You are on page 1of 18

This article was downloaded by: [Tamilnadu Agricultural Univ] On: 10 August 2013, At: 00:46 Publisher: Taylor

& Francis Informa Ltd Registered in England and Wales Registered Number: 1072954 Registered office: Mortimer House, 37-41 Mortimer Street, London W1T 3JH, UK

International Journal of Production Research


Publication details, including instructions for authors and subscription information: http://www.tandfonline.com/loi/tprs20

Fuzzy hybrid decision model for supplier evaluation and selection


Pandian Pitchipoo , Ponnusamy Venkumar & Sivaprakasam Rajakarunakaran
a a

Department of Mechanical Engineering , Kalasalingam University , Krishnankoil , Tamil Nadu , India Published online: 18 Mar 2013.

To cite this article: Pandian Pitchipoo , Ponnusamy Venkumar & Sivaprakasam Rajakarunakaran (2013) Fuzzy hybrid decision model for supplier evaluation and selection, International Journal of Production Research, 51:13, 3903-3919, DOI: 10.1080/00207543.2012.756592 To link to this article: http://dx.doi.org/10.1080/00207543.2012.756592

PLEASE SCROLL DOWN FOR ARTICLE Taylor & Francis makes every effort to ensure the accuracy of all the information (the Content) contained in the publications on our platform. However, Taylor & Francis, our agents, and our licensors make no representations or warranties whatsoever as to the accuracy, completeness, or suitability for any purpose of the Content. Any opinions and views expressed in this publication are the opinions and views of the authors, and are not the views of or endorsed by Taylor & Francis. The accuracy of the Content should not be relied upon and should be independently verified with primary sources of information. Taylor and Francis shall not be liable for any losses, actions, claims, proceedings, demands, costs, expenses, damages, and other liabilities whatsoever or howsoever caused arising directly or indirectly in connection with, in relation to or arising out of the use of the Content. This article may be used for research, teaching, and private study purposes. Any substantial or systematic reproduction, redistribution, reselling, loan, sub-licensing, systematic supply, or distribution in any form to anyone is expressly forbidden. Terms & Conditions of access and use can be found at http:// www.tandfonline.com/page/terms-and-conditions

International Journal of Production Research, 2013 Vol. 51, No. 13, 39033919, http://dx.doi.org/10.1080/00207543.2012.756592

Fuzzy hybrid decision model for supplier evaluation and selection


Pandian Pitchipoo*, Ponnusamy Venkumar and Sivaprakasam Rajakarunakaran
Department of Mechanical Engineering, Kalasalingam University, Krishnankoil, Tamil Nadu, India (Received 7 February 2012; nal version received 4 December 2012) This paper proposes a structured, integrated decision model for evaluating suppliers by combining the fuzzy analytical hierarchy process (FAHP) and grey relational analysis (GRA). The qualitative and partially-known information is incorporated in this decision model using the fuzzy set theory. In this proposed methodology, the weights of the evaluation criteria are calculated by using FAHP, then the ranking of the suppliers is determined by using GRA. Finally to show the robustness of the model, a sensitivity analysis is also performed. In this study, the supplier selection problem of an electroplating industry in the southern part of India was investigated, demonstrating the effectiveness of this developed integrated model. This model can help in solving the complex decision in supplier selection practice. The results generated from the model are properly validated and nally a systematic solution with decision support is provided for decision makers. This model can be integrated with other decision support systems of similar kinds of industries. Keywords: supplier selection; multi-criteria decision making; grey relational analysis; fuzzy analytic hierarchy process; hybrid model

Downloaded by [Tamilnadu Agricultural Univ] at 00:46 10 August 2013

1. Introduction Supplier selection is increasingly recognised as an important decision in both manufacturing and process industries. In most of the industries, the cost involved in the purchasing of materials is more than 50% of the total cost of production, and it was found that more than 30% of errors made during the manufacturing process were blamed on the supply of defective goods from a supplier (Anthony Inman 1992). To triumph over this problem, selecting the right supplier is essential. The identication of suppliers with the highest potential is essential for meeting a rms needs consistently and at an acceptable cost. Good suppliers allow enterprises to achieve good manufacturing performance and get the maximum benets for the business industry or for the rm. In industries, the procurement department often plays an important role in selecting appropriate suppliers and reducing purchasing costs. So supplier selection is the major inuencing factor in the purchasing process. The responsibility of the purchasing department is to identify the set of prospective suppliers, evaluate their performances, and then select the right supplier. The supplier selection problem naturally possesses various complicating elements that make it tough to solve. Regarding supplier selection, the literature shows a variety of research using conceptual, empirical study and decision support methods. Generally in supplier selection there are two important issues to be considered, one is which criteria should be considered, and the other one relates to what methods should be used. To solve the supplier selection problem scientically, an attempt is made in this paper to develop a hybrid decision model using FAHP and GRA for selecting the best supplier. This model will be illustrated with a case study in the electroplating industry. The organisation of the remainder of this paper is as follows: in Section 2, a review of the related literature in supplier evaluation and selection is given; Section 3 describes the problem and proposed framework; in Section 4 the model development and analysis are explained; and Section 5 presents the conclusions of the paper. 2. Literature review The literature in the following two categories was selected and reviewed: literature on supplier selection criteria and techniques, and literature on fuzzy-logic-based integrated models with analytic hierarchy process (AHP) and GRA applications.

*Corresponding author. Email: pitchipoo@klu.ac.in


2013 Taylor & Francis

3904

P. Pitchipoo et al.

2.1 Review of the literature on supplier selection criteria and techniques The identication of inuencing criteria for the evaluation and selection of suppliers has been the focus of many researchers. Dickson (1966) carried out a study with the help of a survey conducted in 300 business organisations. The purchasing managers of those organisations were requested to identify the factors that inuenced supplier selection. As an outcome of the survey, a total of 23 factors were identied as important factors for the supplier selection decision problem. Among these, quality, price, and delivery are the most critical factors in the supplier selection process. Ho, Xu, and Dey (2010) reviewed the literature related to the multi-criteria decision making approaches for supplier evaluation and selection appearing in international journals from 2000 to 2008. For supplier selection, various techniques were found in the literature, such as data envelopment analysis (DEA); mathematical programming linear programming, integer linear programming, and goal programming (GP); AHP; case-based reasoning (CBR); analytic network process (ANP); fuzzy set theory; genetic algorithm (GA); integrated AHP, DEA, and articial neural network; integrated AHP and GP; integrated AHP and GRA; and integrated fuzzy and AHP. Most of the literature is found to consider quality, delivery, and price/cost as the most popular criteria for supplier evaluation and selection. The outcome of this research provides evidence that multi-criteria decision-making approaches are better than the traditional cost-based approach, and it has helped researchers and decision makers in applying the approaches effectively. Athawale, Prasenjit, and Chakraborty (2010) presented a supplier selection model based on an outranking approach PROMETHEE II. Chatterjee, Poulami, and Shankar (2011) compared two multi-criteria decision-making approaches such as VIKOR and ELECTRE for supplier selection.

