Selecting the most efficient maintenance approach using fuzzy multiple criteria decision making

doi:10.1016/S0925-5273(02)00380-8

International Journal of Production Economics

Volume 84, Issue 1, 11 April 2003, Pages 85-100

https://doi.org/10.1016/S0925-5273(02)00380-8 Get rights and content

Abstract

We assess the most popular maintenance approaches, i.e. strategies, policies, or philosophies, using a fuzzy multiple criteria decision making (MCDM) evaluation methodology. We illustrate with two examples how the suggested evaluation methodology identifies the most informative approach. Using the fuzzy MCDM, it would be possible to select in advance, the most informative (efficient) maintenance approach. Consequently, this leads to less planned replacements, and failures would be reduced to approximately zero and higher utilization of component life can be achieved. Thus, the maintenance department could contribute more to the business objectives throughout participating effectively in adding value to the production activities.

Introduction

The importance of maintenance function has increased due to its role in keeping and improving the availability, product quality, safety requirements, and plant cost-effectiveness levels. Maintenance costs constitute an important part of the operating budget of manufacturing firms. Mckone and Wiess (1998) reported that the amount of money Du Pont spent, in 1991, company-wide on maintenance was roughly equal to its net income. Al-Najjar (1997) showed that maintenance expenses vary depending on the type of industry, typically, figures such as 15–40% of production costs may be encountered. The consequences of an inefficient maintenance policy go far beyond the direct costs of maintenance.

The maintenance concept has passed through several major developments. In this paper, we assess the most popular maintenance approaches, i.e. strategies, policies, methodology or philosophy, using a methodology based on fuzzy logic theory, i.e. fuzzy multiple criteria decision-making (MCDM). Section 2 reviews some of the most popular maintenance approaches. Section 3 demonstrates the bases of comparison of maintenance approaches. Section 4 goes through basic concepts of fuzzy logic and MCDM. Section 5 illustrates the evaluation methodology suggested for assessing and selecting the most efficient (informative) maintenance approach by applying it on typical data from two different cases, and finally conclusions.

Section snippets

Maintenance approaches

In the following we present the most popular maintenance approaches, i.e. strategies, policies, methodology or philosophy. Maintenance strategy involves the identification, researching and execution of many repairs, replace and/or inspect decisions, see Al-Najjar (1997) and Kelly (1997).

Failure based maintenance (FBM) is only performed when a failure or breakdown occurs, no action is taken to detect the onset of-, or to prevent-, failure. The maintenance related costs are usually high, but it

Criteria to compare maintenance approaches

The accuracy of the timing of maintenance action highly affects the useful life length of the maintained equipment/component, number of failures, number of planned replacements, mean time to repair, maintenance direct costs and consequently production costs. The more accurate the maintenance action timing, the higher the utilization of the component life. To assess the efficiency of a maintenance policy two measures (effectiveness and accuracy) are suggested in Al-Najjar (1997).

Achieving more

Fuzzy logic and multiple criteria decision making (MCDM)

In the following we discuss the concept of fuzzy logic and MCDM.

Evaluation methodology

In this study, we assessed and identified set of maintenance approaches using a fuzzy MCDM. The objective is to rank the maintenance approaches by evaluating their ability to provide information about the changes in the behavior of failure causes, which are used as criteria, as illustrated in Table 1.

The decision problem is composed of a matrix of m maintenance approaches rated on a set of n failure causes (criteria) that are applicable to the case in question. $w ̃ ={w_{j}, for j=1,2,…,n}$ is a set of

Conclusions

The most cost-effective maintenance approach is the one that is able to provide and utilize the required information about the changes in the failure causes behavior related to machine condition, product quality, and the surroundings. Knowing more information about the changes in the failure causes enables the user to control and maximize the utilization of the component life. This results in minimizing the number of failure (towards zero) and planned replacements.

