Browsing by Author "Lopes, Isabel S."
Now showing 1 - 4 of 4
Results Per Page
Sort Options
- Application of data mining in a maintenance system for failure predictionPublication . Bastos, Pedro; Lopes, Isabel S.; Pires, LuísIn industrial environment, data generated during equipment maintenance and monitoring activities has become increasingly overwhelming. Data mining presents an opportunity to increase significantly the rate at which the volume of data can be turned into useful information. This paper presents an architecture designed to gather data generated in industrial units on their maintenance activities, and to forecast future failures based on data analysis. Rapid Miner is used to apply different data mining prediction algorithms to maintenance data and compare their accuracy in the discovery of patterns and predictions. The tool is integrated with an online system which collects data using automatic agents and presents all the results to the maintenance teams. The purpose of the prediction algorithms is to forecast future values based on present records, in order to estimate the possibility of a machine breakdown and therefore to support maintenance teams in planning appropriate maintenance interventions.
- A decentralized predictive maintenance system based on data mining conceptsPublication . Lopes, Isabel S.; Pires, Luís; Bastos, PedroIn the last years we have assisted to several and deep changes in industrial manufacturing. Induced by the need of increasing efficiency, bigger flexibility, better quality and lower costs, it became more complex [1]. Enterprises had had the need to cope with market expectations, incorporating in their production philosophies new paradigms such as JIT- Just in time, MTOMake to order, Mass Customization, agile manufacturing or Lean Manufacturing, that allow them to satisfy markets with a big diversity of products and also big quantities, becoming therefore more competitive. All this complexity has caused big pressure under enterprises maintenance systems. Maintenance mission is to make equipment and facilities available when requested. Maintenance function, seen as a non value aggregator one, became more and more requested to contribute to cost reduction, based on bigger and consistent equipment reliability. This perspective is stressed when enterprises existing equipment has an advanced service life. It is expected a profusion of breakdowns at those scenarios and consequently a smaller usability of equipment driving to less productivity. From an economic perspective, maintenance function is seen to the enterprise as a cost [2]. In fact, experience shows that a major percentage of the overall costs of the business concerns with maintenance [3]. Considering this perspective, decreasing costs with equipment operationalization will increase maintenance productivity and consequently overall productivity [4].
- A maintenance prediction system using data mining techniquesPublication . Bastos, Pedro; Lopes, Isabel S.; Pires, LuísIn the last years we have assisted to several and deep changes in industrial companies, mainly due to market dynamics and the need to converge with a globalized and impatient world. These changes are transversal to the entire company also impacting on company maintenance function. In an attempt to eliminate faults and keep systems running without interruption, companies incorporated tools into their Information and Communication Technologies (ICT) systems. The benefits are clear in terms of resulting quality and in costs reduction, particularly those related with the data processing time and accuracy of the resulting knowledge. In their daily routine, companies produce and store endless and complex quantities of data of different nature, increasing the difficulty of use in real time. In this sense, considering the relevance of data collected on industrial plants, namely in its maintenance activities, it is intended with this paper to present a functional architecture of a predictive maintenance system, using data mining techniques on data gathered from manufacturing units globally dispersed. Data Mining will identify behavior patterns, allowing a more accurate early detection of faults in machines. The remote data collection is based on an intricate system of distributed agents, which, given its nature, will be responsible for remote data collection through the functional architecture.
- SPAMUF: a behaviour-based maintenance prediction systemPublication . Bastos, Pedro; Lopes, Isabel S.; Pires, LuísIn the last years we have assisted to several and deep changes in industrial manufacturing. Many industrial processes are now automated in order to ensure the quality of production and to minimize costs. Manufacturing enterprises have been collecting and storing more and more current, detailed and accurate production relevant data. The data stores offer enormous potential as source of new knowledge, but the huge amount of data and its complexity far exceeds the ability to reduce and analyze data without the use of automated analysis techniques. The paper addresses an organizational architecture that integrates data gathered in factories on their activities of reactive, predictive and preventive maintenance. The research is intended to develop a decentralized predictive maintenance system (SPAMUF—Prediction System Failures for Industrial Units Globally Dispersed) based on data mining concepts. Predicting failures more accurately will enable taking appropriate measures to increase reliability.