Downloaded by [Tamilnadu Agricultural Univ] at 00:46 10 August 2013

2.2 Review of the literature on the fuzzy-based integrated model in supplier selection Kahraman, Ufuk, and Ziya (2003) proposed FAHP to select the best supplier for a manufacturing rm. The criteria focused on in this paper are quality, delivery speed, capacity, reliability, maintainability, damage tolerance, handling, nancial strength, management approach, technical ability, quality systems, and service performance. Zaim, Mehmet, and Mehves (2003) proposed FAHP for solving the problem of supplier selection in a case study with TV production suppliers. The TV suppliers were evaluated and the best one was selected. Finally the results were compared with the conventional AHP approach. Tsai, Chang, and Chen (2003) evaluated the vendors of a manufacturing industry using the GRA model. The quality of the product, price, and delivery date were considered as evaluation criteria. Vaidya and Kumar (2006) presented a comprehensive review of the literature regarding the application of AHP as a multi-criteria decision-making tool. Haq and Kannan (2006) compared the two supplier selection models AHP and FAHP in a case study. For their study, quality, delivery, production capability, service, engineering/technical capability, business structure, and price were taken as decision criteria and they proposed the model for a rubber tubes industry in India. Yang and Chen (2006) determined the weights of evaluation criteria such as quality, nance, customer service, cost, delivery, and the turnover of various suppliers for a notebook computer manufacturer using AHP. The nal ranking of those suppliers was determined by GRA. Benyoucef and Canbolat (2007) proposed a supplier selection system based on AHP integrated with fuzzy concepts and empirical data. The case study was conducted in a hospital to validate the design of the supplier selection system and its underlying FAHP model. AHP is insufcient in real world situations with uncertain conditions, and sometimes decision makers are not able to give all decisions in exact numerical value. In these situations, FAHP may be preferred to rectify the disadvantages of AHP (Chan and Kumar 2007). Chan et al. (2008) discussed FAHP to efciently tackle both quantitative and qualitative decision factors involved in the selection of global suppliers in current business scenarios. The triangular fuzzy numbers are used to transform the linguistic comparison of the different decision criteria, sub-criteria, and performance of the alternative suppliers. Ketata, Mahmoud, and Romdhan (2008) proposed a new approach based on the integration of fuzzy logic with classical multicriteria methods such as the FAHP process and GP methods. A numerical example was presented to illustrate the new approach which includes comparing the advantages and disadvantages of the selection methods for resolving a supplier selection and evaluation problem. Hua (2008) presented an evaluating method for vendor selection based on the AHP and fuzzy logic method. For the evaluation, the criteria cost (production cost, transportation cost, and transaction cost), quality (qualied rate, development quality, and customer complaint rate), services (delivery accuracy, response ability, and order ll rate), and enterprise quality (enterprise credit, nancial status, and development prospects) were considered. Yuan et al. (2008) proposed an integrated model to evaluate the overall performance of suppliers of a manufacturing company. The integrated method was developed by modifying the DEA method into a weighting constrained DEA method using a triangular weighting fuzzy set. Finally it was concluded that the new integrated method rectied the weaknesses of the traditional DEA method in weight calculation. Li, Yamaguchi, and Nagai (2008) proposed a GRA model to evaluate and select suppliers based on qualitative attributes such as product quality and service, as well as quantitative attributes such as delivery and price.

International Journal of Production Research

3905

Wang, Cheng, and Huang (2009) proposed a fuzzy hierarchical TOPSIS method to simplify the complicated metric distance method (Chen and Cheng 2005) and modify the TOPSIS method (Chen 2000) for application in supplier selection. The nal verication was also presented with a numerical example by comparing the solution obtained with other methods. Lee, Kang and Chang (2009) developed a fuzzy multiple goal programming (FMGP) model to select thin lm transistor liquid crystal display (TFT-LCD) suppliers. First FAHP was applied to analyse the importance of multiple factors by incorporating experts opinions. Then multi-choice goal programming was used to consider the limits of various resources and to formulate the constraints. Lee, Kang and Chang (2009) developed a model for evaluating green suppliers. The rst Delphi method was applied to differentiate the criteria for evaluating traditional suppliers and green suppliers. Next a hierarchy was developed to evaluate the importance of the selected criteria and the performance of green suppliers. Finally the vagueness of experts opinions was rectied by the fuzzy extended analytic hierarchy process. Chamodrakas, Batis, and Martakos (2010) suggested the fuzzy preference programming (FPP) approach for decision support enabling effective supplier selection processes in electronic marketplaces. The evaluation was done in two stages. First an initial screening of suppliers through the enforcement of hard constraints on selection criteria was performed. Next the nal supplier evaluation was completed through the application of a modied variant of the FPP method. The proposed method was demonstrated with the example of a hypothetical metal manufacturing company that selected the supplier in the environment of an electronic marketplace. Kuo, Lee, and Hu (2010) developed a performance evaluation method, which integrates both the FAHP method and fuzzy data envelopment analysis (FDEA) for the supplier selection decision. The FAHP method was rst applied to nd indicators weights through an expert questionnaire survey. Then, these weights were integrated with FDEA. The proposed method was proved with a case study on an auto lighting company. Sen, Sen, and Baslgil (2010) focused on the prequalication of potential suppliers, and the weights of the pre-selected decision criteria were determined by the fuzzy analytic hierarchy process. The outputs of the previous phases, namely problem denition and formulation of criteria, were used as inputs in this methodology. This information supported the decision makers in making the nal selection with effective alternative choices. The application of this methodology was demonstrated in audio electronics in Turkeys electronics industry. Mohammady and Amid (2010) presented a decision-making framework for supplier selection using the fuzzy VIKOR method combined with FAHP. The model was proved by a case study performed in a virtual training and automation services organisation. Azzeh, Neagu, and Cowling (2010) developed a hybrid model using fuzzy set theory with GRA for the accurate and credible estimation of software effort for a software industry. To overcome the challenge of vague and imprecise human judgment, fuzzy-based GRA was proposed. Finally, the results were compared with the results obtained using case-based reasoning, multiple linear regression, and articial neural networks methods. Omid and Khakzar (2011) proposed a supplier selection model to select the best supplier of maize starch in a pharmacy company in Iran. To evaluate the suppliers, criteria such as price, quality, service, and technical issues were used. In this paper FAHP is used for selecting the best supplier. Ozcan and Suzan (2011) developed an FAHP supplier selection model for a washing machine company located in Turkey. For the evaluation of the suppliers, criteria such as price, product quality, lead time, technical support, nancial status, management, technical ability, quality systems, geographical location, production facility, handling, and capacity were used. First, the attributes were dened to design the hierarchy structure. Then the weights of them and alternatives were calculated using the FAHP approach. Finally, the supplier with the highest priority weight was selected as the best supplier. Zeydan, Colpan, and Cobanoglu (2011) considered both qualitative and quantitative variables for the evaluation and selection of suppliers based on efciency and effectiveness in a car manufacturing factory in Turkey. In the rst stage, qualitative performance evaluation was performed by using FAHP to nd the criteria weights, and then fuzzy was used to rank the suppliers. In the second stage, DEA was used to evaluate the quantitative criteria. Punniyamoorthy, Mathiyalagan, and Parthiban (2011) made an attempt to develop a composite model for supplier selection using structural equation modelling and FAHP. The suppliers were evaluated based on criteria such as management and organisation, quality, technical capability, production facilities and capacities, nancial position, delivery, service, relationship, safety, and environment concern and cost. Khaled et al. (2011) provided four different multi-criteria decision-making approaches such as the linear weighted method, categorical method, AHP, and FAHP to select the best supplier. This model was explained with a case study conducted in a manufacturing rm to select the best supplier among three suppliers by considering quality, price, service, production capacity, business structure, and delivery. Nilay Yucenur, Vayvay, and Demirel (2011) proposed a model for selecting a global supplier using FAHP and the fuzzy analytical network process (FANP) based on linguistic variables. Those methodologies used to evaluate different decision criteria such as service quality, cost, risk factors, and supplier characteristics involved in the selection of the best supplier in a global supply chain. Finally the FAHP and FANP results were compared. Zhang and Liu (2011) developed a new method for solving the personnel selection decision-making process by combining the fuzzy entropy method with grey relational analysis. Fuzzy entropy was used to obtain the entropy weights of the criteria. GRA was applied to the ranking and selection of alternatives.

