965 [6, 7, 8] to address the issues of application complexities arising due to nonlinearities, poorly defined dynamics, absence
of a priori information, imprecision, uncertainties and vague description of the system [9]. He laid the foundation of fuzzy sets
which he defined as ‘a class of objects with a continuum of grades of membership’ [6]. He made the use of some of the notions
of set membership such as union, intersection, complement, relation, etc. in the same sense as they are used in set membership.
At that time, his concept had to face a lot of criticisms, some of which were from his colleagues. A few mathematicians
thought that the notions of fuzzy would encourage some sort of imprecise thinking while others believed ‘fuzzification’ is a
kind of scientific permissiveness. Due to the aforementioned reasons, fuzzy logic developed slowly and its applications came
into light after a long time. First industrial applications of fuzzy logic were observed in Europe in 1970s. Later, it became
popular because of ease of application in decision making and data analysis.
Decision making problems involves many ambiguous and vague objectives and constraints. Therefore, a robust
performance evaluation method is a requisite process. In real world problems, these evaluation techniques can handle cases of
subjectivity, fuzziness and imprecise information and the implementation of fuzzy sets theory can provide a more precise and
optimized value in evaluation systems [10]. Several researchers have emulated the above approach through analytical
hierarchy process (AHP), for example in personnel selection [11, 12] and shipping performance evaluation [13], where all the
fuzzy sets were aggregated for evaluation.

© IEOM Society International 1906

 Proceedings of the 2016 International Conference on Industrial Engineering and Operations Management
Kuala Lumpur, Malaysia, March 8-10, 2016

TABLE I. SELECTED LITERATURE REVIEW OF FUZZY LOGIC’S APPLICATION IN MACHINING PROCESSES

Topic Author(s)/Year Description

Optimization of Fang and Jawahir (1994) Proposes integrated fuzzy-sets models to assess total machining performance in finish turning
Machining Processes
Develops fuzzy pulse discriminator to organize various discharge pulses in EDM process for
Tarng, Tseng and Chung (1997)
optimizing machining productivity
Applies integrated approach of artificial neural networks (ANNs) and fuzzy logic for
Kuo and Cohen (1998)
manufacturing process control
Lin, Wang, Yang and Tarng An establishment of a multi-response performance index using Taguchi fuzzy-based approach to
(2000) improve EDM process
Fabricates multi-variables fuzzy logic controller aiming to improve machining accuracy at corner
Lin, Chung and Huang (2001)
parts for wire-EDM

Lin, Lin and Ko (2002) Compares optimization results of grey relation analysis and fuzzy-based Taguchi method

Predicts workpiece surface roughness in end milling using adaptive network based fuzzy
Lo (2003)
inference system (ANFIS) model

Lin and Lin (2005) Multi-objective optimization of EDM process using grey-fuzzy logic

An application of fuzzy logic along with Taguchi methods to study the correlation between
Tzeng and Chen (2007)
machining accuracy and precision
Predicts manufacturing process capability based on Taguchi index using two fuzzy inference
Hsu and Shu (2008)
criteria
Çaydaş, Hasçalık and Ekici Predicts wire-EDM process parameters using adaptive network based fuzzy inference system
(2009) (ANFIS) model
Employs fuzzy based Principal component function to optimize multi-response during dry
Ramanujan et al. (2014)
turning operation

Selection of Performance Balazinski, Bellerose and Use of compositional rule of inference (CRI) to generate fuzzy decision support system (FDSS)
Parameters Czogala (1994)
Baradie (1997) Computerizes Machining Data Handbook to facilitate machining data selection based on fuzzy
logic
Hashmi, Baradie and Ryan Selection of cutting conditions in machining operations based on fuzzy control techniques
(1998)
Yilmaz, Eyercioglu and Gindy Intelligent selection of EDM process parameters by means of user-friendly fuzzy-expert system
(2006)

