Search results

The purpose of this paper is to develop a maintenance decision support system (DSS) framework using in-service lubricant data for fault diagnosis. The DSS reveals embedded patterns in the data (knowledge discovery) and automatically quantifies the influence of lubricant parameters on the unhealthy state of the machine using alternative classifiers. The classifiers are compared for robustness from which decision-makers select an appropriate classifier given a specific lubricant data set.

The DSS embeds a framework integrating cluster and principal component analysis, for feature extraction, and eight classifiers among them extreme gradient boosting (XGB), random forest (RF), decision trees (DT) and logistic regression (LR). A qualitative and quantitative criterion is developed in conjunction with practitioners for comparing the classifier models.

The results show the importance of embedded knowledge, explored via a knowledge discovery approach. Moreover, the efficacy of the embedded knowledge on maintenance DSS is emphasized. Importantly, the proposed framework is demonstrated as plausible for decision support due to its high accuracy and consideration of practitioners needs.

The proposed framework will potentially assist maintenance managers in accurately exploiting lubricant data for maintenance DSS, while offering insights with reduced time and errors.

Advances in lubricant-based intelligent approach for fault diagnosis is seldom utilized in practice, however, may be incorporated in the information management systems offering high predictive accuracy. The classification models' comparison approach, will inevitably assist the industry in selecting amongst divergent models' for DSS.

The present study empirically compares maintenance practices under asset performance management (APM), employed by firms in developed and developing countries (Belgium and Kenya, respectively).

Empirical observations and theoretical interpretations on maintenance practices under APM are delineated. A comparative cross-sectional survey study is conducted through an online questionnaire with 151 respondents (101 Kenya, 50 Belgium). Descriptive statistics and inferential statistics like independent t-test and phi coefficient were used for analyzing the data.

In both countries, reduction of maintenance and operational budget, return on assets, asset ageing and compliance aspects were established as critical factors influencing the implementation of asset maintenance and performance management (AMPM). A significant difference in staff competence in managing vibration, ultrasound and others like predictive algorithms was found to exist between the firms of the two countries. The majority of firms across the divide utilize manual and computer-based tools to integrate and analyse various maintenance data sets, while standardization and maintenance knowledge loss were found to adversely affect maintenance data management.

The study findings are based on the limited number of returned responses of the survey questionnaire and focused on only two countries representing developed and developing economies. This study not only provides practitioners with the practical guidelines for benchmarking, but also induces the need to improve the asset maintenance strategies and data application practices for asset performance management.

The paper provides insights to researchers and practitioners in the articulation of imperative effective maintenance strategies, benchmarking and challenges in their implementation, considering the different operational context.

The paper contributes to theory and practice within the field of AMPM where no empirical research comparing developed and developing countries exist.

Big data and related technologies are expected to drastically change the way industrial maintenance is managed. However, at the moment, many companies are collecting large amounts of data without knowing how to systematically exploit it. It is therefore important to find new ways of evaluating and quantifying the value of data. This paper addresses the value of data-based profitability of maintenance investments.

An analytical wasted value of data model (WVD-model) is presented to quantify how the value of data can be increased through eliminating waste. The use of the model is demonstrated with a case example of a maintenance investment appraisal of an automotive parts manufacturer.

The presented model contributes to the gap between the academic research and the solutions implemented in practice in the area of value optimization. The model provides a systematic way of evaluating if the benefits of investing in maintenance data exceed the additional costs incurred. Applying the model to a case study revealed that even though the case company would need to spend more time in analyzing and processing the increased data, the investment would be profitable if even a modest share of the current asset failures could be prevented through improved data analysis.

The model is designed and developed on the principle of eliminating waste to increase value, which has not been previously extensively discussed in the context of data management.

While the petroleum industry remains to be the main source of energy in the world, it is responsible for a large amount of resource consumption, environmental emission and safety issues. In this industry, most of the refinery equipment are running out of their designed life cycle, leading to many challenges regarding equipment reliability, products quality, organizations’ profitability, human resources safety and job satisfaction, and environmental pollution, which affects not only the human resources of the refinery but also the people who live in the vicinity. This study aims to model and simulate the maintenance system of an oil refinery to reduce the rotating equipment’s downtime while simultaneously considering the three pillars of sustainability.

Considering the complexity of the system and its inherent dynamism, System Dynamics (SD) approach is applied to model and simulate the maintenance system of an oil refinery, aiming at reducing equipment’s downtime considering the three pillars of sustainability simultaneously. As a case study, the maintenance system of rotating equipment in the Abadan oil refinery of Iran is investigated.

Individual policies are investigated and categorized into three main groups: economic, social and environmental. The dynamic nature of the system demonstrates that applying combinations of the policies would be more effective than performing individual ones or even a combination of all policies at the same time. The findings show that to manage the maintenance and reliability issues in complex industries, only operational level maintenance strategies would not be helpful; rather, a holistic strategic solution counting different suppliers or even the government policies supporting the operational level maintenance decisions would be effective.

This study is the first which brings the perspective of sustainable policy-making in the SD modeling of a complex maintenance system like that of the petroleum industry. The developed model considers economic, environmental and social objectives simultaneously. Besides, it reflects the role of different stakeholders in the system. Furthermore, the policy-making attempt is not limited to the operational level corrective and maintenance solutions; instead, a comprehensive, holistic view is applied.