Sie sind auf Seite 1von 8

Expert Systems with Applications 38 (2011) 721728

Contents lists available at ScienceDirect

Expert Systems with Applications


journal homepage: www.elsevier.com/locate/eswa

Developing an integrated model for the evaluation and selection of six sigma
projects based on ANFIS and fuzzy goal programming
Abbas Saghaei *, Hosein Didehkhani
Science and Research Branch, Islamic Azad University, Tehran, Iran

a r t i c l e

i n f o

Keywords:
Six sigma
Project selection
Adaptive neuro fuzzy inference systems
Fuzzy goal programming

a b s t r a c t
Six sigma is one of the most popular tools to eliminate waste in organizations, reduce the cost and
improve quality. The process of creating and evaluating projects is an initial activity in implementing
six sigma. This paper aims at proposing a comprehensive methodology for the evaluation and selection
of the six sigma projects. For the evaluation of projects, reviewing the literature and decision teams opinion, we identied three main categories of criteria including business criteria, technological & process criteria and nancial criteria which contain eight sub-criteria. For deriving the overall utility of projects, we
designed an adaptive neuro fuzzy inference system which is capable to consider interrelations among criteria. Then, applying a fuzzy weighted additive goal programming model, we obtained the optimal portfolio of projects which should be implemented. Finally, we applied the proposed model in a leading
company in Iran to illustrate the applicability of the model.
2010 Elsevier Ltd. All rights reserved.

1. Introduction
Nowadays, the environment of manufacturing and service is
completely competitive. Companies are trying to reach and sustain
a competitive competency to protect their market share. But
reaching this aim is not possible without applying the concept of
a continuous improvement. The Japanese were pioneer in applying
quality concepts and continuous improvement. They have reported their impressive benets in both nancial on non-nancial
parts.
Recently, we have faced with concepts such as quality management, customer satisfaction, cost of poor quality, quality improvement and as likes. These concepts relate to a wide range category
named Total Quality Management (TQM). Six sigma is one of the
most applicable approaches helps organizations to implement
TQM concepts. Since its innovation by the late Bill Smith of Motorola, six sigma concepts have been widely utilized in the world of
industry. Using statistical techniques and approaches, six sigma
tries to eliminate subjectivity of decision making process and propose a systematic way to identify the problems and defects drivers.
Furthermore, six sigma presents some solutions for eliminating
these defects and improves the process capability to achieve a
business excellence and a competitive edge. Nowadays six sigma
has been considered as the most applicable and useful approach

* Corresponding author. Address: Hesarak, Science And Research Branch, Islamic


Azad University, Department of Industrial engineering, Tehran, Iran. Tel.: +98
9123010751.
E-mail address: a.saghaei@srbiau.ac.ir (A. Saghaei).
0957-4174/$ - see front matter 2010 Elsevier Ltd. All rights reserved.
doi:10.1016/j.eswa.2010.07.024

to improve the quality of products and services and also reaching


a business excellence and a competitive advantage by eliminating
wastes (Chao & Chia, 2008). At rst glance, the six sigma looks
strikingly similar to a prior quality management approach. However, leading organizations with a track record in quality have
adopted six sigma and claimed that it has transformed their organization (Roger, Linderman, Liedtke, & Choo, 2008). Researchers
have reported the success of six sigma in both manufacturing
and services (Lanyon, 2003; Robinson, 2005).
DMAIC approach is the most applicable procedure for implementing six sigma includes ve major phases:
1. Dene: At this phase, after identifying potential projects and
selecting best one(s), by constructing a decision team, an organization tries to implement those projects.
2. Measure: This phase includes the measurement of current process capabilities and identies the most important parameters
of goods and services.
3. Analyze: In this phase, organization tries to collect and analyze
the past and current data to identify the relations and the reasons of defects and variations in process and products
characteristics.
4. Improve: In this phase, based on the previous data, we propose
some solutions and remedies to overcome the wastes. Also we
should prove the effectiveness and efciency of these solutions
and implement them.
5. Control: And nally, decision team sets some standards and
provides feedbacks to sustain the improvements (Gryna, Chua,
& Defeo, 2005, pp 90106).

