| Resumo: | The increase in automation provided by Industry 4.0 combined with the growing competitiveness in the market highlights the importance of intelligent maintenance. Companies must rethink current maintenance strategies in order to detect failures before they occur. This is the motto of predictive maintenance, through the analysis of data from equipment it is possible to predict when failures will occur and act in accordance with the forecast. This project, in addition to developing a platform capable of receiving and processing data in real-time from deferent equipment, also proposes a predictive maintenance approach based on time series segmentation. This new predictive maintenance approach was applied to data from a mechanical press, located in Bosch Thermotechnology, S.A., having achieved an efficiency of 90.91%. Throughout the document, all elements of the developed system are discussed in detail, from the data acquisition systems to sending forecasts on the condition of the equipment to a visualization platform.
|
|---|