کنترل و راه اندازی یک برنامه نگهداری پیشگویانه با استفاده از یک سیستم شاخص ها

Predictive maintenance is one of the maintenance policies which is revolutionising the industry, due to the increase in security, quality and availability which is on offer to an industrial plant. However, the implantation of a predictive maintenance programme (PMP) is a strategic decision, and to date the analysis and study of questions relative to its setting up, management and supervision have not been carried out sufficiently. This paper proposes a system composed of indicators to control the setting up of PMPs which should facilitate the early detection of anomalies which can appear during setting up, thus avoiding the failure of these programmes. The system developed can be considered a predictive control of the PMP.

The increase in competition, globalisation of businesses, moves towards total quality management, constant technological changes, the supremacy of security and the implication of industry in environmental questions, are some of the factors which have brought about great changes in the structure of companies. These modifications have been carried over to the production area, as this is the one most directly involved in the efficiency and sustainability of the industrial processes. This concern has been transferred to maintenance, traditionally considered a source of costs, and now associated with more strategic issues, from an approximation based on the concept of sustainability, thereby pursuing the strategic consensus defined in Boyer et al. [1]. The implications in production and maintenance [2] suggest the need to change the focus of maintenance policies, traditionally centred on short term issues (use of resources, costs, etc.) towards the consideration of longer term goals (competitivity, sustainability and strategy). Predictive maintenance is a maintenance policy in which selected physical parameters associated with an operating machine are sensored, measured and recorded intermittently or continuously for the purpose of reducing, analysing, comparing and displaying the data and information so obtained for support decisions related to the operation and maintenance of the machine [3]. The benefits which can be obtained by introducing a predictive maintenance programme (PMP) are: an increase in the availability and safety of the plant, improvements in the quality of products [4] and of maintenance [5] as well as in the quantity and quality of the information available about industrial machinery, the increase in the programming capacity of maintenance activities, optimisation in management of the store for spare parts, support in the design and improvement of industrial machinery, [6], reduction of maintenance costs and capacity to research the root causes of breakdowns [7], improved image as the time needed preceding delivery to the client is reduced, etc. As explained in Christer et al. [8], it is necessary to identify maintenance needs in advance in order to maintain the normal functioning of production systems. Multiple models have been developed for the optimisation of maintenance. Cassidy et al. [9] propose a system whereby the decision-making centre can choose between multiple maintenance options, such as minimal repair of faulty components, replacement of faulty components and preventive maintenance. Murthy et al. [10] suggest a model to obtain optimum decision making in a maintenance service operation. McKone and Schroeder [11], describe the factors which contribute to the setting up of total productive maintenance programs (TPM), determining which contribute most to the development of maintenance systems. Deris et al. [12] and Wang [13] describe the timing of programmed replacement of components or consumables, and Sheu's [14] objective is similar in relation to minimum costs. Triantaphyllou et al. [15] develop a model for classifying different criteria relating to industrial maintenance, including availability, reliability, etc. Developments have also arisen concerning the decision to carry out the maintenance process in an individualised way, or co-ordinating maintenance activities in various components with the aim of minimising maintenance set-up costs, like the heuristic algorithm presented in Wijnmalen and Hontelez [16], in Wildeman et al. [17] and in Dijkhuizen and Harten [18]. However, whilst an effort has been made to construct mathematical models for optimising the preventive maintenance policy, we should point out the absence of tools for optimising and checking the predictive maintenance policy. The aim of this paper is to contribute to research by developing a model which will allow to evaluate the setting up of a PMP, an aspect that has not been analysed until now, as research in predictive maintenance has focused mainly on the development of new diagnostic techniques. Hence there is a marked lack of models for analysing the problems of PMPs with respect to evaluation, management and control. The model proposed will be applied in industrial maintenance, an area in which mathematical developments are of complex practical application [19] due to the lack of information, insufficient understanding of mathematical models by the staff required to apply them in an industrial plant, or to the difficulty of applying new models when the company does not provide additional resources to adapt to the new situation. This paper continues in Section 2 with an explanation of some concepts relating to problems in setting up PMPs. Section 3 explains the characteristics of PMPs. Section 4 includes a description of the indicators which make up the control system for setting up of PMPs. Section 5 presents the main empirical findings. Section 6 gives the conclusions.

The questions related to the structuring of the PMP in phases and the categorising of the technological levels of the PMP have not as yet been analysed despite the importance of controlling the set-up of a PMP. This paper represents a contribution to this topic. A control system for the set-up of a PMP composed of indicators has been developed. The indicators proposed have been classified in four categories: economic evaluation, external and internal quality of the PMP, organisational structure and evolution through time. These indicators facilitate the early detection of anomalies which can appear during set-up, thus avoiding the failure of these programmes. An exploratory study using the control system has been developed in some companies that have set up a PMP. This study demonstrates that a control system is a decision support system in the PMP set-up process. There are three directions for future research. Firstly, research on the question of developing standards for the setting-up process of the control system. This contributes to the successful setting up of PMPs. We should also point out the need to develop standards for the acquisition of the information that would allow quantifying of the control indicators. Secondly, additional research addressing the question of how to obtain the levels of control of the different indicators in relation to different industrial sectors. In so doing ideal values can be obtained for each control indicator depending on the type of company, since the need for a PMP and the available resources are very different depending on the type of company and in close relation to the sector of activity. Thirdly, the results of this paper have been obtained from programs of predictive maintenance based on vibration and lubricant analysis techniques. It would however be very interesting to incorporate new predictive techniques such as thermography, ultrasounds, noise and thickness analysis. These techniques are generating considerable interest due to the advantages they offer in thermal, nuclear, petrochemical, electrical plants, etc.