722

A. Saghaei, H. Didehkhani / Expert Systems with Applications 38 (2011) 721728

In six sigma, all improvement activities are dened as projects


and improvement projects denition. Furthermore, selections are
the most important and initial activities to implement six sigma.
A suitable project selection is a major factor in the early success
and a long-term acceptance of six sigma within an organization.
A strategic project selection is one of the elements of six sigma definition in Rogers work (2008). Adam, Gupta, and Wilson (2003)
have identied the major elements of a six sigma project selection
as below:
1.
2.
3.
4.
5.

The identication of potential projects.


Project criteria.
Project selection.
Project assignment.
Project completion.

Recently, researchers have dealt with the problem of project


selection in six sigma. Chao and Chia (2008) developed a systematic methodology for the creation of six sigma projects. They developed an approach for the creation and evaluation of critical six
sigma projects and ranking them based on identied criteria. They
applied a fuzzy AHP methodology for ranking projects. Kahraman
and Bykzkan (2008) developed a weighted additive fuzzy goal
programming methodology for selecting the best suitable portfolio
of projects in six sigma. They used fuzzy AHP for deriving the
importance weights of criteria such as maximize nancial benets,
maximize process capability, maximize customer satisfaction,
minimize cost, minimize project completion time and minimize
risk. Kumar, Saranga, Ramirez-Marquez, and Nowicki (2007) applied a DEA model to derive the efcient six sigma projects. They
identied inputs and outputs of the six sigma projects, and then
applying a basic DEA model, they derived the efcient frontier of
six sigma projects. Also, they carried out a sensitivity analysis to
study the impact of variation in projects inputs and outputs on
project performance and to identify the critical inputs and outputs.
Yang and Hsieh (2008) developed a fuzzy AHP model for the selection of six sigma projects. Taiwan national quality award criteria
were used to evaluate projects. Kumar, Nowicki, Ramirez-Marquez,
and Verma (2008) in other works, developed a mathematical programming methodology for selecting the best six sigma projects.
They used a non-linear binary model based on Taghuchi function
to select the best projects. The basic models for the assessment
and ranking of projects in all elds of industry and business are
MCDM models such as AHP, TOPSIS and etc. but some factors
should be considered when we apply these models. The most
important challenge is that these models cannot take into consideration the inner dependencies and relations among criteria, so the
validity of these models, where these inner dependencies exist, is
questionable. Another challenge is that these models need predetermined weights of criteria. In particular, when there is more than
one decision maker (DM), it is very hard to obtain reliable weights
of criteria. Another challenge is that which category the sub-criteria belong to. Because the global weight of sub-criteria strongly depends on the weight of criterion which they belong to, so, where
there is an ambiguity about the structure of criteria and sub-criteria, it is not reasonable to use structural approaches like AHP. To
handle these challenges, we used the concept of neural networks
and especially adaptive neuro fuzzy inference systems which are
efcient models for function approximation, clustering and pattern
recognition. These hybrid models are the combination of fuzzy
inference systems and neural networks. The use of neural networks
enhances fuzzy inference systems to t the best membership
functions (antecedent parameters) and functions coefcients (consequent parameters). These models simply identify interrelationships and non-linear treats of criteria. In the case of six sigma