C. Application: Optimization of Machining Processes

Researchers have attempted to apply methodology of fuzzy systems in a wide domain. One of these is the optimization of
machining with the application of fuzzy system. The implementation of fuzzy system proved to be highly helpful in case of
very complex or highly nonlinear processes, in the absence of any simple mathematical model or the need of processing of
expert knowledge. Tarng, Tseng and Chung (1997) used fuzzy set theory to develop a new pulse discriminator in electric
discharge machining (EDM) process. In EDM process, cutting performance indexes such as material removal rate (MRR) and
surface roughness have strong relationship with the EDM discharge pulses. Hence it is very important to develop a pulse
discriminator in order to classify various discharge pulses in EDM for optimization of machining productivity. The fuzzy pulse
discriminator (FPD) consisted of a fuzzifier, a knowledge base and an inference engine. In FPD, the EDM discharge pulses
were classified based on the linguistic rules attained from the knowledge of experts and expressed mathematically through the
fuzzy sets theory. Since the membership functions of FPD have a great influence on its classification performance, the relevant
membership functions have been synthesized automatically with the application of a machine learning method. This method
was based on a simulated annealing algorithm which is a heuristic search technique. This approach can classify EDM
discharge pulses correctly and instantly under varying cutting conditions [14]. The aim of the work done by Tzeng and Chen
(2007) was to develop a robust, versatile and high speed EDM technique. This was achieved by optimizing the machining
precision and accuracy with the application fuzzy logic analysis incorporation with the Taguchi dynamic method. They
employed a fuzzy logic system to study the association of machining precision with machining accuracy. The fuzzy system is
composed of a fuzzifier, an inference system, a data base, a rule base and defuzzifier, and further used ANOVA to determine
the process parameters that significantly affect the multiple performance characteristics (MPCs) and a confirmatory test of the
calculated optimal process showed that targeted MPCs have improved [15]. Lin, Wang, Yang and Tarng applied the Taguchi

© IEOM Society International 1907

Proceedings of the 2016 International Conference on Industrial Engineering and Operations Management
Kuala Lumpur, Malaysia, March 8-10, 2016

method with fuzzy logic to improve the electrical discharge machining (EDM) process with multiple performance
characteristics (MPCs) by transforming the optimization of these complicated MPCs into the optimization of a single multiple
response performance index (MRPI). The Taguchi method can optimize performance characteristics by adjusting the process
parameters and increase the insensitivity of the performance of the system to sources of variation. As a result, the Taguchi
method has become a powerful tool in the design of experiment (DOE) methods. It uses a special orthogonal array design to
study the entire parameter space preventing the conduction of a large number of experiments. Considering the MPCs (electrode
wear ratio (EWR) and material removal rate (MRR)), the machining parameters such as the workpiece polarity, pulse-on time,
duty factor, open discharge voltage, discharge current and dielectric fluid are optimized. A fuzzy reasoning of the MPCs has
been carried out by the fuzzy logic unit. The fuzzy logic unit comprises a fuzzifer, membership functions, a fuzzy rule base, an
inference engine, and a defuzzifer [16].
Ramanujan, Venkatesan, Saxena, Pandey, Harsha et al. attempted to combine the multi-responses of the dry turning
operation into a single multiple performance index using principal component function based on fuzzy system as well as
design of experiment based on Taguchi method. The aim of their work was to optimize the machining parameters during dry
turning operation of Inconel 625 to minimize surface roughness and power consumption and maximize material removal rate.
The entire machining parameter space is investigated using L9 orthogonal array. The fuzzy reasoning grades are evaluated and
are optimized using the Taguchi method. A hybrid principal component analysis based on fuzzy system was employed because
it takes into account all the principal components to obtain the multiple performance index which leads to the reduction in
errors [17]. Hsu and Shu developed a realistic approach to work on imprecise output data observed during the measurements of
