Search results

The purpose of this paper is to perform an extensive literature review in the area of decision making for condition-based maintenance (CBM) and identify possibilities for proactive online recommendations by considering real-time sensor data. Based on these, the paper aims at proposing a framework for proactive decision making in the context of CBM.

Starting with the manufacturing challenges and the main principles of maintenance, the paper reviews the main frameworks and concepts regarding CBM that have been proposed in the literature. Moreover, the terms of e-maintenance, proactivity and decision making are analysed and their potential relevance to CBM is identified. Then, an extensive literature review of methods and techniques for the various steps of CBM is provided, especially for prognosis and decision support. Based on these, limitations and gaps are identified and a framework for proactive decision making in the context of CBM is proposed.

In the proposed framework for proactive decision making, the CBM concept is enriched in the sense that it is structured into two components: the information space and the decision space. Moreover, it is extended in a way that decision space is further analyzed according to the types of recommendations that can be provided. Moreover, possible inputs and outputs of each step are identified.

The paper provides a framework for CBM representing the steps that need to be followed for proactive recommendations as well as the types of recommendations that can be given. The framework can be used by maintenance management of a company in order to conduct CBM by utilizing real-time sensor data depending on the type of decision required.

The results of the work presented in this paper form the basis for the development and implementation of proactive Decision Support System (DSS) in the context of maintenance.

With production systems become more digitized, data-driven maintenance decisions can improve the performance of production systems. While manufacturers are introducing predictive maintenance and maintenance reporting to increase maintenance operation efficiency, operational data may also be used to improve maintenance management. Research on the value of data-driven decision support to foster increased internal integration of maintenance with related functions is less explored. This paper explores the potential for further development of solutions for cross-functional responsibilities that maintenance shares with production and logistics through data-driven approaches.

Fifteen maintenance experts were interviewed in semi-structured interviews. The interview questions were derived based on topics identified through a structured literature analysis of 126 papers.

The main findings show that data-driven decision-making can support maintenance, asset, production and material planning to coordinate and collaborate on cross-functional responsibilities. While solutions for maintenance planning and scheduling have been explored for various operational conditions, collaborative solutions for maintenance, production and logistics offer the potential for further development. Enablers for data-driven collaboration are the internal synchronization and central definition of goals, harmonization of information systems and information visualization for decision-making.

This paper outlines future research directions for data-driven decision-making in maintenance management as well as the practical requirements for implementation.

As the world approaches a new millennium, more and more industrial and manufacturing processes are being computerized and rapid retrieval and use of necessary information is vital if an organization is to remain competitive. The present work develops a computerized decision support system to assist in maintenance planning. The system design and analysis, and the decision support system design and development are all developed in an object‐oriented environment. The support system is driven by maintenance performance indices. Both object‐oriented databases and relational databases are used, for transient and permanent entities respectively. A knowledge base with if‐then rules is developed for fault diagnosis and repair. The methodology was applied to a powder coating plant to develop its maintenance decision support system.

The purpose of this paper is to explore the applicability of the Decision Making Grid (DMG) and its usefulness, in practice, in the maintenance of rolling stock in the railway industry. The Class 319 fleet operated by First Capital Connect (FCC) is used to demonstrate the application of the DMG.

The level of use of the data recorded in the CMMS, in the decision making process for reviewing, and updating the maintenance policy, was established through discussions with senior management at FCC. Available decision support systems were then researched, with emphasis on the DMG concept. The advantages of using the DMG and its application in the real world using data for the Class 319 fleet were then explored and are discussed in this paper.

This paper discusses the value in applying the DMG concept in the decision‐making process for prioritising systems and the work that should be done to ensure the maintenance policy takes into account the performance of the units of rolling stock against the most important criteria for FCC. Through the research carried out, it was established that the existing CMMS already records the data required for the application of the DMG, although in itself, the CMMS does not have any decision support capabilities.

Although a number of different CMMSs are used in the railway industry, few or none of these are capable of providing decision support for maintenance. This paper explores the use of the DMG concept to demonstrate the use of data recorded in the CMMS to develop a more effective maintenance policy and to determine exactly which maintenance activities need to be carried out in order to remedy the worst performing systems in terms of the most important criteria as identified by the business.

This paper aims to present a dual-perspective framework for maintenance service delivery that should be used by manufacturing companies to structure and manage their maintenance service delivery process, using aggregated historical and real-time data to improve operational decision-making. The framework, built for continuous improvement, allows the exploitation of maintenance data to improve the knowledge of service processes and machines.

The Dual-perspective, data-based decision-making process for maintenance delivery (D3M) framework development and test followed a qualitative approach based on literature reviews and semi-structured interviews. The pool of companies interviewed was expanded from the development to the test stage to increase its applicability and present additional perspectives.

The interviews confirmed that manufacturing companies are interested in exploiting the data generated in the use phase to improve operational decision-making in maintenance service delivery. Feedback to improve the framework methods and tools was collected, as well as suggestions for the introduction of new ones according to the companies' necessities.

The paper presents a novel framework addressing the data-based decision-making process for maintenance service delivery. The D3M framework can be used by manufacturing companies to structure their maintenance service delivery process and improve their knowledge of machines and service processes.

