You are on page 1of 9

Available online at www.sciencedirect.

com
Available online at www.sciencedirect.com
ScienceDirect
ScienceDirect
Procedia
Available Computer
online Science 00 (2019) 000–000
at www.sciencedirect.com
Procedia Computer Science 00 (2019) 000–000 www.elsevier.com/locate/procedia
www.elsevier.com/locate/procedia
ScienceDirect
Procedia Computer Science 167 (2020) 1941–1949

International Conference on Computational Intelligence and Data Science (ICCIDS 2019)


International Conference on Computational Intelligence and Data Science (ICCIDS 2019)
Prioritizing Autonomous Maintenance System Attributes using
Prioritizing Autonomous Maintenance System Attributes using
Fuzzy EDAS Approach
Fuzzy EDAS Approach
Priyank Srivastavaa, Arsalan Mustafaa, Dinesh Khandujab, Sunil Kumar Chowdharya, Naveen Kumara, Kartika,
Priyank Srivastavaa, Arsalan Mustafaa, Dinesh Khanduja
Rajendra
b
Kumar , Sunil Kumar
Shukla c Chowdharya, Naveen Kumara, Kartika,
Rajendra Kumar Shuklac
a
Amity University,Uttar Pradesh, Noida-201313, India,
b
National
a
Institute
Amity of Technology,
University,Uttar Haryana,
Pradesh, Kurukshetra-136119,
Noida-201313, India, India,
cb
ABES EnginneringCollege,
National , UttarHaryana,
Institute of Technology, Pradesh,Kurukshetra-136119,
Ghaziabad- 201009,India,
India
c
ABES EnginneringCollege, , Uttar Pradesh, Ghaziabad- 201009, India

Abstract
Abstract
With advancement in IT enabled tools, there is paradigm shift in maintenance process to become an automated or appropriately
With advancement
autonomous system.in For
IT enabled tools, there
understanding is paradigm
system shift in of
and application maintenance
IT enabledprocess to become anand
tools identification automated or appropriately
prioritization of system
autonomous system. For
attributes is essential. understanding
This system
paper is focused on and applicationofofautonomous
identification IT enabled maintenance
tools identification
system and prioritization
attributes that are ofbased
system
on
attributes
technologyis perspective
essential. This
and paper is focused on
its prioritization identification
using Fuzzy EDAS of autonomous maintenance
method. Fuzzy methodologysystem
wasattributes
used to that are based
remove issues on
of
technology
uncertainty perspective and its prioritization
and vague judgments. using Fuzzy
Sensor technology and EDAS
database method. Fuzzy were
management methodology
identifiedwas
as used to remove
pertinent issuesThe
attributes. of
uncertainty
prioritizationand vague
results fromjudgments.
Fuzzy EDAS Sensor
weretechnology
compared andwithdatabase management
fuzzy TOPSIS were
approach andidentified as pertinent The
it shows consistency. attributes. The
results were
prioritization
shared with the results from Fuzzy
management EDAS were
for decision compared with fuzzy TOPSIS approach and it shows consistency. The results were
making.
shared with the management for decision making.
© 2019 The Authors. Published by Elsevier B.V.. This is an open access article under the CC BY-NC-ND license
©
© 2020
2019 The
The Authors.
Authors. Published
Published by by Elsevier
Elsevier B.V.
(http://creativecommons.org/licenses/by-nc-nd/4.0/) B.V.. This is an open access article under the CC BY-NC-ND license
This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
(http://creativecommons.org/licenses/by-nc-nd/4.0/)
Peer-review under responsibility of the scientific committee of the International Conference on Computational Intelligence and
Peer-review under responsibility of the scientific committee of the International Conference on Computational Intelligence and Data
Peer-review
Data Science
Science under
(ICCIDS responsibility
(ICCIDS
2019). 2019) of the scientific committee of the International Conference on Computational Intelligence and
Data Science (ICCIDS 2019)
Keywords: Autonomus maintenance; Fuzzy Methodology; EDAS
Keywords: Autonomus maintenance; Fuzzy Methodology; EDAS

1. Introduction
1. Introduction
In today’s world, there have been rapid changes in technology that are influencing manufacturing paradigms.
In today’s in
Development world, there have
IT enabled been
services arerapid changes
key factor in technology
to bring that in
these changes aremanufacturing
influencing manufacturing
sector. paradigms.
Development in IT enabled services are key factor to bring these changes in manufacturing sector.