the products quality. They introduced a general method which combines the vector of fuzzy numbers to produce the
membership function of fuzzy eliminator of the Taguchi index for further process capability testing. The Taguchi index, also
called the loss-based process capability index Cpm, was proposed by Hsiang and Taguchi (1985) to measure process capability,
wherein the output process data is precise. Process capability index provides statistical measures to check whether a process
binds to the specified manufacturing capability prerequisite. In this approach, Hsu and Shu proposed two fuzzy inference
criteria, the critical value and the fuzzy P-value, to assess the manufacturing process capability based on Cpm. They applied the
proposed methodology to the luminous intensity of LED sources data to check for its applicability [18].
Lin, Chung and Huang (2001) tried to improve the wire-EDM machining accuracy at corner parts without compromising
with its cutting feed rate. They presented a new control strategy based on fuzzy logic to improve the cutting precision. With the
application of fuzzy logic control, software implementation and incorporation of expert knowledge without any need for an
explicit mathematical model can be done easily. The fuzzy rules are developed based on the physical characteristics and
experimental data of the wire-EDM process and on the past experience of the operator. Using this approach, machining errors
of corner parts are found to be reduced to less than 50% of those in normal machining, while the machining process time is
increased not more than 10% of the normal value [19]. In finish turning operation, the interrelated machining parameters are
present which make it is difficult to evaluate the total machining performance (TMP) including surface finish, tool wear rate,
dimensional accuracy, cutting power and chip breakability. Fang and Jawahir provided a new technique to evaluate each facet
of the TMP in finish turning of steels. They established a machining reference database providing a fundamental and
quantitative standard and a knowledge pool giving all the major factors influencing the TMP. The effects of these factors have
been quantified with the application of fuzzy-set method. They proposed a series of fuzzy-set models to evaluate quantitative
values of the TMP for any specific input conditions, encompassing work material properties, tool geometries, chipbreaker
types and cutting conditions [20].
Fuzzy logic coupled with artificial neural networks (ANN) has been utilized in a wide range of domains. Çaydaş, Hasçalık
and Ekici (2009) adopted an adaptive neuro-fuzzy inference system (ANFIS) model for predicting the average surface
roughness and white layer thickness (WLT) in the wire-EDM process. ANFIS model is made by the fusion of fuzzy inference
system (FIS) and artificial neural network (ANN) approaches as it uses the FIS modeling function and the ANN learning
ability. A hybrid learning algorithm, which merges the gradient method with the least squares method to optimize the process
parameters, forms the basis of this model. The machining parameters which were input to the model are pulse duration, open
circuit voltage, dielectric flushing pressure and wire feed rate. Fuzzy if-then rules of Sugeno type make the rule base of
ANFIS. To predict the desired performance parameters, the authors performed normalization of measured performance
parameters using standard min-max normalization methodology, feature reduction using principal component analysis (PCA)
and ANFIS tests using computer simulation. It was concluded that the proposed approach can be of great use for optimization
of surface roughness and WLT in the wire-EDM process [21]. Kuo and Cohen (1998) proposed a self-organizing and self-
adjusting fuzzy model (SOSAFM) which was based on the integration of fuzzy logic and ANN. They presented an online
estimation system which can be applied in the manufacturing control area. In this approach, Kohonen’s feature mapping is
employed to divide the inputs and outputs to the system and error back propagation (EBP)-type learning algorithm is used to
improve training parameters of ANNs. Evaluation of the proposed methods was done by conducting some physical
experiments for manufacturing process control. SOSAFM is found to be better than the multiple regression and artificial neural
network both with respect to speed and accuracy for the purpose of multi-sensor integration [22]. For predicting the surface
roughness of the workpiece after the completion of end milling process, Lo (2003) employed an adaptive-network based fuzzy