Downloaded by [Tamilnadu Agricultural Univ] at 00:46 10 August 2013

3906

P. Pitchipoo et al.

Chen, Kuo, and Luo (2011) focused on the issue of supply chain performance evaluation of the wafer testing house in Taiwan. This evaluation was performed by using FAHP and GRA. FAHP was used to derive the weights of inuential indicators. GRA was used to evaluate the performance between the two kinds of markets. Pitchipoo, Venkumar, and Rajakarunakaran (2012) constructed a distinct hybrid model for the supplier selection process by integrating AHP and GRA. First the mutual information-based feature selection method was used to select the highly inuencing criteria and then the weights of the selected criteria were calculated using AHP. Finally the best supplier was selected using GRA. 3. Proposed supplier evaluation and selection framework In this work, various issues were considered related to the evaluation and selection of a supplier for an electroplating industry functioning for more than 15 years. The major activities carried out in this industry are nickel and chrome coating for auto components. The existing methodology adopted for supplier selection based on the sealed bid technique is that the supplier who quotes the least amount is given the order. The major drawback of the existing approach, which was followed for the supplier selection process, is that there is ample scope for receiving inferior-quality products with sustainable delay getting the goods at the right time. To overcome the problem, supplier evaluation is carried out based on performance assessment criteria, manufacturing criteria, quality system assessment criteria, and business factors. Table 1 shows the merits and drawbacks of the various supplier evaluation approaches available in the literature. Due to more merits, the hybrid fuzzy AHPGRA model was proposed for supplier evaluation and selection. Figure 1 shows the proposed framework for supplier evaluation and selection which will be used in this study. This framework contains three modules: Module I: Computation of weights using FAHP Module II: Ranking of alternatives using GRA Module III: Sensitivity analysis Module I: Computation of weights using FAHP This module begins with the determination of the objective and choosing possible alternatives and inuencing criteria for this study. The data related to this study such as number of alternatives (suppliers), number of decision criteria, and opinions of decision makers were collected from the industry in which the case study was performed. Based on the judgment obtained from the decision maker, a set of pairwise comparisons between the decision criteria, which is known as the original matrix, were constructed by using Saatys (1990) nine-point measurement scale. The original matrix was converted into a fuzzy original matrix using triangular fuzzy numbers. This fuzzy original matrix was normalised and is called the fuzzy adjusted matrix. Then the consistency of the developed model was checked. From the fuzzy adjusted matrix, the weights of the criteria were determined. After that, the suppliers were compared based on each criterion and the supplier matrixes were formulated. These supplier matrixes were normalised to develop the supplier adjusted matrix. Finally the overall score of the suppliers based on each criterion was computed. Module II: Ranking of alternatives using GRA This module starts with the formulation of a referential series based on the determination of overall priority after defuzzication. From the referential series the grey relational coefcient is computed. Finally the degree of grey equation coefcient for each alternative is determined. From the degree of grey equation coefcient, the higher degree of coefcient is ranked as 1 and, based on this, the best supplier is determined. The application of GRA not only integrates qualitative and quantitative data but also considers its characteristic larger is better or smaller is better. The important advantage of using GRA is that it can generate satisfying outcomes using a relatively small amount of data with greater variability in factors.

Downloaded by [Tamilnadu Agricultural Univ] at 00:46 10 August 2013

Module III: Sensitivity analysis In this module the robustness of the developed model is checked by using a sensitivity analysis. Sensitivity analysis is a technique used to determine how different values of an independent variable will carry an impact on a particular dependent variable under a given set of assumptions. Sensitivity analysis is used to investigate the robustness of a study when the study includes some form of statistical modelling. Sensitivity analysis supports the decision makers in the following:

Downloaded by [Tamilnadu Agricultural Univ] at 00:46 10 August 2013

Table 1. Merits and drawbacks of various supplier evaluation approaches. ELECTRE & PROMETHEE & VIKOR approaches

Salient features GRA AHP

Simple additive weight (SAW) and weighted point model (WPM) methods

Proposed model (hybrid fuzzy AHPGRA)

Merits


It is an effective tool where limited data are available. It can be used to evaluate quantitative data.

Easy to compute. It can be used to evaluate quantitative data.


Ability to handle problems which cannot be handled by mathematical models. Ability to mix qualitative and quantitative criteria in the same decision framework Can handle more criteria.

Ability to use the criteria in their own units. Can be programmable.

Able to evaluate under vague and uncertain conditions. Ability to mix qualitative and quantitative criteria. Can be programmable. Adoption of linguistic variables is possible. Can handle more criteria.

International Journal of Production Research

Drawbacks


Adoption of linguistic variables is difcult. Not able to evaluate qualitative data.

Adoption of linguistic variables is difcult. Not able to evaluate qualitative data. Not able to use the criteria in their own units. No solution with equal weights.

Requires high level of management involvement. Not able to evaluate under uncertainty.

Not able to evaluate under vagueness and uncertainty.

Time consuming.

3907

3908

P. Pitchipoo et al.
Determine objective and choose alternatives and criteria

Collection of linguistic decisions

Data collection

Quantitative data

Formulation of pairwise comparison (crisp) matrix for criteria

Conversion into fuzzy matrix

If no

Determination of normalised matrix

Check for consistency

Downloaded by [Tamilnadu Agricultural Univ] at 00:46 10 August 2013

Module I

If yes Formulation of supplier (crisp) based on each criterion Determination of criteriaweights Module II

Conversion into fuzzy matrix

Determination of weights of suppliers

Defuzzification Determination of overall priority

Generation of referential series Module III

Sensitivity analysis

Determination of grey relational coefficient

Determination of grey relational grade

Determination of best supplier

Figure 1. Framework of supplier selection.

Identication of critical assumptions Comparison of alternative model structures Guiding in future data collection Detecting important criteria Optimisation of uncertainty in parameters Model simplication

4. Model development and analysis The structure of the decision model consists of ve alternatives (suppliers). The evaluation criteria considered in this study are performance assessment criteria: cost (C), quality (Q), and delivery lead time (D); manufacturing criteria: production capacity (Ca); quality system assessment criteria: warranty given on the material (W); and business factors:

International Journal of Production Research

3909

reputation or brand image of the supplier (R) and nancial position of the supplier (FP). Each alternative is evaluated based on each decision criterion. 4.1 Module I: Computation of weights using FAHP AHP is one of the extensively used multi-criteria decision-making methods. AHP reects the humans natural behaviour and thoughts. AHP is an effective tool which can handle both qualitative and quantitative data. AHP involves the principles of decomposition, pairwise comparisons, and priority generation. The most important disadvantage of using AHP is that it uses a scale of one to nine which cannot handle uncertainty decisions in comparison of the attributes. All comparisons during AHP implementations may not include certainty, therefore the decision maker needs more than a nine-point scale to describe the uncertainty. In real world situations much information is available in vague and incomplete form. Sometimes the decision maker may not express preferences accurately. Therefore, in order to make realistic decisions, concepts of fuzzy logic can be applied in such cases. The concept of a linguistic variable is very useful when the system is too complex or not able to dene reasonable quantitative expressions (Zadeh 1965). Linguistic variables and triangular fuzzy numbers (TFN) can be used to decide the priority of one decision variable over another. Fuzzy logic can be used to make evaluations by linguistic statement (Bevilacqua, Ciarapica, and Giacchetta 2006). FAHP is the extension of AHP to efciently handle fuzziness in the decision process to select the best supplier by using both qualitative and quantitative data in multi-criteria decision-making problems. In this approach, TFN are used in place of the nine-point scale in traditional AHP. The FAHP procedure starts with the formation of an original crisp matrix. 4.1.1 Formulation of original matrix The numerical as well as the linguistic decisions on the comparison of criteria were collected from the industry. Based on the judgment obtained from the decision maker, the evaluation criteria were compared. The ranking of evaluation criteria was collected from decision makers in the purchasing department of that industry. First the criteria matrix was formed based on Saatys nine-point scale which is shown in Table 2. The criteria matrix is shown in Table 3. This was converted into a fuzzy original matrix using TFN prescribed by Alias, Siti Zaiton, and Supiah (2009), which is also shown in Table 2. The fuzzy number in a fuzzy set can be represented by Equation (1). F fx; lF x; x 2 Rg 1