Corresponding author. Tel.: +91-9811800986


E-mail address:
Corresponding psriavstava5@amity.edu
author. Tel.: +91-9811800986
E-mail address: psriavstava5@amity.edu
1877-0509 © 2019 The Authors. Published by Elsevier B.V.. This is an open access article under the CC BY-NC-ND license
(http://creativecommons.org/licenses/by-nc-nd/4.0/)
1877-0509 © 2019 The Authors. Published by Elsevier B.V.. This is an open access article under the CC BY-NC-ND license
Peer-review under responsibility of the scientific committee of the International Conference on Computational Intelligence and Data Science
(http://creativecommons.org/licenses/by-nc-nd/4.0/)
(ICCIDS 2019)
Peer-review under responsibility of the scientific committee of the International Conference on Computational Intelligence and Data Science
(ICCIDS 2019)

1877-0509 © 2020 The Authors. Published by Elsevier B.V.


This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Peer-review under responsibility of the scientific committee of the International Conference on Computational Intelligence and Data
Science (ICCIDS 2019).
10.1016/j.procs.2020.03.217
21942 Priyank Srivastava/
Priyank SrivastavaProcedia ComputerComputer
et al. / Procedia Science 00 (2019)167
Science 000–000
(2020) 1941–1949

Nomenclature

EDAS Evaluation based on Distance from Average Solution.


MADM Multi Attribute Decision Making
WSFPDA Weighted Sum of all Fuzzy positive distance from average solution
WSFNDA Weighted Sum of all Fuzzy positive distance from average solution
NFPDA Normalized fuzzy positive distance from average solution
NFNDA Normalized fuzzy negative distance from average solution

This paradigm can make a factory smart by applying many features such as: intelligent information processing
approach, future-oriented techniques, communication systems and many more [1]. As the systems in Industry 4.0 will
be highly complex, automated, therefore flexibility of an intelligent factory will bring new challenges to safety,
reliability and state of being preserved. These issues mandate the application of autonomous maintenance system
(AMS). AMS is a perfect subset of Industry 4.0. By decreasing cost associated with maintenance activities, profit
margins of organization can be increased (Fig.1.).
Primary Input Primary Output

Production

Maintenance Demand

Maintenance

Figure 1. Maintenance Support to Production [2]


Maintenance can be defined as process of preserving the state of being or condition. Autonomous machines in Industry
4.0 will be requiring autonomous maintenance system. This type of maintenance philosophy demands proactive
approach and application of data management system along with data analytics and sensor systems for monitoring and
control of devices attached. Maintenance system can be categorized as follow:
(1) Planned Maintenance (Fig.2.)
(2) Unplanned Maintenance

Preventive Planned
Reliability Centred
Maintenance Maintenance
Maintenance

Condition Based Opportunistic


Maintenance Predictive Maintenance
Maintenance

Figure 2. Type of Planned Maintenance


India is a developing country with a motto of “Make in INDIA”, which makes India a country with many Micro, Small
& Medium Enterprise (MSME) sector that is contributing roughly 33% of manufacturing gross value output (GVO).
Studies have shown that maintenance cost is one of the main expenditures items that can have share of 15% - 70% of
the total cost of operating a complex system. Therefore, there is vast scope and opportunity of implementing
autonomous maintenance system in these MSME. The implementation will depend upon different attributes of AMS
Priyank Srivastava et al. / Procedia Computer Science 167 (2020) 1941–1949 1943
Priyank Sriavstava/ Procedia Computer Science 00 (2019) 000–000 3