© IEOM Society International 1908

Proceedings of the 2016 International Conference on Industrial Engineering and Operations Management
Kuala Lumpur, Malaysia, March 8-10, 2016

inference system (ANFIS). Considering that spindle speed, feed rate and depth of cut are the three parameters of milling
process that have a major influence on the surface roughness, these performance parameters were analyzed. A comparison
between the triangular and trapezoidal membership functions was made during the training process of ANFIS to examine the
accuracy in predicting the surface roughness by these two membership functions. Results showed very satisfactory predicting
accuracy when either of the membership functions is used while the prediction accuracy of ANFIS has reached as high as 96%
when a triangular membership function is employed [23].
Many researchers adopted grey relational analysis based on the grey system theory to solve the complicated
interrelationships among the multiple responses. In their paper, Lin and Lin also attempted the application of grey-fuzzy logic
based on orthogonal array for the optimization of electrical discharge machining (EDM) process with MPCs. The effects of
machining parameters (pulse on time, duty factor and discharge current) to the MPCs (EWR, MRR and surface roughness)
were studied and analyzed. The experimental plan was designed based on L9 orthogonal array. Grey relational coefficient
(GRC) for each process response is calculated to analyze the degree of relation of the multiple responses. Fuzzy reasoning of
the MPCs is done using fuzzy logic and the experimental data was analyzed using the technique of analysis of variance
(ANOVA). It was concluded that these approaches could greatly improve the process responses such in the EDM process [24].
Lin, Lin and Ko (2002) applied the grey relational analysis based on an orthogonal array and fuzzy-based Taguchi method for
improving MPCs in the electrical discharge machining (EDM) process. The influence of the machining parameters (pulse on
time, duty factor, and discharge current) on the MPCs (electrode wear ratio, material removal rate, and surface roughness) is
investigated. The entire machining parameter space is investigated using L9 orthogonal array. The grey relational analysis
method comprises of grey relational generation, calculation of grey relational coefficient and computation of grey relational
grade to convert the optimization of complicated MPCs into optimization of a single grey relational grade. In fuzzy-based
Taguchi method, S/N ratio corresponding to each MPC is evaluated and fuzzified and fuzzy reasoning grade is obtained by
using the max–min fuzzy inference and centroid defuzzification methods to convert the optimization of complicated MPCs into
optimization of a single fuzzy reasoning grade. Both approaches can produce very similar experimental results but the
calculation using the grey relational analysis is much simpler than that the fuzzy logic analysis [25].
D. Application: Selection of Performance Parameters
Machining data play a vital role in the efficient utilization of machine tools and thus significantly influences the overall
manufacturing costs. Machining Data Handbook [26], published by Metcut Research Associates, is a vast information source
that compiles machining data for different combinations of tool-work. Baradie (1997) suggested the need and importance of
computerization of the Machining data Handbook which would provide an easy access to an immense collection of machining
data and lead to the integrated automation of the manufacturing process. He demonstrated the implementation of a fuzzy logic
model for metal cutting operation to develop a computerized machining database system that could be a great aid to the
process planner for establishment of the strategy for selecting machining data for a specific machining process [27]. In
Machinability data hand book [26], one may find different tool materials possible for each work material and hardness. So it
proves to be an ample way for selecting cutting parameters in machining processes. But in some cases, uncertainty may occur
if more than one choice is applicable for a particular cutting condition. To overcome this problem, Hashmi, Baradie and Ryan
(1998) applied fuzzy logic principles for selection process. The material hardness and the cutting speed are considered the
fuzzy input and output variables respectively. The fuzzy if-else rules are synthesized based on the information extracted from
the used machine tool. The triangular shaped membership functions are employed for both input and output. He compared the
cutting speed values predicted using the fuzzy logic model with the speed values recommended by the Machinability Data
Handbook and the results showed a good correlation between two speed values [28].
Balazinski, Bellerose and Czogala (1994) developed a fuzzy decision support system (FDSS) based on the compositional
rule of inference (CRI). CRI preserves a maximum amount of information contained in the rules and the observations. It is
based on the inference method of approximate reasoning applied for handling imprecise information. They attempted the
application of FDSS to the choice and modification of cutting parameters considering metal cutting processes to be stochastic,
nonlinear and ill-defined. The reasonable results showed that the proposed method would be appropriate for such kinds of
decision problems [29]. The parameter selection of the EDM is an obscure problem which is difficult to model as it depends on
heuristics and is based on experts’ experiences. Fuzzy set theory can play a major role in such problems and fuzzy logic can be
employed to emulate the performance of the expert and provide decision making abilities in the presence of certain degree of
vagueness. Following this approach, Yilmaz, Eyercioglu and Gindy (2006) developed a user-friendly intelligent system based
on fuzzy logic to make the selection of EDM parameters easy and accurate. A compact selection method is used based on
expert rules which are evaluated by the fuzzy set theory. A fuzzy model has been developed which uses fuzzy expert rules,
triangular membership functions for fuzzification and centroid area method for defuzzification processes. A system has been
implemented based on the proposed model which helps an unskilled user to select important parameters according to the
specific operation [30].

© IEOM Society International 1909

Proceedings of the 2016 International Conference on Industrial Engineering and Operations Management
Kuala Lumpur, Malaysia, March 8-10, 2016

III. CONCLUSION
This study is based on a state-of-the-art literature review of the application of fuzzy logic and fuzzy systems in various
sectors of manufacturing, specifically machining processes. Firstly, a brief definition of fuzzy logic and fuzzy inference system
is provided. It is followed by a brief description of origin of the notion of fuzzy logic and stating the reasons responsible for the
success & wide acceptability of fuzzy logic as a concept efficiently mimicking the human mind. The research includes the
work done in the field of manufacturing based on fuzzy system. From the literature available, it was concluded that fuzzy logic
has a wide area of application where imprecise and vague information is available but leaves a room for a more specialized
application and adaptation for the industry. Fuzzy Inference Systems (FIS) have been found to be the most commonly applied
fuzzy tool for processing information and data incorporating uncertainty. The concepts have gained wide popularity within the
academic community as a research subject for machining applications like EDM, turning, milling etc. and other manufacturing
processes like injection molding. It was observed that the fuzzy based concepts have been complementing other intelligent
systems like Artificial Neural Networks (ANN) and widely contributing to the field of machine learning. Fuzzy logic has also
found use in selection of performance parameters in conjugation with preexisting handbooks. This calls for a more adaptive
approach to this largely academic concept which gives due emphasis to taking fuzzy concepts out of research laboratories to
factories.