project selection, as we can see in the literature, most of models


are AHP, TOPSIS etc., but the six sigma project selection criteria
are not independent. For example business criteria strongly depend on nancial and process criteria. So we cannot consider these
criteria in a hierarchy. In ANFIS the weights of criteria and the position of criteria are not important because in the training procedure, ANFIS chooses the best combination of criteria to create the
best solutions with the minimum of error. As mentioned in the literature, we can categorize the previous works into two categories:
The evaluation and ranking of projects (Kumar et al., 2007; Chao &
Chia, 2008) and the selection of projects (Kahraman & Bykzkan,
2008; Kumar et al., 2008). In this paper, we deal with both the evaluation and selection of projects. First, applying an ANFIS model
which can derive the subjective knowledge of decision team and
ts the best FIS, the utility of projects is evaluated. Then, by designing a weighted additive fuzzy binary goal programming model, we
select the optimal portfolio of projects to implement.
2. Six sigma project selection criteria
Identifying the criteria of selection procedures is the most
important and challenging part of any selection process. In the eld
of six sigma, there are some conventional criteria which, six sigma
stands for them. Criteria such as, reducing reworks and failures,
improving customer satisfaction and business excellence. But, in
practical works, there are always some special criteria which
should be considered. These criteria usually are derived by decision
team. Snee (2002) has discussed that suitable six sigma projects
should satisfy some criteria such as reasonable scope, business priorities and as likes. In another work, Banuelas, Antony, and Brace
(2005) applied a cause and effect matrix to identify the projects.
They only used three factors, runtime, quality and waste. We have
summarized six sigma project selection criteria in Table 1.
In this paper, we consider a comprehensive range of criteria
should be taken into consideration for six sigma project assessment and selection. We categorized those criteria into three main
categories: business & customer criteria, nancial criteria, process
and technological criteria. We describe each category briey:
2.1. Business and customer satisfaction criteria
Reaching business excellence and competitive competencies are
the most requested aims of implementing six sigma projects. In a
competitive environment, even a bit improvement in customer
satisfaction may result in extending the market share. So, projects
which have an impressive impact on customer satisfaction and
improving competitiveness are desirable. Another important criterion is reaching strategic goals and the mission of the company. All
quality rewards have considered the strategic plan as an important

Table 1
Review of six sigma project selection criteria.
Criteria
Snee (2002)
Banuelas et al. (2005)
Kahraman and
Bykzkan (2008)
Adam et al. (2003)
Yang and Hsieh (2008)

Reasonable scope, business priorities, major


importance to organization
Financing, customer satisfaction, cost, risks and
alignment of strategic business goals and objectives
Financial benets, process capability, customer
satisfaction, cost, project completion time and risk
Customer impact, nancial impact, business process,
Time to complete, Learning and growth
Leadership, strategic management, customer/
market development, process management,
business results and etc. ( Taiwan quality award
criteria)

723

A. Saghaei, H. Didehkhani / Expert Systems with Applications 38 (2011) 721728

criterion in the process of evaluation. In this category, we consider


three sub-criteria: customer satisfaction, reaching business excellence and helping company implement the strategic plan.
2.2. Financial criteria
Contemporary companies continuously try to reduce the cost.
Because cost reduction, is one of the most important strategies
for extending market share. Improving the process capabilities
and reliability and eliminating the cost of poor quality, six sigma
projects can reduce the total cost of the company. Also for deriving
the top management agreement for applying six sigma projects, we
should predict the outcomes of projects in the term of nancial
variables. We considered three sub-criteria including: increasing
return on investment (ROI), reducing cost of reworks and scrap,
reducing cost of appraisal and prevention activities.
2.3. Process and technological criteria
In the concept of the cost of a poor quality (CoPQ), the major
elements are related to the process criteria. Variability of product
characteristics, unplanned downtime of equipment, inventory
shrinkage, variation of process from best practice and non valueadded activities are some inefciencies mentioned by Gryna
et al. (2005). These criteria have been shown in Table 2.

3. Model construction
In this section, we describe stages of the proposed methodology
elaborately. The model includes two stages: The evaluation stage
and the selection stage. In the rst stage, we develop an adaptive
neuro fuzzy inference system to derive the total utility of each project considering project selection criteria. In the second stage, we
develop a fuzzy binary weighted additive goal programming model
for deriving the optimal portfolio of projects.
3.1. Evaluation Stage: designing an ANFIS for deriving overall utility of
projects