The purpose of this paper is to present the development of a maintenance engineering policy in the context of a decision support model based on a production machine process perspective.

The structure of the policy is called the maintenance decision support (MDS) model, which consists of three steps: initial setup, deterioration monitoring, and decision making. A detailed presentation of each step of the proposed model together with a real case example from the pulp manufacturing industry proves the applicability of the model.

Validation of the proposed MDS model is as follows. In Task 1 of Step 1, the cutting, sealing, and perforating line processes are classified as critical machining processes. The analysis of Task 2 of Step 1 found that cutting knife, bearing, and motor are classified as the components that most possibly contribute to the cutting appearance quality. In Task 3 of Step 1, it was found that the cutting knife is classified as a maintenance-significant component with non-repairable and single-component type characteristics. The result of Step 2 suggested that at the 29th hour of operating time, the decision of do-something was suggested. In the following step (Step 3), for the case of the cutting knife, which has been classified as a non-repairable type component, the decision to perform preventive replacement of cutting knife is recommended to be carried out at the 29th hour of operating time.

The uniqueness of this model is that it systematically considers different machinery component(s) characteristics, including single- and multiple-component cases, repairable and non-repairable types, and functional or/and physical failure types, to make maintenance decisions.

The proposed MDS model provides a systematic guideline for identifying, evaluating, and monitoring, which makes maintenance-related decisions. Three significant maintenance decisions can be determined based on the proposed MDS model, which includes an appropriate time-to-perform maintenance, correct maintenance actions to be performed, and the right component required for maintenance (for multi-component cases).

One of the vital elements in considering the production machine process perspective toward the development of the MDS model is the need to use product output/quality characteristics for machine deterioration-monitoring and decision-making processes.

The purpose of this paper is to increase productivity through smart maintenance planning by including productivity as one of the objectives of the maintenance organization. Therefore, the goals of the paper are to investigate existing machine criticality assessment and identify components of the criticality assessment tool to increase productivity.

An embedded multiple case study research design was adopted in this paper. Six different cases were chosen from six different production sites operated by three multi-national manufacturing companies. Data collection was carried out in the form of interviews, focus groups and archival records. More than one source of data was collected in each of the cases. The cases included different production layouts such as machining, assembly and foundry, which ensured data variety.

The main finding of the paper is a deeper understanding of how manufacturing companies assess machine criticality and plan maintenance activities. The empirical findings showed that there is a lack of trust regarding existing criticality assessment tools. As a result, necessary changes within the maintenance organizations in order to increase productivity were identified. These are technological advancements, i.e. a dynamic and data-driven approach and organizational changes, i.e. approaching with a systems perspective when performing maintenance prioritization.

Machine criticality assessment studies are rare, especially empirical research. The originality of this paper lies in the empirical research conducted on smart maintenance planning for productivity improvement. In addition, identifying the components for machine criticality assessment is equally important for research and industries to efficient planning of maintenance activities.

The aim with this paper is to describe current IT practices within maintenance in Swedish industry, and to outline the future possible developments.

The study is performed as a web‐based questionnaire survey consisting of 71 participants. A systems perspective is applied for capturing the most relevant aspects of IT utilisation.

The IT practices are characterised by high use of business‐specific IT solutions, low use of company‐wide IT solutions, low IT intensity and the client‐server architecture is dominating. The purchase decision and ownership of IT is to high extent tied to the maintenance function. Moreover, IT systems are apprehended as beneficial and connected to real needs. The findings imply a decentralised IT governance form and a mainly vertical (functional) IT support.

The socio‐technical approach suggested in this paper helps us to identify which areas to study, and also shows the tight interrelationship between different factors, layers and systems.

The study results could be used for benchmarking purposes or to highlight state‐of‐the‐art of IT utilisation in maintenance, and thereby set the topic on the corporate agenda.

Studies describing IT utilisation within maintenance in the form of case studies and surveys exist, but they mainly focus on one aspect. This study approached the problem from a socio‐technical perspective, covering several aspects connected to IT utilisation.

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.

Competitiveness has forced companies to improve the overall performance of the business. In the area of maintenance, much has been written about strategies, such as total productive maintenance or reliability centred maintenance, in order to increase the reliability and therefore capacity of the industrial plants in their quest for world‐class maintenance. However, if a strategy is to be effective, it must be supported with an invaluable resource, information. In the present work, the role of computerised maintenance management systems (CMMSs) is discussed as a powerful tool necessary for obtaining information from raw data and support the decision‐making process. Furthermore, a CMMS has been designed, developed, customised and implemented for a disc brake pad manufacturing company based in England. In addition, a maintenance maturity grid has been proposed to support the CMMS implementation. The grid shows that the complexity of the CMMS will increase as the maintenance function moves from a reactive to a proactive culture. The implemented CMMS aims to reduce total downtime and frequency of failures of the machines by improving the efficiency and effectiveness of the maintenance force. The computer program simplifies and reduces the time of data capture compared to the currently used paper‐based reporting system. It also provides the maintenance planners with a platform for decision analysis and support often ignored in the commercial CMMSs available in the market.