Downloaded by [Tamilnadu Agricultural Univ] at 00:46 10 August 2013

where F is a fuzzy set; x is a fuzzy number; R : 1 x 1 and F(x) is a continuous mapping from R in the interval [0, 1]. A TFN expresses the relative strength of each pair of elements in the same hierarchy, denoted as TFN (M) = (l, m, u) where l m u in which l is the smallest possible value, m is the most promising value, and u is the largest possible value in a fuzzy event (Kaufmann and Gupta 1991). The triangular membership function of M fuzzy number can be described in Equation (2) 8 0 x\l > > < x l =m l l x l lA x f x u x=u m m x u > > : 0 x[u
Table 2. Measurement scale for pairwise comparison. Verbal judgment or preference Extremely preferred Very strongly to extremely preferred Very strongly preferred Strongly to very strongly preferred Strongly preferred Moderately to strongly preferred Moderately preferred Equally to moderately preferred Equally preferred Saatys scale of relative importance 9 8 7 6 5 4 3 2 1 Triangular fuzzy numbers 9,9,9 7,8,9 6,7,8 5,6,7 4,5,6 3,4,5 2,3,4 1,2,3 1,1,1

3910 Table 3. Original crisp matrix. C C Q D W Ca R FP Total 1.000 3.000 0.330 0.200 0.250 0.167 0.200 5.147 Q 0.330 1.000 0.200 0.167 0.143 0.167 0.143 2.150 D

P. Pitchipoo et al.

W 5.000 6.000 3.000 1.000 0.500 0.333 0.250 16.083

Ca 4.000 7.000 4.000 2.000 1.000 0.333 0.333 18.666

R 6.000 6.000 5.000 3.000 3.000 1.000 0.500 24.500

FP 5.000 7.000 4.000 4.000 3.000 2.000 1.000 26.000

3.000 5.000 1.000 0.333 0.250 0.200 0.250 10.033

The original fuzzy matrix is shown in Table 4. Then the fuzzy original matrix is normalised using Equation (3).

Downloaded by [Tamilnadu Agricultural Univ] at 00:46 10 August 2013

Nij

aij Tj

P where aij is the cell value of the ith row and jth column in the fuzzy original matrix; 1 i; j m; and Tj m i1 aij. The fuzzy adjusted matrix is shown in Table 5. The weights were calculated by converting fuzzy numbers into crisp values by using the defuzzication technique. The defuzzication has the capability to reduce a fuzzy to a crisp singlevalued quantity. There are seven methods used for the defuzzication of fuzzy output functions, including the maxmembership principle, centroid method, weighted average method, meanmax membership, centre of sums, centre of largest area, and rst of maxima or last of maxima. In this study, the centroid method was used for defuzzication, which is given in Equation (4). Pk Weights Crisp valueWi Pk
i 1

Dip oi Dip

i 1

where k is the number of rules, Oi is the class generated by rule i (from 0, 1, . L-1); L is the number of classes; and Dip is determined by the product over mli from i = 1 to n. Dip
n Y i 1

mli

where n is the number of inputs; and mli is the membership grade of feature l in the fuzzy regions that occupy the ith rule. 4.1.2 Consistency checking Since the pairwise comparison matrix is formulated by the values collected from the decision maker of the industry, it is necessary to ensure that the values collected are accepted values by the literature and expert. To check the consistency, the consistency ratio (CR) is calculated using Equation (6) CR CI =RI 6

where CI is the consistency index which is determined using Equation (7) and RI is the random index for criteria size m. CI kmax m m 1 7

where kmax is the maximum eigenvalue and m is the number of criteria.

Downloaded by [Tamilnadu Agricultural Univ] at 00:46 10 August 2013

Table 4. Original fuzzy matrix. Q 0.330 1.000 0.200 0.167 0.143 0.167 0.143 2.150 0.250 1.000 0.167 0.143 0.125 0.143 0.125 1.953 2.000 4.000 1.000 0.500 0.333 0.250 0.333 8.416 3.000 5.000 1.000 0.333 0.250 0.200 0.250 10.033 4.000 6.000 1.000 0.250 0.200 0.167 0.200 11.817 4.000 5.000 2.000 1.000 1.000 0.500 0.333 13.833 5.000 6.000 3.000 1.000 0.500 0.333 0.250 16.083 6.000 7.000 4.000 1.000 0.333 0.250 0.200 18.783 3.000 6.000 3.000 1.000 1.000 0.500 0.500 15.000 4.000 7.000 4.000 2.000 1.000 0.333 0.333 18.666 5.000 8.000 5.000 3.000 1.000 0.250 0.250 22.500 5.000 5.000 4.000 2.000 2.000 1.000 1.000 20.000 6.000 6.000 5.000 3.000 3.000 1.000 0.500 24.500 7.000 7.000 6.000 4.000 4.000 1.000 0.333 29.333 4.000 6.000 3.000 3.000 2.000 1.000 1.000 20.000 D W Ca R FP 5.000 7.000 4.000 4.000 3.000 2.000 1.000 26.000 6.000 8.000 5.000 5.000 4.000 3.000 1.000 32.000

C Q D W Ca R FP Total

1.000 2.000 0.500 0.250 0.333 0.200 0.250 4.533

1.000 3.000 0.330 0.200 0.250 0.167 0.200 5.147

1.000 4.000 0.250 0.167 0.200 0.143 0.167 5.927

0.500 1.000 0.250 0.200 0.167 0.200 0.167 2.484

International Journal of Production Research

Table 5. Fuzzy adjusted matrix. Q 0.153 0.465 0.093 0.078 0.067 0.078 0.067 0.128 0.512 0.086 0.073 0.064 0.073 0.064 0.238 0.475 0.119 0.059 0.040 0.030 0.040 0.299 0.498 0.100 0.033 0.025 0.020 0.025 0.338 0.508 0.085 0.021 0.017 0.014 0.017 0.289 0.361 0.145 0.072 0.072 0.036 0.024 0.311 0.373 0.187 0.062 0.031 0.021 0.016 D W 0.319 0.373 0.213 0.053 0.018 0.013 0.011 0.200 0.400 0.200 0.067 0.067 0.033 0.033 Ca 0.214 0.375 0.214 0.107 0.054 0.018 0.018 0.222 0.356 0.222 0.133 0.044 0.011 0.011 0.250 0.250 0.200 0.100 0.100 0.050 0.050 R 0.245 0.245 0.204 0.122 0.122 0.041 0.020 0.239 0.239 0.205 0.136 0.136 0.034 0.011 0.200 0.300 0.150 0.150 0.100 0.050 0.050 FP 0.192 0.269 0.154 0.154 0.115 0.077 0.038 0.188 0.250 0.156 0.156 0.125 0.094 0.031 Row Average 0.229 0.398 0.145 0.085 0.068 0.042 0.034

C Q D W Ca R FP

0.221 0.441 0.110 0.055 0.073 0.044 0.055

0.194 0.583 0.064 0.039 0.049 0.032 0.039

0.169 0.675 0.042 0.028 0.034 0.024 0.028

0.201 0.403 0.101 0.081 0.067 0.081 0.067

3911

3912

P. Pitchipoo et al.

RI was approximated by Saaty (1990) which is shown in Table 6. If the CR is <0.10 the decision maker s pairwise comparison matrix is acceptable. For the model selected for this study, the consistency ratio was calculated as 0.0967 which is less than 0.1. Thus this model is acceptable. 4.1.3 Determination of fuzzy supplier matrix After checking the consistency, the suppliers were compared with each other based on all selected criteria which are shown in Tables 7, 9, 11, 13, 15, 17, and 19. Then these fuzzy matrixes were normalised and shown in Tables 8, 10, 12, 14, 16, 18, and 20. 4.1.4 Determination of criteria weights The weights of all criteria were computed by the nal fuzzy scores which were calculated by multiplying the weight of the supplier with the weight of the criteria. The weights of the criteria for all suppliers are shown in Table 21.