being mapped to different industries. Not all the attributes are important to a particular industry. Therefore, there is
need for identifying pertinent attributes.
As various attributes are required for analysis, therefore its selection is a MADM problem. MADM approach assist
the decision maker to arrive at optimal decision in situation involving number of attributes. This is the reason for
application of MADM approach in field of process, service, manufacturing, information technology, pharmaceutical
industries. Various MADM approached has been used by researchers for selection of alternatives or prioritization of
attributes [3] [4] [5] [6] [7] [8] [9] [10]. The EDAS approach is relatively new MADM approach [11], was introduced
by Ghorabaee. The performance of this approach is consistent with popular MADM approach of technique for order
of preference by similarity to ideal solution (TOPSIS), VlseKriterijumska Optimizacija I Kompromisno Resenje
(VIKOR). EDAS is different from distance-based approach as positive and negative distance is calculated from
average solution. This calculation was dependent on benefit and non-benefit attribute.
In the view of above requirement of AMS for maintenance planning process, and large number of attributes associated
with it, it is essential to identify and prioritize attribute of AMS. The first objective of study is to identify various
perspectives associated with AMS. This objective is supported by relevant literature review. The second objective is
to prioritization of attributes associated with perspectives of AMS to manage maintenance planning effectively. But
the prioritization using MADM approach is always subjected to issue of uncertainty [12]. To remove this limitation.
fuzzy methodology is integrated with EDAS approach. The proposed research work deals with prioritization of AMS
attributes using fuzzy EDAS for a manufacturing concern in northern part of India. The rest of the paper is structured
as: Section 2 explains the research methodology. The proposed method is described in Section 3. The application of
the methodology and results are shown in Section 4. The conclusion, limitations, managerial implications and future
potential scope is discussed in Section 5.

2. Methodology

The methodology is shown in Fig.3.

Identification of Attribute from Identify scale of rating Formation of decision matrix


Literature and Expert Opinion

Prioritization of Attributes Formation of Aggregated


Using Fuzzy TOPSIS Decision Matrixx

Comparison of Prioritization Prioritization of Attributes


Using Fuzzy EDAS
Figure 3. Methodology
The steps involved, according to the methodology are as follow:

 The first step is identification of perspectives and attribute from literature review and expert opinion. It is an
important activity as it is building block of the study.
 The second step is selection of rating scale. Often expert’s judgement is recorded in terms of linguistic terms
approximated by some rating scale. In present study, Wang’s scale [13] is used for taking expert’s judgement.
 The next step is to form expert’s judgement matrix. It is a pairwise comparison matrix. It forms the basis of
further evaluation using fuzzy EDAS and TOPSIS approach.

3. Method

3.1 Fuzzy EDAS

The EDAS method was introduced by Ghorabaee. The steps involved in this approach are:
1944 Priyank Srivastava et al. / Procedia Computer Science 167 (2020) 1941–1949
4 Priyank Srivastava/ Procedia Computer Science 00 (2019) 000–000

 Formulation of judgement matrix from different expert. This matrix is in the form of linguistic variables. To
remove uncertainty, these linguistic variables are approximated by triangular fuzzy number (TFN).

𝐶𝐶� 𝐶𝐶� … . . 𝐶𝐶�


𝐶𝐶� 𝑎𝑎
��� 𝑎𝑎��� 𝑎𝑎���
…….
𝑎𝑎
� 𝑎𝑎
� 𝑎𝑎
���
E1= .𝐶𝐶.� � �� ��
� (1)
𝑎𝑎��� 𝑎𝑎��� 𝑎𝑎���
𝐶𝐶 � … … . .
𝑎𝑎��� 𝑎𝑎��� 𝑎𝑎���
Where E1 is expert elicitation in form linguistic variable approximated by TFN. Wang scale [13] is used for
matrix generation.
 Formation of aggregated decision matrix.

 Evaluate average solution.