The main conclusion is that by

References (39)

B. Al-Najjar
Accuracy, effectiveness and improvement of vibration-based maintenance in paper mills; case studies
Journal of Sound and Vibration
(2000)
E. Carrasco et al.
Rule-based diagnosis and supervision of a pilot-scale wastewater treatment plant using fuzzy logic techniques
Expert Systems with Applications
(2002)
R. Dekker
Applications of maintenance optimization modelsa review and analysis
Reliability Engineering and System Safety
(1996)
C. Gits
Design of maintenance concepts
International Journal of Production Economics
(1992)
G. Liang
Fuzzy MCDM based on ideal and anti-ideal concepts
European Journal of Operational Research
(1999)
S. Martorell et al.
Age-dependent reliability model considering effects of maintenance and working conditions
Reliability Engineering and System Safety
(1999)
K. Mckone et al.
Total productive maintenancea contextual view
Journal of Operations Management
(1999)
L. Pintelon et al.
Maintenance management decision-making
European Journal of Operational Research
(1992)
M. Rausand
Reliability centered maintenance
Reliability Engineering and System Safety
(1998)
M. Roubens
Choice procedures in fuzzy multi-criteria decision analysis based on pair-wise comparisons
Fuzzy Sets and Systems
(1996)

M. Setnes et al.

Fuzzy arithmetic-based interpolative reasoning for nonlinear dynamic fuzzy systems

Engineering Application of Artificial Intelligence

(1998)

E. Triantaphyllou et al.

Development and evaluation of five multiattribute DM methods

International Journal of Approximate Reasoning

(1996)

Y. Wang et al.

Rolling contact fatigue failure modes of lubricated silicon nitride in relation to ring crack defects

Wear

(1999)

Y. Yang et al.

Application of a specialized capacitance probe in bearing diagnosis

Wear

(1999)

S. Zanakis et al.

Multi-attribute decision-makinga simulation comparison of select methods

European Journal of Operational Research

(1998)

B. Al-Najjar

Total quality maintenance an approach for continuous reduction in costs of quality products

Journal of Quality in Maintenance Engineering

(1996)

Al-Najjar, B., 1997. Condition-based maintenance: selection and improvement of a cost-effective vibration-based policy...

Al-Najjar, B., 1999. An approach for continuous reduction in LCC when using integrated vibration-based maintenance: a...

Al-Najjar, B., 2000a. Product quality problems can be detected earlier by vibration spectral analysis than by...

Cited by (368)