Downloaded by [Tamilnadu Agricultural Univ] at 00:46 10 August 2013

Table 6. Random indices. m RI 1 0 2 0 3 0.58 4 0.90 5 1.12 6 1.24 7 1.32 8 1.41 9 1.45 10 1.49 11 1.51 12 1.58

Table 7. Fuzzy supplier matrix: Based on cost. S1 S 1 1.000 1.000 1.000 S 2 0.250 0.200 0.167 S 3 0.167 0.143 0.125 S 4 0.111 0.111 0.111 S 5 9.000 9.000 9.000 Net 10.528 10.454 10.403 S2 S3 S4 0.111 0.250 0.250 0.111 1.000 1.722 S5 0.111 0.200 0.200 0.111 1.000 1.622 0.111 0.167 0.167 0.111 1.000 1.556

4.000 5.000 6.000 6.000 7.000 8.000 9.000 9.000 9.000 1.000 1.000 1.000 2.000 3.000 4.000 6.000 7.000 8.000 0.500 0.333 0.250 1.000 1.000 1.000 4.000 5.000 6.000 0.167 1.430 0.125 0.250 0.200 0.167 1.000 1.000 1.000 4.000 5.000 6.000 4.000 5.000 6.000 9.000 9.000 9.000 9.667 12.763 13.375 13.250 16.200 19.167 29.000 31.000 33.000

Table 8. Fuzzy adjusted supplier matrix: Based on cost. S1 S S S S S 1 2 3 4 5 0.095 0.024 0.016 0.011 0.855 0.096 0.019 0.014 0.011 0.861 0.096 0.016 0.012 0.011 0.865 0.414 0.103 0.052 0.017 0.414 S2 0.392 0.078 0.026 0.112 0.392 0.449 0.075 0.019 0.009 0.449 0.453 0.151 0.075 0.019 0.302 S3 0.432 0.185 0.062 0.012 0.309 0.417 0.209 0.052 0.009 0.313 0.310 0.207 0.138 0.034 0.310 S4 0.290 0.226 0.161 0.032 0.290 0.273 0.242 0.182 0.030 0.273 0.064 0.145 0.145 0.064 0.581 S5 0.068 0.123 0.123 0.068 0.617 Score 0.071 0.353295 0.107 0.16798 0.107 0.118084 0.071 0.04753 0.643 0.590435

Table 9. Fuzzy supplier matrix: Based on quality. S1 S1 S2 S3 S4 S5 Net 1.000 0.167 0.111 0.250 0.500 2.028 1.000 0.143 0.111 0.200 0.333 1.787 1.000 0.125 0.111 0.167 0.250 1.653 6.000 1.000 0.250 2.000 4.000 13.250 S2 7.000 1.000 0.200 3.000 5.000 16.200 8.000 1.000 0.170 4.000 6.000 19.170 9.000 4.000 1.000 4.000 6.000 24.000 S3 9.000 5.000 1.000 5.000 7.000 27.000 9.000 6.000 1.000 6.000 8.000 30.000 4.000 0.500 0.250 1.000 2.000 7.750 S4 5.000 0.333 0.200 1.000 3.000 9.533 6.000 0.250 0.167 1.000 4.000 11.417 2.000 0.250 0.167 0.500 1.000 3.917 S5 3.000 0.200 0.134 0.333 1.000 4.667 4.000 0.167 0.125 0.250 1.000 5.542

International Journal of Production Research Table 10. Fuzzy adjusted supplier matrix: Based on quality. S1 S S S S S 1 2 3 4 5 0.493 0.082 0.055 0.123 0.247 0.560 0.080 0.062 0.112 0.186 0.605 0.076 0.067 0.101 0.151 0.453 0.075 0.019 0.151 0.302 S2 0.432 0.062 0.012 0.185 0.309 0.417 0.052 0.009 0.209 0.313 0.375 0.167 0.042 0.167 0.250 S3 0.333 0.185 0.037 0.185 0.259 0.300 0.200 0.033 0.200 0.267 0.516 0.065 0.032 0.129 0.258 S4 0.524 0.035 0.021 0.105 0.315 0.526 0.022 0.015 0.088 0.350 0.511 0.064 0.043 0.128 0.255 S5 0.643 0.043 0.029 0.071 0.214 0.722 0.030 0.023 0.045 0.180

3913

Score 0.514178 0.115967 0.041133 0.146334 0.265409

Table 11. Fuzzy supplier matrix: Based on delivery. S1 S2 1.000 8.000 6.000 0.170 4.000 19.170 0.167 1.000 0.500 0.167 0.220 2.054 0.143 1.000 0.333 0.143 0.200 1.819 0.125 1.000 0.250 0.125 0.170 1.670 0.250 2.000 1.000 0.167 0.500 3.917 S3 0.200 3.000 1.000 0.143 0.333 4.676 0.170 4.000 1.000 0.125 0.250 5.545 4.000 6.000 6.000 1.000 6.000 23.000 S4 5.000 7.000 7.000 1.000 7.000 27.000 6.000 8.000 8.000 1.000 8.000 31.000 0.500 4.500 2.000 0.167 1.000 8.167 S5 0.333 5.000 3.000 0.143 1.000 9.476 0.250 6.000 4.000 0.125 1.000 11.375

Downloaded by [Tamilnadu Agricultural Univ] at 00:46 10 August 2013

S1 S2 S3 S4 S5 Net

1.000 6.000 4.000 0.250 2.000 13.250

1.000 7.000 5.000 0.200 3.000 16.200

Table 12. Fuzzy adjusted supplier matrix: Based on delivery. S1 S S S S S 1 2 3 4 5 0.075 0.453 0.302 0.019 0.151 0.062 0.432 0.309 0.012 0.185 0.052 0.417 0.313 0.009 0.209 0.081 0.487 0.243 0.081 0.107 S2 0.079 0.550 0.183 0.079 0.110 0.075 0.599 0.150 0.075 0.102 0.064 0.511 0.255 0.043 0.128 S3 0.043 0.642 0.214 0.031 0.071 0.031 0.721 0.180 0.023 0.045 0.174 0.261 0.261 0.043 0.261 S4 0.185 0.259 0.259 0.037 0.259 0.194 0.258 0.258 0.032 0.258 0.061 0.551 0.245 0.020 0.122 S5 0.035 0.528 0.317 0.015 0.106 Score 0.022 0.1161 0.527 0.512624 0.352 0.264383 0.011 0.050811 0.088 0.17613

Table 13. Fuzzy supplier matrix: Based on warranty. S1 S1 S2 S3 S4 S5 Net 1.000 0.143 0.143 0.200 0.167 1.653 1.000 0.125 0.125 0.167 0.143 1.560 1.000 0.111 0.111 0.143 0.125 1.490 S2 7.000 8.000 9.000 1.000 1.000 1.000 1.000 1.000 1.000 0.167 0.143 0.125 0.143 0.125 0.111 9.310 10.268 11.236 S3 S4 S5