Average Matrix = �𝐴𝐴𝐴𝐴� �1x m (2)
∑�
��� ���
�𝐴𝐴𝐴𝐴� �= (3)

Where aij is the crisp score.

 Calculate fuzzy positive distance from average solution (FPDA) and fuzzy negative distance from average
solution (FNDA)
FPDAi = �𝐹𝐹𝐹𝐹𝐹𝐹𝐹𝐹�� �n x m = max�0, �𝑎𝑎�� − 𝐴𝐴𝐴𝐴� �� / (𝐴𝐴𝐴𝐴� ) (4)
FNDAi= �𝐹𝐹𝐹𝐹𝐹𝐹𝐹𝐹�� �n x m = max�0, �𝐴𝐴𝐴𝐴� − 𝑎𝑎�� �� / (𝐴𝐴𝐴𝐴� ) (5)
Where Eq. 4 and 5 are for beneficial attribute.

 Calculate weighted sum of all FPDA and FNDA


WSFPDA = ∑� ��� 𝑤𝑤� 𝐹𝐹𝐹𝐹𝐹𝐹𝐹𝐹�� (6)
WSNDA = ∑� ��� 𝑤𝑤� 𝐹𝐹𝐹𝐹𝐹𝐹𝐹𝐹�� (7)
Where 𝑤𝑤� is weight of each attribute.

 Normalization of WSFPDA and WSNDA


NFPDAi= WSFPDAi / maxi (WSFPDAi) (8)
NFNDAi = 1- WSFNDAi / maxi (WSFNDAi) (9)

 Evaluation of appraisal score (AS)



AS = (𝑁𝑁𝑁𝑁𝑁𝑁𝑁𝑁𝑁𝑁� + 𝑁𝑁𝑁𝑁𝑁𝑁𝑁𝑁𝑁𝑁� ) (10)

 The prioritization of attributes is done using appraisal score.

3.2 Fuzzy TOPSIS

TOPSIS method, a MADM approach was proposed and developed by [14]. This technique is based on the fact that
preferred alternative should be closest to positive ideal solution and farthest to anti or negative ideal solution. The
fuzzy-TOPSIS has been used by different researchers in different field of application [15][7]. The steps involved in
computations by using fuzzy TOPSIS are as follow:
 The first two steps are same as that of fuzzy EDAS
 Normalization of aggregate matrix.
���
�𝑟𝑟�� = ∑� � (11)
� ���
Where 𝑥𝑥�� are the cell values of aggregated matrix and �𝑟𝑟�� normalized aggregated matrix.
Priyank Srivastava et al. / Procedia Computer Science 167 (2020) 1941–1949 1945
Priyank Sriavstava/ Procedia Computer Science 00 (2019) 000–000 5

m= 1,2, 3,………………….M; n = 1,2,3…………..N.


 Next step is to determine the weighted normalized decision matrix.
𝑣𝑣��� = �𝑟𝑟�� ⊗ 𝑤𝑤��� (12)
Where 𝑤𝑤��� normalized weight of each attribute.
 Evaluation of fuzzy positive and negative ideal solution respectively.

𝐴𝐴� = �𝑉𝑉��∗ , 𝑉𝑉��∗ , 𝑉𝑉��∗ , … … . . 𝑉𝑉��∗ � where 𝑉𝑉��∗ = (𝑐𝑐̃�∗ , 𝑐𝑐̃�∗ , 𝑐𝑐̃�∗ ) and 𝑐𝑐̃�∗ = 𝑚𝑚𝑚𝑚𝑚𝑚
� {𝑐𝑐̃�� } (13)

𝐴𝐴� = �𝑉𝑉��� , 𝑉𝑉��� , 𝑉𝑉��� , … … . . 𝑉𝑉��� � where 𝑉𝑉��� = (𝑎𝑎��∗ , 𝑎𝑎��∗ , 𝑎𝑎��∗ ) and 𝑎𝑎��� = � {𝑎𝑎��� }
𝑚𝑚𝑚𝑚𝑚𝑚 (14)

Where both 𝐴𝐴� and 𝐴𝐴� are positive and negative ideal solutions for benefit attribute
 Calculation of Euclidean distance.