fuzzy reasoning. Fuzzy reasoning, also known as approximate reasoning, is an inference procedure that derives conclusions from a
set of fuzzy if-then rules and known facts. The fuzzy inference system is a popular computing framework based on the concepts of
fuzzy set theory, fuzzy if-then rules, and fuzzy reasoning. It has
been applied successfully in a wide range of science and engineering such as control, function approximation, signal processing,
simulation, data clustering and data mining and decision support
systems. In literature, we can nd some other names such as fuzzy
rule-based system, fuzzy expert system, fuzzy model, fuzzy associative memory, fuzzy logic controller, and simply (and ambiguously) fuzzy system. Fuzzy IF-THEN rules are the basic on fuzzy
inference systems (Jang, Sun, & Mizutani, 1996). A fuzzy rule is
in the following form:
IF premise (antecedents), THEN conclusion (consequents).
In application cases, there is always more than a one rule. There
has been developed some inference methods such as Mamdani
inference system (1977), and Takagi and Sugeno inference systems
(1985). Conventional inference systems, in spite of their applicability, have some shortages such as: there is no systematic procedure
for rule generation and validation, and also there is no systematic
approach for optimizing the system parameters such as membership function parameters to achieve more accurate solutions. Jang
(1993) developed a network-based inference system which was
capable to be trained from experiments. He called that ANFIS,
which is the abbreviation of adaptive neuro fuzzy inference system. He applied least square estimator (LSE) and back-propagation
(BP) to train the system. The most common inference system used
in ANFIS is a rst order Sugenu system which is in the form of:

e 1 and x2 is A
e 1 . . . and xn is A
e 1 then y f1 x1 ; x2 ; . . . ; xn
If x1 is A
1
1
2
n
e m and x2 is A
e m . . . and xn is A
e m then y fm x1 ; x2 ; . . . ; xn
If x1 is A
1

Table 2
Six sigma project selection criteria.
Criteria

Sub-Criteria

Business excellence and


Customer satisfaction

(i) Customer satisfaction (CS)


(ii) Reaching business excellence (BE)
(iii) Implementing strategic plan (SP)

Financial benets

(i) Increasing return on investment (ROI)


(ii) Reducing cost of reworks and scrap (RS)
(iii) Reducing cost of appraisal and
prevention activities (AP)

Process improvement

(i) Variability of product characteristics (VC)


(ii) Eliminating waste (non value-added)
activities (NV)

1
Where, xi; i = 1, . . . , n, are crisp inputs of system and yj is a crisp linear combination of inputs. The output of the system is calculated as
the weighted average of output functions as below:

Pm

j1 yj

Fuzzy set theory is a perfect mean for modeling uncertainty (or


imprecision) arising from mental phenomena, which are neither
random nor stochastic. Human beings are heavily involved in the
process of decision analysis. A rational approach toward decision
making should take into account a human subjectivity, rather than
employing only objective probability measures. This attitude
towards the uncertainty of human behavior led to the study of
a relatively new decision analysis eld: Fuzzy decision making
(Kahraman, Ertay, & Buyukozkan, 2006). Fuzzy inference systems
are one of the most applied and popular systems developed for


y

Pm

j1

n
Q

i1
n
Q

i1

lAi xi
2

lAi xi

In the rst layer, the rates of each project with respect to criteria are
fed into the network. These ranks are derived by a decision team.
The layer 2 includes fuzzy partitions of each input. The model is
capable to use different types of membership functions. Also, we
can choose different numbers of membership functions (MFs) to
partition the criteria space. Each MF has some parameters and
ANFIS during the training process will tune these parameters into
present desirable outputs with the minimum error. In layer 3, we
have some rules that can be derived by manager or by partitioning
of the criteria (input) space. Clustering the inputs is another
efcient way for a rule generation. Traditional K-means and fuzzy
c-means are criticized because we should impose the number of
clusters. Mountain clustering developed by Yager and Filev (1994)
is an efcient clustering approach which approximates the center
of clusters by using a density function called mountain function.
This approach uses the grid points as the alternatives of cluster centers. Chiu (1994) used data points as clusters center alternative instead of grid points in mountain clustering and called the method
subtractive clustering. In this paper, we use subtractive clustering
for rule generation. In the last layer, we aggregate the consequents
(yj; j = 1, . . . , m) to obtain the output of the system. In a hybrid learning method, consequent parameters are tuned too.