7.000 8.000 9.000 5.000 6.000 7.000 6.000 7.000 8.000 1.000 1.000 1.000 6.000 7.000 8.000 7.000 8.000 9.000 1.000 1.000 1.000 6.000 7.000 8.000 7.000 8.000 9.000 0.167 0.143 0.125 1.000 1.000 1.000 0.200 0.167 0.143 0.143 0.125 0.111 5.000 6.000 7.000 1.000 1.000 1.000 9.310 10.268 11.236 23.000 27.000 31.000 21.200 24.167 27.143

Table 14. Fuzzy adjusted supplier matrix: Based on warranty. S1 S S S S S 1 2 3 4 5 0.605 0.087 0.087 0.121 0.101 0.641 0.080 0.080 0.107 0.092 0.671 0.074 0.074 0.096 0.084 0.752 0.107 0.107 0.018 0.015 S2 0.779 0.097 0.097 0.014 0.012 0.801 0.089 0.089 0.011 0.010 0.752 0.107 0.107 0.018 0.015 S3 0.779 0.097 0.097 0.014 0.012 0.801 0.089 0.089 0.011 0.010 0.217 0.261 0.261 0.043 0.217 S4 0.222 0.259 0.259 0.037 0.222 0.226 0.258 0.258 0.032 0.226 0.283 0.330 0.330 0.009 0.047 S5 0.290 0.331 0.331 0.007 0.041 0.295 0.332 0.332 0.005 0.037 Score 0.64691 0.233616 0.233616 0.074622 0.156947

3914 Table 15. Fuzzy supplier matrix: Based on capacity. S1 S1 S2 S3 S4 S5 Net 1.000 5.000 6.000 5.000 9.000 26.000 S2

P. Pitchipoo et al.

S3 0.167 0.250 1.000 0.250 4.000 5.667 0.143 0.200 1.000 0.200 5.000 6.543

S4 0.125 0.200 0.167 0.143 0.167 1.000 1.000 1.000 1.000 4.000 5.000 6.000 0.167 1.000 1.000 1.000 6.000 5.000 6.000 7.000 7.459 11.200 13.167 15.143 0.111 0.200 0.250 0.200 1.000 1.761

S5 0.111 0.167 0.200 0.167 1.000 1.645 0.111 0.143 0.167 0.143 1.000 1.564

1.000 1.000 0.200 0.167 0.143 6.000 7.000 1.000 1.000 1.000 7.000 8.000 4.000 5.000 6.000 6.000 7.000 1.000 1.000 1.000 9.000 9.000 5.000 6.000 7.000 29.000 32.000 11.200 13.167 15.143

Table 16. Fuzzy adjusted supplier matrix: Based on capacity. S1 S2 0.031 0.219 0.250 0.219 0.281 0.018 0.089 0.357 0.089 0.446 0.013 0.076 0.380 0.076 0.456 0.009 0.066 0.396 0.066 0.462 0.029 0.044 0.176 0.044 0.706 S3 0.022 0.031 0.153 0.031 0.764 0.017 0.022 0.134 0.022 0.804 0.018 0.089 0.357 0.089 0.446 S4 0.013 0.076 0.380 0.076 0.456 0.009 0.066 0.396 0.066 0.462 0.063 0.114 0.142 0.114 0.568 S5 0.067 0.102 0.122 0.102 0.608 0.071 0.091 0.107 0.091 0.639 Score 0.043553 0.133015 0.300118 0.133015 0.561717

Downloaded by [Tamilnadu Agricultural Univ] at 00:46 10 August 2013

S S S S S

1 2 3 4 5

0.038 0.192 0.231 0.192 0.346

0.034 0.207 0.241 0.207 0.310

Table 17. Fuzzy supplier matrix: Based on reputation. S1 S1 S2 S3 S4 S5 Net 1.000 1.000 0.250 1.000 0.250 3.500 1.000 1.000 0.200 1.000 0.200 3.400 1.000 1.000 0.167 1.000 0.167 3.334 1.000 1.000 0.250 1.000 0.250 3.500 S2 1.000 1.000 0.200 1.000 0.200 3.400 1.000 1.000 0.167 1.000 0.167 3.334 4.000 4.000 1.000 4.000 1.000 14.000 S3 5.000 5.000 1.000 5.000 1.000 17.000 6.000 6.000 1.000 6.000 1.000 20.000 1.000 1.000 0.250 1.000 0.250 3.500 S4 1.000 1.000 0.200 1.000 0.200 3.400 1.000 1.000 0.167 1.000 0.167 3.334 4.000 4.000 1.000 4.000 1.000 14.000 S5 5.000 5.000 1.000 5.000 1.000 17.000 6.000 6.000 1.000 6.000 1.000 20.000

Table 18. Fuzzy adjusted supplier matrix: Based on reputation. S1 S S S S S 1 2 3 4 5 0.286 0.286 0.071 0.286 0.071 0.294 0.294 0.059 0.294 0.059 0.300 0.300 0.050 0.300 0.050 0.286 0.286 0.071 0.286 0.071 S2 0.294 0.294 0.059 0.294 0.059 0.300 0.300 0.050 0.300 0.050 0.286 0.286 0.071 0.286 0.071 S3 0.294 0.294 0.059 0.294 0.059 0.300 0.300 0.050 0.300 0.050 0.286 0.286 0.071 0.286 0.071 S4 0.294 0.294 0.059 0.294 0.059 0.300 0.300 0.050 0.300 0.050 0.286 0.286 0.071 0.286 0.071 S5 0.294 0.294 0.059 0.294 0.059 0.300 0.300 0.050 0.300 0.050 Score 0.293265 0.293265 0.060102 0.293265 0.060102

Table 19. Fuzzy supplier matrix: Based on nancial position. S1 S1 S2 S3 S4 S5 Net 1.000 4.000 0.167 0.200 0.333 5.700 1.000 5.000 0.143 0.167 0.250 6.560 1.000 6.000 0.125 0.143 0.200 7.468 0.250 1.000 0.111 0.167 0.250 1.778 S2 0.200 1.000 0.111 0.143 0.200 1.654 0.167 1.000 0.111 0.125 0.167 1.570 6.000 9.000 1.000 4.000 5.000 25.000 S3 7.000 9.000 1.000 5.000 6.000 28.000 8.000 9.000 1.000 6.000 7.000 31.000 5.000 6.000 0.250 1.000 2.000 14.250 S4 6.000 7.000 0.200 1.000 3.000 17.200 7.000 8.000 0.167 1.000 4.000 20.167 3.000 4.000 0.200 0.500 1.000 8.700 S5 4.000 5.000 0.167 0.333 1.000 10.500 5.000 6.000 0.143 0.250 1.000 12.393

International Journal of Production Research Table 20. Fuzzy adjusted supplier matrix: Based on nancial position. S1 S S S S S 1 2 3 4 5 0.175 0.702 0.029 0.035 0.058 0.152 0.762 0.022 0.025 0.038 0.134 0.803 0.017 0.019 0.027 0.141 0.562 0.062 0.094 0.141 S2 0.121 0.605 0.067 0.086 0.121 0.106 0.637 0.071 0.080 0.106 0.240 0.360 0.040 0.160 0.200 S3 0.250 0.321 0.036 0.179 0.214 0.258 0.290 0.032 0.194 0.226 0.351 0.421 0.018 0.070 0.140 S4 0.349 0.407 0.012 0.058 0.174 0.347 0.397 0.008 0.050 0.198 0.345 0.460 0.023 0.057 0.115 S5 0.381 0.476 0.016 0.032 0.095 0.403 0.484 0.012 0.020 0.081