REFERENCES

[1] A. Azadegan, L. Porobic, S. Ghazinoory, P. Samouei and A.S. Kheirkhah, “Fuzzy logic in manufacturing: a review of literature and a
specialized application”, International Journal of Production Economics, vol. 132, issue 2, pp. 258-270, 2011.
[2] http://www.cs.princeton.edu/courses/archive/fall07/cos436/HIDDEN/Knapp/fuzzy002.htm.
[3] http://in.mathworks.com/help/fuzzy/comparison-of-sugeno-and-mamdani-systems.html.
[4] S. Korner, “Laws of thought,” Encyclopedia of Philosophy, Vol. 4, MacMillan, NY: 1967, pp. 414-417.
[5] C. Lejewski, ”Jan Lukasiewicz,” Encyclopedia of Philosophy, Vol. 5, MacMillan, NY: 1967, pp. 104-107.
[6] L.A. Zadeh, “Fuzzy Sets,” Information and Control, 1965.
[7] L.A. Zadeh, “Outline of A New Approach to the Analysis of Complex Systems and Decision Processes”, 1973.
[8] L.A. Zadeh, ”Fuzzy algorithms,” Info. & Ctl., Vol. 12, pp. 94-102, 1968.
[9] M. F. Azeem, “Fuzzy inference system– theory and applications”, InTech, Croatia, April, 2012, ISBN 978-953-51-0525-1.
[10] D. Zhou, J. Ma, E. Turban, N. Bolloju, “A fuzzy set approach to the evaluation of journal grades”, Fuzzy Sets and Systems, Volume
131, Issue 1, Pages 63-74, 1 October 2002.
[11] Saaty, T. (1995). The Analytic Hierarchy Process: RWS publications Pittsburgh, PA.
[12] F.A. Taylor III, A.F. Ketcham, D. Hoffman, "Personnel evaluation with AHP", Management Decision, Vol. 36 Iss: 10, pp.679 – 685,
1998.
[13] T. Chou, & G. Liang, “Application of a fuzzy multi-criteria decision-making model for shipping company performance evaluation”,
Maritime Policy & Management, 28(4), pp. 375-392, 2001.
[14] Y. S. Tarng, C. M. Tseng and L. K. Chung, “A Fuzzy Pulse Discriminating System For Electrical Discharge Machining”, International
Journal of Machine Tools and Manufacture, Vol. 37, No. 4, pp. 511-522, 1997.
[15] Y. F. Tzeng and F. C. Chen, “Multi-objective optimization of high speed electrical discharge machining process using a Taguchi
fuzzy-based approach”, Materials and Design, Vol. 28, pp. 1159 – 1168, 2007.
[16] J. L. Lin, K. S.Wang, B. H. Yan, and Y. S. Tarng, ‘‘Optimization of the electrical discharge machining process based on the Taguchi
method with fuzzy logics’’ Journal of Materials Processing Technology,Vol.102, pp.48-55, 2000.
[17] R. Ramanujam, K. Venkatesan, Vimal Saxena, Rachit Pandey, T. Harsha, Gurusharan Kumar, “Optimization of Machining
Parameters Using Fuzzy Based Principal Component Analysis during dry turning operation of Inconel 625 – A hybrid approach”,
Procedia Engineering, Volume 97, pp. 668-676, 2014.
[18] Bi-Min Hsu, Ming-Hung Shu, “Fuzzy inference to assess manufacturing process capability with imprecise data”, European Journal of
Operational Research, Volume 186, Issue 2, pp. 652-670, 16 April 2008.
[19] C. T. Lin, I. F. Chung, and S. Y. Huang, “Improvement of machining accuracy by fuzzy logic at corner parts for wire-EDM”, Fuzzy
Sets and Systems, Vol. 122, pp. 499 – 511, 2001.
[20] X. D. Fang and I. S. Jawahir, “Predicting total machining performance in finish turning using integrated fuzzy-set models of the
machinability parameters”, International Journal of Production Research, Vol. 32, Issue 4, pp. 833 – 849, 1994.
[21] U. Çaydaş, A. Hasçalık, S. Ekici, “An adaptive neuro-fuzzy inference system (ANFIS) model for wire-EDM”, Expert Systems with
Applications, Volume 36, Issue 3, Part 2, pp. 6135-6139, April 2009.
[22] R.J. Kuo, P.H. Cohen, “Manufacturing process control through integration of neural networks and fuzzy model”, Fuzzy Sets and
Systems, Volume 98, Issue 1, pp. 15-31, 16 August 1998.
[23] Ship-Peng Lo, “An adaptive-network based fuzzy inference system for prediction of workpiece surface roughness in end milling”,
Journal of Materials Processing Technology, Volume 142, Issue 3, pp. 665-675, 10 December 2003.
[24] J. L. Lin and C.L. Lin, “The use of grey-fuzzy logic for the optimization of the manufacturing process”, Journal of Materials
Processing Technology, pp. 9 – 14, November 2005.