724

A. Saghaei, H. Didehkhani / Expert Systems with Applications 38 (2011) 721728

The proposed ANFIS model for assessment of projects is as


below:

Up

N
X

~ g
ui xi Pu

i1

3.2. Selection Stage: obtaining the portfolio of six sigma project using a
fuzzy weighted additive goal programming model
Goal programming has been a widely discussed and applied
technique for solving decision problems with multiple criteria. In
classical GP models, unpleasant deviations from goal values and
constraints dened by decision maker are minimized to derive a
desirable solution. The unwanted deviations are measured using
positive and negative deviation variables that are dened for each
and they represent overachievement of the goal, respectively. After
introducing the concept of fuzzy decision making by Bellman and
Zadeh (1970), researchers applied fuzzy logic with a Goal Programming. In classical goal programming models, all goals have equal
importance. Weighted additive models developed to consider different importance weights of goals and constraints. These models
use a single utility function that is the weighted summation of
goals and constraints satisfaction level (membership functions).
The weighted additive model, proposed by Tiwari, Dharmar, and
Rao (1987) is:

lD x

p
X

wj lzj x

wj

h
X

br lgr x

r1

j1
p
X

h
X

br 1

r1

j1

Parameters wj and br are normalized weighting coefcients represent relative importance among objectives and constraints. In fuzzy
goal programming, objectives and constraints are treated in the
same way. But, by varying weighting parameters, we can prioritize
objectives and constraints and emphasize on goals should be satised more strictly. By identifying variables kj and cr, the model can
be converted into this crisp single objective model:

Max

p
X

wj kj

h
X

cr 6 lgr x r 1; 2; . . . ; h

j1

wj

h
X

N
X

~
C i xi 6B

i1

Where B is the budget and Ci is the specic cost of ith project


3.3.3. Maximize the expected nancial benets (NPV) of projects
The nal goal of implementing six sigma projects is to increase
the protability of products and services by eliminating waste
activities and developing the product prole. Decision team should
estimate the nancial impact of projects. Moreover, the model
should look for portfolios with a higher nancial impact. We use
the net present value of projects as the metric of nancial benets.

Fp

N
X

~ g
NPV i xi PF

i1

So, by combining (5), (6) and (7), the FGP model for deriving portfolio of projects is:

p h 1; . . . ; m

ku 6 lu X
kc 6 lc X

kf 6 lf X
xi 2 f0; 1g
4

kj ; cr 2 0; 1 j 1; 2; . . . ; q and r 1; 2; . . . ; h
p
X

Cp

s:t:

br cr

s:t : kj 6 lzj x j 1; 2; . . . ; q

g p x 6 bp

3.3.2. The initial investment cost of the portfolio of projects


In organizations, the budget for implementing six sigma projects is limited and it isnt possible and reasonable to implement
all projects. Every project has its specic cost according to the
scope of project. By this goal, we try to minimize the cost of selected projects and have a portfolio of projects with the minimum
cost. Also, the minimum cost should be less or equal to the budget
approximately. The mathematical form of this goal is:

Max wu ku wc ku wf kf

r1

j1

Where, ui is overall utility of ith potential project derived by ANFIS


and ug is the requested utility level of portfolio. N is the number of
potential projects and xi is a binary variable where, is 1 if ith project
is selected otherwise is zero.

br 1; wj ; br P 0

r1

3.3. FGP Model formulating


In this section, we introduce the goals (or constraints) of proposed FGP model should be satised approximately. The term
approximately refers to fuzzy nature of the model. These goals
and constraints are:
3.3.1. Maximizing the utility of the portfolio of projects
In the previous stage, we derived the overall utility scores of
projects to enter them into the FGP model. These scores derived
by considering a wide range of criteria inuence the utility of a
project so, it is reasonable to have a portfolio of projects which
has a higher utility value. According to this objective, model tries
to select projects with a higher overall utility. In FGP, every goal
or constraint has an aspiration level which should be satised by
solutions approximately. These aspiration levels are derived by
managers. So, we can have this objective in this form:

Where, X = (x1, x2, . . . , xN) and wu, wf and wc are the relative importance weights of goals.
4. Model implementation
For proving the applicability of the model and illustration, we
applied the model in one of the leading companies in Iran. The rst
step to apply the model was to construct the decision team. We
constructed the decision team including top and middle managers:
strategic planning manager, nancial manager, engineering manager, quality control and insurance manager and process manager.
Then, we asked them to identify the assessment criteria and rate
the potential projects with respect to each criterion in the range
of [0, 10]. Decision team identied the criteria as mentioned in
Table 1.
4.1. Training ANFIS and obtaining the overall utility of projects
For training the ANFIS, we needed some experiences about the
system behavior. For this aim, we designed a questionnaire including different combinations of criteria and asked the decision team
to give a utility score to them if possible at all, based on their
knowledge about the system. But where the number of antecedents (criteria) is large, it is not practical to ask the decision team

725

A. Saghaei, H. Didehkhani / Expert Systems with Applications 38 (2011) 721728

Layer 1: Criteria

Layer 2: Membership functions

Layer 3: Rule block

Layer 4: Utilities

R1

Business
criteria (BC)

R2
Fuzzy partitions
Financial
criteria (FB)

Utility Score = w i * f i
i =1

Aij
Rn

Process
criteria (PI)

Fig. 1. Architecture of ANFIS for assessment of projects in six sigma.

Fig. 2. (a) Trained sub-ANFIS (I) surface: BC and business excellence-customer satisfaction. (b) Trained sub-ANFIS (II) surface: BC and ROI-Cost of appraisal.

726

A. Saghaei, H. Didehkhani / Expert Systems with Applications 38 (2011) 721728

Fig. 3. Trained sub-ANFIS (III) surface: PI and process variability and non value-added.

Fig. 4. Trained main ANFIS surface: overall utility and FBBC.

Table 3
Inputs (rates of projects) and outputs of ANFIS and sub-ANFISs.
Project code

CS

BE

SP

sub-ANFIS (1)
BC

ROI

RS

SP

sub-ANFIS (2)
FB

VC

NV

sub-ANFIS (3)
PI

ANFIS
Overall utility (OU)

A
B
C
D
E
F
G

5
3
8
5
4
7
2

5
8
6
6
6
6
4

6
3
7
2
7
7
4

5.2
4.5
7.2
4.7
5.2
6.7
3

5
4
6
5
3
5
6

4
5
5
6
6
6
3

3
2
7
2
8
7
2

4.45
3.95
5.9
4.8
4.5
5.55
4.65

7
9
4
4
4
6
5

8
3
8
7
8
5
7

7.3
7.2
5.2
4.9
5.2
5.7
5.6

4.72
4.23
5.65
4.19
4.23
5.17
3.51

to give a rate to different combination. For handling this problem,


we used three sub-ANFIS to derive business and customer satisfaction score (BC), nancial benets score (FB) and process improvement score (PI). After deriving these scores, we used them as the
inputs of main ANFIS. We generated 200 questions and derived
130 completed questions by decision team, as much as possible
for decision team to answer. We used 100 of them for training
the ANFIS and the rest (30) for checking and validation of the model. For rule generation, we used subtractive clustering where the
range of inuence, squash factor, acceptance ratio, and rejection
ratio were set at 0.5, 1.25, 0.5 and 0.15, respectively during the pro-

Table 4
Initial and optimal data of projects.
Project

NPV

Initial investment

Utility score

Value

Status

a
b
c
d
e
f
g

50000
33000
45000
75000
38000
55000
25000

11500
8000
12000
12700
10000
11500
10000

4.72
4.23
5.65
4.19
4.23
5.17
3.51

0
1
0
0
1
1
0

Rejected
Selected
Rejected
Rejected
Selected
Selected
Rejected

A. Saghaei, H. Didehkhani / Expert Systems with Applications 38 (2011) 721728

727

Fig. A1. Trend of errors during epochs.