3915

Score 0.291188 0.557421 0.043327 0.115239 0.041

Table 21. Fuzzy score (criteria weights). C S S S S S 1 2 3 4 5 0.081 0.038 0.027 0.011 0.135 Q 0.204 0.046 0.016 0.058 0.106 D 0.017 0.074 0.038 0.007 0.026 W 0.055 0.020 0.020 0.006 0.013 Ca 0.003 0.009 0.020 0.009 0.038 R 0.012 0.012 0.003 0.012 0.003 FP 0.010 0.019 0.001 0.004 0.005

Downloaded by [Tamilnadu Agricultural Univ] at 00:46 10 August 2013

4.2 Module II: Ranking of alternatives using GRA The ranking of the suppliers is determined by using GRA which consists of the following steps: (i) Generation of the data set of referential series (ii) Calculation of the grey relational coefcient (iii) Calculation of the degree of the grey equation coefcient

4.2.1 Generation of data set of referential series X0 The referential series is the optimal values of each criterion in the input matrix which is the fuzzy score of the criteria. The data set obtained by the fuzzy score is given in the following matrix Xi. 0:081 6 0:038 6 Xi 6 6 0:027 4 0:011 0:135 2 0:204 0:046 0:016 0:058 0:106 0:017 0:074 0:038 0:007 0:026 0:055 0:020 0:020 0:006 0:013 0:003 0:009 0:020 0:009 0:038 0:012 0:012 0:003 0:012 0:003 3 0:010 0:019 7 7 0:001 7 7 0:004 5 0:005

Xi = cell value of each criteria for supplier i; i = 1,2,3,4, and 5. The referential series of Xo is formed by having the optimum values from each column (criteria) of the input matrix Xi. Xo = (0.011, 0.204, 0.007, 0.055, 0.038, 0.012, 0.019). 4.2.2 Calculation of grey relational coefcient The grey relational coefcient (c0i j) of each supplier is calculated by using Equation (8) and is given in Table 22. c0i j D min nD max D0i j nD max 8

where, D min min min D0i j; D max max max D0i j and n = distinguished coefcient ne0; 1:The distinguished coefcient was taken as 0.5, an average value between 0 and 1.
i j i j

3916 Table 22. Grey relational coefcient. Grey relational coefcient c1 c2 c3 c4 c5 C 0.470 0.693 0.794 1.000 0.333 Q 1.000 0.373 0.333 0.391 0.487

P. Pitchipoo et al.

D 0.780 0.333 0.519 1.000 0.648

W 1.000 0.409 0.409 0.333 0.369

Ca 0.333 0.377 0.498 0.377 1.000

R 1.000 1.000 0.333 1.000 0.333

FP 0.491 1.000 0.333 0.368 0.391

Table 23. Degree of the grey equation coefcient. Grey equation coefcient Value 0.784 0.491 0.483 0.638 0.490

Downloaded by [Tamilnadu Agricultural Univ] at 00:46 10 August 2013

1 C 2 C 3 C 4 C 5 C

Degree of grey equation coefficient

0.9 0.8 0.7 0.6 0.5 0.4 0.3 0.2 0.1 0 1 2 3 Suppliers 4 5

Figure 2. Degree of the grey equation coefcient of suppliers.

4.2.3 Calculation of the degree of the grey equation coefcient  0) was determined using Equation (9), and the values were tabuFinally, the degree of the grey equation coefcient (C lated in Table 23.  0i C
7 X j 1

Wi j c0i j

The weightage of criteria (Wi(j)) is taken from Table 5. Figure 2 shows the pictorial representation of the degree of the grey equation coefcient of all suppliers. The suppliers are ranked based on the degree of the grey equation coefcient. From this, the supplier with the highest grey equation coefcient degree is selected as the best supplier. 4.3 Module III: Sensitivity analysis A sensitivity analysis was executed for getting accurate results. The value of only one variable is changed repeatedly, and the resulting changes on other variables are observed. In this study, two different sensitivity analyses were

International Journal of Production Research


0.900 0.800 0.1 0.2 0.3 0.4 0.5 0.400 0.6 0.300 0.200 0.100 0.7 0.8 0.9 1

3917

Grey equation coefficient

0.700 0.600 0.500

Downloaded by [Tamilnadu Agricultural Univ] at 00:46 10 August 2013

Figure 3. Sensitivity analysis with change of distinguished coefcient.

Grey equation coefficient

weights from FAHP Equal Weights

Figure 4. Sensitivity analysis with change of criteria weight.

performed. First, the sensitivity of the degree of the grey equation coefcient was determined with the different distinguished coefcient (n) which varies from 0.1 to 1.0, and is shown in Figure 3. Next the sensitivity of the grey equation coefcient degree was determined with the different weightages (weights from FAHP and equal weights to each criterion) and is shown in Figure 4. Figures 3 and 4 explain that supplier ranking is not changed with a change in the distinguished coefcient. Thus the robustness of the proposed model is proved. 5. Conclusion This work has focused on the decision-making process for the selection of the best supplier for a process industry. In this study a reliable hybrid model for selecting the supplier according to the decision maker s perceptions was presented. The major advantage of this work is that it can be used for both qualitative and quantitative criteria. The alternatives are ranked by using a two-phase methodology based on combined FAHP and GRA. The resulting scores are used to rank the alternatives and, in addition, to understand the degree of superiority among the alternatives. In this work, the fuzzy set theory is used for dealing with uncertainty and improving the lack of precision in evaluating criteria and different alternatives. This approach provides a better way to select suppliers and optimise procurement processes for decision makers. As a result of the study, it is found that the proposed model is practical for ranking alternatives with respect to multiple coniction criteria. It helps purchasing ofcials make the right sourcing decisions. This proposed model is also exible with a potential scope of application in similar kinds of industries for choosing suppliers. This can be extended to other corporate environments by considering appropriate criteria and their weights.