Towards intelligent industrial systems: A comprehensive survey of sensor fusion techniques in IIoT
2024, Measurement: Sensors
Industrial Internet of Things (IIoT) is systems aim to facilitate human monitoring and the direction of efficient production of goods in industrial settings by linking a wide variety of intelligent devices such as sensors, actuators, and controllers. This is achieved by utilizing Internet of Things (IoT) to diagnose a problem with a specific IIoT part is to employ a basic diagnostic technique that's based on models and data. Physical models, signal patterns, and machine-learning strategies must be adequately built to account for system challenges. Another factor that could lead to an exponential rise in complexity is the ever-increasing interconnections between different electronic hardware. The knowledge-based defect diagnosis methods boost interoperability in the operation. Users don't need to be experts in the field to benefit from the system's high-level thinking and response to their queries. So, in advanced IIoT systems, a knowledge-based fault diagnostic approach is favored over traditional model-based and data-driven diagnosis methods. The goal of this study is to evaluate recent improvements in the design of knowledge-based defect detection in the context of IIoT systems, deductive and inductive reasoning, and many other forms of logical reasoning. IIoT-based systems have revolutionized industrial settings by connecting intelligent devices such as sensors, actuators, and controllers to enable efficient production and human monitoring. In this survey paper, we explore machine learning-based sensor fusion techniques within the realm of Industrial Internet of Things (IIoT), addressing critical challenges in fault detection and diagnosis.
A Fuzzy DEMATEL framework for maintenance performance improvement: A case of Moroccan Chemical Industry
2023, Journal of Engineering Research (Kuwait)
Maintenance performance has vital importance for enterprises to continue their operations without any interruption. The satisfaction of stakeholders and the achievement of strategic goals in a manufacturing organization are highly dependent on effective maintenance performance. A good management system is essential to achieve the desired level of performance. A good management system could be divided into two main parts. The first part consists of identifying and determining the most relevant indicators for maintenance. The determined indicators have to be measured to offer a comprehensive examination of their performance. The second part consists of improving the maintenance performance; however, from the multi-criteria aspect, system performance improvement requires simultaneously various limited sources such as time, resources, and skills. Therefore, improving maintenance performance needs to assign priority to the most critical indicators to use limited resources effectively; however, this is not easy to achieve. Furthermore, the benefit of such efforts may be less than the expected level. In this context, this paper proposes an approach to improve maintenance performance based on the Fuzzy DEMATEL method. The proposed method identifies and priorities the most sufficient indicators to improve overall maintenance performance of an enterprise. Consequently, DMs can put in place the most appropriate action plan, which allows an effective and efficient enhancement of the maintenance performance. Then, the proposed method is implemented in the case of Moroccan Company which is one of the leaders in the chemical industry. The results of this research allow DMs to develop the most advantageous action plan for effective and efficient improvement of both local and global maintenance performance in the company.
Towards a smart workflow in CMMS/EAM systems: An approach based on ML and MCDM
2022, Journal of Industrial Information Integration
In the context of Industry 4.0, process automation and predictive maintenance play an essential role. There is a need to provide more effective and faster maintenance through the integration of industrial tools and processes, to support manufacturing operations, in the perspective of integration standards and architectures. In a typical maintenance system, registration and maintenance requests are made through maintenance orders, which consist of a standard form and usually are created and filled manually. However, predictive maintenance requires a higher level of automatization, from data acquisition to maintenance order generation in a Computerized Maintenance Management System (CMMS) / Enterprise Asset Management (EAM). The proposal is to automate the process of generating maintenance orders, providing for automated form completion. At the physical level, assets are monitored by sensors, and, based on a set of rules, the respective predictive maintenance order will be issued in CMMS/EAS. Maintenance orders may contain variable fields according to each asset, so Machine Learning (ML) and Multicriteria Decision Making (MCDM) will be applied to fill in these fields, as well as the allocation of the maintenance orders to the maintainer that best fit for the maintenance specification. This automatic process will assist the maintenance workflow, leading to a Smart Workflow concept. A serial and parallel framework are presented, the former consists in applying TOPSIS (MCDM method) to extract features for the use in ML classification, in order to automatically fill in the appropriate form fields. The latter consists in a classification using both methods (ML and MCDM), where TOPSIS performs the initial classification, and if the alternatives ranking scores are close to each other, ML is used for more accurate classification. A case study was carried out in a Brazilian company that develops a CMMS/EAM system, distributed worldwide, and the results demonstrate that the concept of Smart Workflows is valuable, simplifying and enhancing maintenance processes.
Strategical selection of maintenance type under different conditions
2023, Scientific Reports
Straightening machine preventive maintenance intervention plan based on AHP: a case study in a steel company in Brazil
2023, Operations Management Research
RBM-MCDM framework for optimization of maintenance and inspection intervals of small unmanned aircrafts
2023, Journal of Quality in Maintenance Engineering

View all citing articles on Scopus

View full text

Selecting the most efficient maintenance approach using fuzzy multiple criteria decision making

Abstract

Introduction

Section snippets

Maintenance approaches

Criteria to compare maintenance approaches

Fuzzy logic and multiple criteria decision making (MCDM)

Evaluation methodology

Conclusions

Journal of Sound and Vibration

Expert Systems with Applications

Reliability Engineering and System Safety

International Journal of Production Economics

European Journal of Operational Research

Reliability Engineering and System Safety

Journal of Operations Management

European Journal of Operational Research

Reliability Engineering and System Safety

Fuzzy Sets and Systems

Engineering Application of Artificial Intelligence

International Journal of Approximate Reasoning

Wear

Wear

European Journal of Operational Research

Total quality maintenance an approach for continuous reduction in costs of quality products

Journal of Quality in Maintenance Engineering