cess of subtractive clustering. Figs. 14 show the surface of ANFIS


and sub-ANFIS (s) after training. The rate of projects with respect
to criteria and the output of ANFIS (overall utility of projects) have
been shown in Table 3. The training error and checking error of the
ANFIS were 0.09 and 0.14 respectively after 850 epochs. By increasing the number of epochs, we could have reached the less training
error, but the over-tting would occur (incremental trend of checking error).
The trained FIS includes 11 rules (clusters). Because by using
subtractive clustering, input space was categorized into 11 clusters. Each input has 11 Gaussian curve built-in membership functions. The modied rules have been shown in Appendix B.
4.2. Deriving the optimal portfolio of projects
After deriving overall utility score of projects, we can design and
solve the FGP model for obtaining the optimal portfolio. First, we
should introduce membership function for each goal according to
aspiration levels derived by managers. For instance, the membership function of budget goal is as below:

lc X

8
>
>
>
1
>
>
>
>
>
>
>
<
1
>
>
>
>
>
>
>
>
>
>
:0

if

N
P

tuned. In ANFIS, it is not important which category the criteria belong to, in spite of MCDM models. In this paper, we considered a
wide range of subjective and objective criteria affect the utility of
a six sigma project. We categorized them into three main categories. We used these criteria to derive the overall utility of projects
by ANFIS. Also, we developed a FGP model considering three main
goals to derive the optimal portfolio of project should be done. We
applied the proposed model in a leading company in Iran to illustrate the applicability of model. By using model results, company
could select an efcient portfolio of six sigma projects to handle
its problems considering the constraints of company such as budget and desired nancial benets level. For further researches,
model parameters such as NPV of projects and initial capital cost
can be considered fuzzy, as they are in nature, and by using a possibilistic models instead of FGP models, derive the efcient portfolio of projects.

Appendix A
See Fig. A1.

c i xi 6 B

i1
N
P

Appendix B
ci xi B

i1

ac

if

B6

N
P

ci xi 6 B ac

i1

if

N
P

ci xi P B ac

i1

Membership function of budget


Where, ac is the allowed tolerance of budget. Other needed data derived by decision team such as the predicted cost of projects, estimated nancial benet of projects. By applying Tiwari approach,
the transmitted crisp LP model was solved by LINGO. The results
have been shown in Table 4.
5. Conclusion
The selection of projects is one of the most challenging issues in
the eld of business and industries. In most situations, project
selection problem has been considered as a MCDM model, so models such as AHP, TOPSIS and SAW have been applied to solve this
problem. As mentioned in literature, there have been developed
some models for selecting projects in six sigma. But, where there
is no complete knowledge about the hierarchy of assessment and
the weights of criteria also where there are interrelations among
criteria, these models dont work well. In this paper to handle these
challenges, we developed an ANFIS model which is capable to be

Modied fuzzy rules of The ANFIS.


1. If (BC is MF1) and (FB is MF1) and (PI is MF1) then
0.5448BC + 2.47FB + 0.1944PI  2.641
2. If (BC is MF2) and (FB is MF2) and (PI is MF2) then
0.1489BC + 0.1781FB + 0.3153PI + 1.727
3. If (BC is MF3) and (FB is MF3) and (PI is MF3) then
0.4563BC + 0.006157FB + 0.3964PI  2.128
4. If (BC is MF4) and (FB is MF4) and (PI is MF4) then
2.348BC  0.3979FB + 0.505PI  1.126
5. If (BC is MF5) and (FB is MF5) and (PI is MF5) then
0.5105BC  0.3928FB + 1.017PI  8.055
6. If (BC is MF6) and (FB is MF6) and (PI is MF6) then
1.327BC + 1.228FB + 0.8612PI  13.26
7. If (BC is MF7) and (FB is MF7) and (PI is MF7) then
1.403BC + 0.1121FB + 1.116PI  4.658
8. If (BC is MF8) and (FB is MF8) and (PI is MF8) then
1.039BC + 0.6117FB + 1.225PI  6.917
9. If (BC is MF9) and (FB is MF9) and (PI is MF9) then
0.2265BC + 0.05FB  0.9442PI + 2.771
10. If (BC is MF10) and (FB is MF10) and (PI is MF10) then
0.1665BC + 0.336FB  1.569PI  13.84
11. If (BC is MF11) and (FB is MF11) and (PI is MF11) then
0.8563BC  0.7444FB + 0.8938PI + 4.054

OU =
OU =
OU =
OU =
OU =
OU =
OU =
OU =
OU =
OU =
OU =

728

A. Saghaei, H. Didehkhani / Expert Systems with Applications 38 (2011) 721728

Appendix C
Crisp LP model for deriving the optimal portfolio of projects

Kahraman, C., Ertay, T., & Buyukozkan, G. (2006). A fuzzy optimization model for
QFD planning process using analytic network approach. European Journal of
Operational Research, 171, 390411.
Kumar, U. D., Nowicki, D., Ramirez-Marquez, J. E., & Verma, D. (2008). On the
optimal selection of process alternatives in a six sigma implementation.
Internationl Journal of Production Economics, 111, 456467.