𝑑𝑑� = �∑� ��� −𝑉𝑉��� )� (positive distance)
���(𝑣𝑣 (15)


𝑑𝑑� = �∑� ��� −𝑉𝑉��� )� (negative distance)
���(𝑣𝑣 (16)
 Calculation of Closeness coefficient.

��
𝐶𝐶� = ∗ �� � (17)
�� �

Where m=1, 2,….M

4. Case Analysis

To implement the proposed methodology, a case study from manufacturing organization serving automobile,
construction and agro sectors in India has been taken. Although, many attributes and sub attributes have been identified
for AMS, but in this study only technology perspective [16] has been taken into consideration.
The expert’s judgement aggregated matrix is shown by Table 1.
Table 1. Aggregated Expert Judgement Matrix
Technology Database Data Storage Data Analysis Sensor
Perspective Management Technology
Database (0.33 0.33 0.33) (0.3 0.58 0.92) (0.17 0.33 0.67) (0.15 0.27 0.58)
Management
Data Storage (0.15 0.27 0.58) (0.33 0.33 0.33) (0.17 0.33 0.67) (0.17 0.33 0.67)

Data Analysis (0.17 0.33 0.67) (0.17 0.33 0.67) (0.33 0.33 0.33) (0.33 0.33 0.33)
Sensor Technology (0.3 0.58 0.92) (0.17 0.33 0.67) (0.33 0.33 0.33) (0.33 0.33 0.33)
Weight (Wj) (0.50 0.75 1.0) (0.50 0.75 1.0) (0.75 1.0 1.0) (0.50 0.75 1.0)
This matrix was used for prioritization of attributes for technology perspective by fuzzy EDAS and TOPSIS approach
respectively.

4.1 Analysis

Using Eq. 1 to 7, WSFPDA and WFNDA was calculated and is shown in Table 2. And 3. respectively, as:
6 Priyank Srivastava/ Procedia Computer Science 00 (2019) 000–000

1946 Priyank Srivastava et al. / Procedia Computer Science 167 (2020) 1941–1949

Table 2. WSFPDA
Technology Database Data Sensor
Data Analysis
Perspective Management Storage Technology
Database
Management -0.159235669 0.477707 -0.08280255 -0.2356688
Data Storage -0.23566879 -0.1592357 -0.08280255 -0.0828025
Data Analysis -0.082802548 -0.0828025 -0.15923567 -0.1592357
Sensor
Technology 0.477707006 -0.0828025 -0.15923567 -0.1592357

Table 3. WSFNDA
Technology Database Data Data Sensor
Perspective Management Storage Analysis Technology
Database
Management 0.159235669 -0.477707 0.082802548 0.2356688
Data Storage 0.23566879 0.1592357 0.082802548 0.0828025
Data
Analysis 0.082802548 0.0828025 0.159235669 0.1592357
Sensor
Technology -0.47770700 0.0828025 0.159235669 0.1592357

The average score was calculated using Eq. 8-10 and is shown in Table 4.
Table 4. Average Score
Attribute AS
Database
0.5703971
Management
Data Storage 0
Data
0.0433213
Analysis
Sensor
0.6137184
Technology
The negative and positive ideal solution was calculated using Eq. 1,11-14 and is shown in Table 5 and 6 respectively.
Table 5. Fuzzy Negative Ideal Solution
Database Data Data Sensor
Attribute Management Storage Analysis Technology
Database
0.004972552 0 0 0.0004354
Management
Data Storage 0.00623757 0.004693045 0 0
Data
0.003850744 0.003634294 0.0001698 0.0001088
Analysis
Sensor
0 0.003634294 0.0001698 0.0001088
Technology