3918

P. Pitchipoo et al.

References
Alias, Mohamad Ashari, Siti Zaiton Mohd Hashim, and Supiah Samsudin. 2009. Using Fuzzy Analytic Hierarchy Process for Southern Johor River Ranking. International Journal of Advanced Soft Computing Applications 1 (1): 6276. Anthony Inman, R. 1992. Quality Certication of Suppliers by JIT Manufacturing Firms. Production and Inventory Management Journal 31 (2): 5961. Athawale, Vijay Manikrao, Prasenjit Chatterjee, and Shankar Chakraborty. 2010. Supplier Selection Using PROMETHEE II Method. International Journal of Manufacturing Technology Industrial Engineering 1 (1): 95102. Azzeh, Mohammad., Daniel Neagu, and Peter I. Cowling. 2010. Fuzzy Grey Relational Analysis for Software Effort Estimation. Empirical Software Engineering 15 (1): 6090. Benyoucef, Morad, and Mustafa Canbolat. 2007. Fuzzy AHP-Based Supplier Selection in E-Procurement. International Journal of Services and Operations Management 3 (2): 172192. Bevilacqua, M., F. E. Ciarapica, and G. Giacchetta. 2006. A Fuzzy-QFD Approach to Supplier Selection. Journal of Purchasing and Supply Management 12 (1): 1427. Chamodrakas, I., D. Batis, and D. Martakos. 2010. Supplier Selection in Electronic Marketplaces Using Satiscing and Fuzzy AHP. Expert Systems with Applications 37 (1): 490498. Chan, Felix T. S., and Niraj Kumar. 2007. Global Supplier Development Considering Risk Factors Using Fuzzy Extended AHPBased Approach. Omega 35 (4): 417431. Chan, Felix T. S., N. Kumar, M. K. Tiwari, H.C.W. Lau, and K. L. Choy. 2008. Global Supplier Selection: A Fuzzy-AHP Approach. International Journal of Production Research 46 (14): 38253857. Chatterjee, Prasenjit, Poulami Mikherjee, and Shankar Chakraborty. 2011. Supplier Selection Using Compromise Ranking and Outranking Approaches. Journal of Industrial Engineering International 7 (14): 6173. Chen, C. T. 2000. Extensions of the TOPSIS for Group Decision-Making Under Fuzzy Environment. Fuzzy Sets and Systems 114 (1): 19. Chen, L. S., and C. H. Cheng. 2005. Selecting IS Personnel Using Ranking Fuzzy Number by Metric Distance Method. European Journal of Operational Research 160 (3): 803820. Chen, Yun-Chin, Jun-Yuan Kuo, and Bang-Ting Luo. 2011. Applying Fuzzy Analytic Hierarchy Process and Grey Relation Analysis to Evaluate the Supply Chain Performance of the Wafer Testing House. American Journal of Applied Sciences 8 (12): 13981403. Dickson, G. W. 1966. An Analysis of Vendor Selection Systems and Decisions. Journal of Purchasing 2 (1): 517. Haq, A. N., and G. Kannan. 2006. Fuzzy Analytical Hierarchy Process for Evaluating and Selecting a Vendor in a Supply Chain Model. International Journal of Advanced Manufacturing Technology 29 (78): 826835. Ho, William., Xiaowei Xu, and Prasanta K. Dey. 2010. Multi-Criteria Decision Making Approaches for Supplier Evaluation and Selection: A Literature Review. European Journal of Operational Research 202 (1): 1624. Hua, Bai. 2008. A Fuzzy AHP Based Evaluation Method for Vendor-Selection. Proceedings of 4th IEEE International Conference on Management of Innovation and Technology [ICMIT 2008], Bangkok, 10771081. Kahraman, Cengiz, Ufuk Cebeci, and Ziya Ulukan. 2003. Multi-Criteria Supplier Selection Using Fuzzy AHP. Logistics Information Management 16 (6): 382394. Kaufmann, Arnold, and Madan M. Gupta. 1991. Introduction to Fuzzy Arithmetic: Theory and Applications. New York, NY: Van Nostrand Reinhold Publishers. Ketata, Raouf, Hajer Ben Mahmoud, and Taieb Ben Romdhan. 2008. A New Approach for Resolving a Supplier Selection and Evaluation Problem. Malaysian Journal of Computer Science 21 (1): 6679. Khaled, A. A., Sanjoy Paul Kumar, Ripon Kumar Chakraborty, and Md. Salahuddin Ayuby. 2011. Selection of Suppliers Through Different Multi-Criteria Decision Making Techniques. Global Journal of Management and Business Research 11 (4): 111. Kuo, R. J., L. Y. Lee, and Tung-Lai Hu. 2010. Developing a Supplier Selection System Through Integrating Fuzzy AHP and Fuzzy DEA: A Case Study on an Auto Lighting System Company in Taiwan. Production Planning and Control 21 (5): 468484. Lee, Amy H. I., He-Yau Kang, and Ching-Ter Chang. 2009. Fuzzy Multiple Goal Programming Applied to TFT-LCD Supplier Selection by Downstream Manufacturers. Expert Systems with Applications 36 (3): 63186325. Lee, Amy H. I., He-Yau Kang, Chang-Fu Hsu, and Hsiao-Chu Hung. 2009. A Green Supplier Selection Model for High-Tech Industry. Expert Systems with Applications 36 (4): 79177927. Li, Guo-Dong., Daisuke Yamaguchi, and Masatake Nagai. 2008. A Grey-Based Rough Decision-Making Approach to Supplier Selection. International Journal of Advanced Manufacturing Technology 36 (910): 10321040. Mohammady, Peyman, and Amin Amid. 2010. Integrated Fuzzy VIKOR and Fuzzy AHP Model for Supplier Selection in an Agile and Modular Virtual Enterprise; Application of FMCDM on Service Companies. The Journal of Mathematics and Computer Science 1 (4): 413434. Nilay Yucenur, G., Ozalp Vayvay, and Nihan Cetin Demirel. 2011. Supplier Selection Problem in Global Supply Chains by AHP and ANP Approaches Under Fuzzy Environment. International Journal of Advanced Manufacturing Technology 56 (58): 823833. Omid, Khorasani, and Bafruei Morteza Khakzar. 2011. A Fuzzy AHP Approach for Evaluating and Selecting Supplier in Pharmaceutical Industry. International Journal of Academic Research 3 (1): 346352.

Downloaded by [Tamilnadu Agricultural Univ] at 00:46 10 August 2013

International Journal of Production Research

3919

Downloaded by [Tamilnadu Agricultural Univ] at 00:46 10 August 2013

Ozcan, Kilincci., and Asli Onal Suzan. 2011. Fuzzy AHP Approach for Supplier Selection in a Washing Machine Company. Expert Systems with Applications 38 (8): 96569664. Pitchipoo, P., P. Venkumar, and S. Rajakarunakaran. 2012. A Distinct Model for Evaluation and Selection of Supplier for an Electro Plating Industry. International Journal of Production Research 50(16): 46354648. Punniyamoorthy, M., P. Mathiyalagan, and P. Parthiban. 2011. A Strategic Model Using Structural Equation Modeling and Fuzzy Logic in Supplier Selection. Expert Systems with Applications 38 (1): 458474. Saaty, Thomas L. 1990. How to Make a Decision: The Analytic Hierarchy Process. European Journal of Operational Research 48 (1): 926. Sen, Ceyda Gungor, Selcuk Sen, and Huseyin Baslgil. 2010. Preselection of Suppliers Through an Integrated Fuzzy Analytic Hierarchy Process and MaxMin Methodology. International Journal of Production Research 48 (6): 16031625. Tsai, Chih-Hung, Ching-Liang Chang, and Lieh Chen. 2003. Applying Grey Relational Analysis to the Vendor Evaluation Model. International Journal of the Computer, the Internet and Management 11 (3): 4553. Vaidya, Omkarprasad S., and Sushil Kumar. 2006. Analytic Hierarchy Process: An Overview of Applications. European Journal of Operational Research 169 (1): 129. Wang, Jia-Wen, Ching-Hsue Cheng, and Kun-Cheng Huang. 2009. Fuzzy Hierarchical TOPSIS for Supplier Selection. Applied Soft Computing 9 (1): 377386. Yang, Ching-Chow, and Bai-Sheng Chen. 2006. Supplier Selection Using Combined Analytical Hierarchy Process and Grey Relational Analysis. Journal of Manufacturing Technology Management 17 (7): 926941. Yuan, Shouhua, Xiao Liu, Tu Yiliu, and Deyi Xue. 2008. Evaluating Supplier Performance Using DEA and Piecewise Triangular Fuzzy AHP. Journal of Computing and Information Science in Engineering 8: 17. Zadeh, L. A. 1965. Fuzzy Sets. Information and Control 8: 338353. Zaim, Selim, Mehmet Sevkli, and Mehves Tarim. 2003. Fuzzy Analytic Hierarchy Based Approach for Supplier Selection. Journal of Euro Marketing 12 (34): 147176. Zeydan, Mithat, Cuneyt Colpan, and Cemal Cobanoglu. 2011. A Combined Methodology for Supplier Selection and Performance Evaluation. Expert Systems with Applications 38 (3): 27412751. Zhang, Shi-fang, and San-yang Liu. 2011. A GRABased Intuitionistic Fuzzy Multi-Criteria Group Decision Making Method for Personnel Selection. Expert Systems with Applications 38 (9): 1140111405.

You might also like