Max 0:5ku 0:3kf 0:2kc


11000x1 8000x2 9500x3 12700x4 10000x5 9000x6 10000x7 10000
s:t:
kc 6 1 
1000
0:07x1  0:43x2 1:03x3  0:47x4  0:33x5 0:79x6  1:07x7 0:25
ku 6
0:25
55000x1 33000x2 63000x3 75000x4 38000x5 65000x6 25000x7  50000
kf 6
5000
xi 2 f0; 1g; i 1; . . . ; 7

References
Adam, W. C., Gupta, P., & Wilson, C. E. (2003). Six sigma deployment. USA:
Butterworth-Heinemann.
Banuelas, R., Antony, J., & Brace, M. (2005). An application of six sigma to
reduce waste. Quality and Reliability Engineering International, 21(6),
553570.
Bellman, R., & Zadeh, L. A. (1970). Decision-making in a fuzzy environment.
Management Science, 17, 141164.
Chao, T. S., & Chia, J. C. (2008). A systematic methodology for the creation of six
sigma projects: A case study of semiconductor foundry. Expert Systems with
Applications, 34, 26932703.
Chiu, S. (1994). Fuzzy model identication based on cluster estimation. Journal of
Intelligent and Fuzzy Systems, 2(3), 267278.
Gryna, F. M., Chua, R. C. H., & Defeo, J. A. (2005). Jurans quality planning and analysis:
for enterprise quality. McGraw-Hill.
Jang, R. (1993). ANFIS: Adaptive-network-based fuzzy inference systems. IEEE
Transactions on Systems, Man, and Cybernetics, 23, 665685.
Jang, R., Sun, C. T., & Mizutani, E. (1996). Neuro-fuzzy and soft computing. Prentice
Hall.
Kahraman, C., & Bykzkan, G. (2008). A combined fuzzy AHP and fuzzy goal
programming approach for effective six-sigma project selection. Journal of
Multiple-Valued Logic and Soft Computing, 14(6).

Kumar, U. D., Saranga, U., Ramirez-Marquez, J. E., & Nowicki, D. (2007). Six sigma
project selection using data envelopment analysis. TQM magazine, 19(5),
419441.
Lanyon, S. (2003). At Raytheon six sigma works, too, to improve HR management
processes. Journal of Organizational Excellence, 22(4), 2942.
Mamdani, E. H. (1977). Application of fuzzy logic to approximate reasoning using
linguistic systems. Fuzzy Sets and Systems, 26, 11821191.
Robinson, B. (2005). Build a management system based on six sigma. ASQ six sigma
Forum Magazine, 5(1), 2834.
Roger, G. S., Linderman, K., Liedtke, C., & Choo, A. S. (2008). Six sigma: Denition and
underlying theory. Journal of Operations Management, 26, 536554.
Snee, R. D. (2002). Dealing with the Achilles heel of six sigma initiatives project
selection is key to success. Quality Progress, 34(3), 6669.
Takagi, T., & Sugeno, M. (1985). Fuzzy identication of systems and its application
to modeling and control. IEEE Transactions on Systems Man and Cybernetics,
15(1), 116132.
Tiwari, R. N., Dharmar, S., & Rao, J. R. (1987). Fuzzy goal programming An additive
model. Fuzzy Sets and Systems, 24, 2734.
Yager, R. R., & Filev, D. P. (1994). Approximate clustering via the mountain method.
IEEE Transactions on Systems Man and Cybernetics, 24(8), 12791284.
Yang, T., & Hsieh, T. H. (2008). Six-sigma project selection using national quality
award criteria and fuzzy multiple criteria decision-making method. In
Proceeding of WiCOM08 fourth international conference.

Das könnte Ihnen auch gefallen