Table 6. Fuzzy Positive Ideal Solution


Database Data Data Sensor
Attribute
Management Storage Analysis Technology
Database
0.00007 0.00469 0.00017 0.00000
Management
Data Storage 0.00000 0.00000 0.00017 0.00044
Data
0.00029 0.00007 0.00000 0.00011
Analysis
Sensor
0.00624 0.00007 0.00000 0.00011
Technology

The closeness coefficient was calculated using Eq. 15-17 and is shown in Table 7.
Priyank Srivastava et al. / Procedia Computer Science 167 (2020) 1941–1949 1947
Priyank Sriavstava/ Procedia Computer Science 00 (2019) 000–000 7

Table 7. Closeness Coefficient Score for fuzzy TOPSIS


Positive Negative
Closeness
Attribute Ideal Ideal
Coefficient
Solution Solution
Database
0.0049726 0.0049345 0.5019225
Management
Data Storage 0.0109306 0.0001698 0.9847023
Data
0.0076548 0.000354 0.955799
Analysis
Sensor
0.0038041 0.0063051 0.3762993
Technology

The combined ranking for fuzzy EDAS and fuzzy TOPSIS is shown in Table 8.
Table 8. Combined Ranking
Fuzzy Fuzzy
Attribute Ranking Ranking
EDAS TOPSIS
Database
0.5703971 2 0.5019225 2
Management
Data Storage 0 4 0.9847023 4
Data
0.0433213 3 0.955799 3
Analysis
Sensor
0.6137184 1 0.3762993 1
Technology

The prioritization of attributes is shown in Fig. 4.

1.2
1
0.8
0.6
0.4
0.2
0
Database Data Storage Data Analysis Sensor
Management Technology

Fuzzy EDAS Fuzyy TOPSIS

Figure 4. Comparison Figure

4.1 Result and Discussion

From Table 8., the prioritization of attributes from Technology perspective is as follow:
 Fuzzy EDAS: The prioritization of attribute is Sensor Technology> Database Management>Data
Analysis>Data Storage. The higher ranking is given to attribute having high numerical value of average
score.
 Fuzzy TOPSIS: The prioritization of attribute is same as fuzzy EDAS approach. It depends on closeness
coefficient value, where attribute having numerical value close to ideal solution is ranked at higher level.
 Both the results are consistent, evaluating sensor technology as the pertinent attribute in technology
perspective.
1948 Priyank Srivastava et al. / Procedia Computer Science 167 (2020) 1941–1949
8 Priyank Srivastava/ Procedia Computer Science 00 (2019) 000–000

From the analysis part it is quite evident that sensor technology is the most important attribute in technology
perspective. The primary work of sensor technology is monitoring of the system under observation and reporting any
deviation from set parameter to the mainframe for decision making. Data is considered as the new fuel that will drive
the future innovations. The management of data is very important issue. The data can have many source or formats.
In AMS, there will be number of sensors, image processing, voice or sound processing systems respectively,
continuously feeding data to the mainframe. The importance of data lies in its end application. This potential can be
envisaged using data management system. Filtration, modulation and integration of data is essential for proactive
fault diagnostic. Data analysis assist system analyst, for cleaning and transforming data into goals and objective of
organization

5. Conclusion

With the advancement in information technology enabled services, the conventional manufacturing process are
transforming from automatic to autonomous systems. Maintenance is important sub-set of manufacturing system.
Therefore, for achieving Industry 4.0, autonomous maintenance system design is one of the prerequisites. The research
work identifies and prioritize attributes of technology perspective for AMS.
The research outcomes of the study are important as, perspectives of AMS are identified and attribute are prioritized.
Before modeling of AMS, the identification and prioritization of its subsystems and attribute is important. This
research works builds up and present a methodology for doing the same. It will assist system analyst and maintenance
engineer for designing AMS as per the requirement.
The EDAS and TOPSIS calculation are based on expert judgment. There is inherent issue of uncertainty and biased
judgement in it. The author understands it. To remove it, fuzzy methodology was integrated with conventional EDAS
and TOPSIS. This present research work was done considering technology perspective only. For future research work,
other perspective can also be identified and prioritized. Other MADM approach of can also be used for prioritization
of attribute. These findings were forwarded to management of organization for their pursual.

