Maintenance behaviour-based prediction system using data mining

In 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. The complexity of this new scenario has caused big pressure under enterprises production systems and consequently in its maintenance systems. Manufacturing systems recognize high level costs due equipment breakdown, motivated by the time spent to repair, which corresponds to no production time and scrapyard, and also money spent in repair actions. Usually, enterprises do not share data produced from their maintenance interventions. This investigation intends to create an organizational architecture that integrates data produced in factories on their activities of reactive, predictive and preventive maintenance. The main idea is to develop a decentralized predictive maintenance system based on data mining concepts. Predicting the possibility of breakdowns with bigger accuracy will increase systems reliability.