Short and long forecast to implement predictive maintenance in a pulp industry

Predictive maintenance is very important for effective prevention of failures in an industry. The present paper describes a case study where wood chip pump system was analyzed, and predictive model proposed. An Ishikawa diagram FMECA are used to identify possible causes failure. Chip Wood has several sensors installed monitor the working conditions state. authors propose variation exponential smoothing technique short time forecasting artificial neural network long forecasting. algorithms were integrated into dashboard online condition monitoring, users alerted when variable determined or predicted get out expected range. Experimental results show prediction errors general less than 10 %. proposed may be help monitoring asset, aiming at greater availability