Acknowledgement
The authors are thankful to anonymous reviewers, who have put their valuable time in reviewing this article and
suggesting necessary modifications.

References
[1] Vaidya S, Ambad P, Bhosle S. (2018) "Industry 4.0–a glimpse." In: Procedia Manufacturing, 20(1): 233-238.

[2] Gits C. (1994) "Structuring maintenance control systems." International Journal of Operations & Production Management, 14(7):5–
17.

[3] Shahin A, Shirouyehzad H, Pourjavad E. (2012) "Optimum maintenance strategy: a case study in the mining industry." International J
of Services and Operations Management, 12(3):368–86.

[4] Moghimi R, Anvari A.(2017) "An integrated fuzzy MCDM approach and analysis to evaluate the financial performance of Iranian
cement companies." The International Journal of Advanced Manufacturing Technology. 71(1–4):685–98.

[5] Sharma R K, Kumar D and Kumar P. (2005) "Systematic failure mode effect analysis (FMEA) using fuzzy linguistic modelling."
International Journal of Quality & Reliability Management,22(9):986–1004.

[6] Srivastava P, Khanduja D and Agrawal VP. (2018) "Integrating Agile Thinking into maintenance strategy performance analysis. Int J
Process Management and Benchmarking, 8(2):228–45.

[7] Srivastava P, Khanduja D and Agrawal VP. (2017) "A framework of fuzzy integrated MADM and GMA for maintenance strategy
selection based on agile enabler attributes." Mathematics-in-Industry Case Studies, 8(1):5.

[8] Srivastava P, Agarwal M, Narayanan A, Tandon M, Tulsian M. (2019) "Mitigation of Risk in CNG Station Using Fuzzy-Integrated
Technique." In Advances in Interdisciplinary Engineering:535–42.
Priyank Srivastava et al. / Procedia Computer Science 167 (2020) 1941–1949 1949
Priyank Sriavstava/ Procedia Computer Science 00 (2019) 000–000 9

[9] Panchal D, Jamwal U, Srivastava P, Kamboj K and Sharma R. Panchal, D., Jamwal, U. (2018) "Fuzzy methodology application for
failure analysis of transmission system." International Journal of Mathematics in Operational Research,12(2):220–37.

[10] Panchal D, Chatterjee P, Shukla RK, Choudhury T, Tamosaitiene J. (2017) "Integrated Fuzzy AHP-Codas Framework for Maintenance
Decision in Urea Fertilizer Industry." Economic Computation & Economic Cybernetics Studies & Research, 51(3).

[11] Keshavarz Ghorabaee M ZE, Olfat L, Turskis Z. (2015) "Multi-criteria inventory classification using a new method of evaluation based
on distance from average solution (EDAS)." Informatic, 26(3):435–51.

[12] Panchal D, Srivastava P. (2019) Qualitative analysis of CNG dispensing system using fuzzy FMEA–GRA integrated approach.
International Journal of System Assurance Engineering and Management, 10(1):44–56.

[13] Wang L, Chu J and Wu J. (2007) "Selection of optimum maintenance strategy based on a fuzzy analytic hierarchy Process."
International J of Production Economics, 107(1):151–163.

[14] Hwang C-L, Yoon K. (1981) "Methods for Multiple Attribute Decision Making." In Multiple attribute decision making : 58–191.
Available from: http://link.springer.com/10.1007/978-3-642-48318-9_3

[15] Panchal D and Kumar D. (2017) "Risk analysis of compressor house unit in thermal power plant using integrated fuzzy FMEA and
GRA approach." International Journal of Industrial and Systems Engineering, 25(2):228–50.

[16] Galar D, Mirka K. (2017) "The impact of maintenance 4.0 and big data analytics within strategic asset management." In: Maintenance
Performance and Measurement and Management 2016: 96-104

You might also like