© IEOM Society International 1910

Proceedings of the 2016 International Conference on Industrial Engineering and Operations Management
Kuala Lumpur, Malaysia, March 8-10, 2016

[25] C. L. Lin, J. L. Lin, and T. C. Ko, “Optimisation of the EDM Process Based on the Orthogonal Array with Fuzzy Logic and Grey
Relational Analysis Method”, The International Journal of Advanced Manufacturing Technology, Volume 19, Issue 4, pp. 271 - 277,
February 2002.
[26] Metcut Research Associates Inc., Machining Data Handbook, 3rd edn, Vols I and 2. Cincinnati, 1980.
[27] M. A. El-Baradie, “A fuzzy logic model for machining data selection”, International Journal of Machine Tools and Manufacture, Vol.
37, No. 9, pp. 1353 – 1372, 1997.
[28] K. Hashmi, M.A El-Baradie, and M. Ryan, “Fuzzy-logic based intelligent selection of machining parameters”, Journal of Materials
Processing Technology, Vol. 94, Issues 2–3, pp 94–111, September 1999.
[29] M. Balazinski, M. Bellerose, E. Czogala, “Application of fuzzy logic techniques to the selection of cutting parameters in machining
processes”, Fuzzy Sets and Systems, Volume 63, Issue 3, pp. 307-317, 10 May 1994.
[30] O. Yilmaz, O. Eyercioglu , and N. N. Z. Gindy, “A user-friendly fuzzy-based system for the selection of electro discharge machining
process parameters”, Journal of Materials Processing Technology, Vol. 173, No. 3, pp. 363 - 371, March 2006.

BIOGRAPHY

Shubham Singhal is a student of Mechanical Engineering at Delhi Technological University, New Delhi, India. He has been involved in
several research projects with Centre for Advanced Studies and Research in Automobile Engineering (CASRAE), DTU and many
governmental organizations. His research interests inlcude manufacturing, machining, mechatronics and robotics, six sigma, IC engines and
parametric optimization. He wishes to pursue his research in Robotics specializing in Humanoid robots after graduation. He is a member of
ASME, IET, IEEE, SAE and IMechE.

Dr. Ranganath M. Singari is currently the Associate Professor, Department of Production & Industrial Engineering, Delhi Technological
University. He is a Post Graduate and Doctorate from University of Delhi. He has made contribution in the areas of Production
Engineering, Metal Cutting and Automation. He is a Life member of Indian Society of Technical Education, Computer Society of India and
Indian Society of Mechanical Engineering. He has published more than 50 research papers in the area of Productio Engineering.

Rushil Batra is a student of Mechanical Engineering at Delhi Technological University, New Delhi, India. He has led the braking system
and manufacturing departments in SAE BAJA team of the university. He has done research projects with automobile manufacturers and
governmental organizations. His research interests include manufacturing, process engineering, non-conventional machining, lean
management, operations management and ergonomics. He wishes to pursue his research in Production & Industrial Engineering after
graduation. He is an active member of SAE, SME and IMechE.

Sahil Nanda is a student of Mechanical Engineering at Delhi Technological University, New Delhi, India. He has done research projects
with Indian Railways and many governmental organizations. His research interests inlcude manufacturing, machining, lean transformation,
six sigma, SCM and automotive systems. He wishes to do a job specializing in Manufacturing or Automotive Engineering after graduation.
He is a member of IEEE, IET, SAE and IMechE.

© IEOM Society International 1911