IDI PROJECT 20190292

NEW MODEL FOR ANALYSIS AND INTELLIGENT PROCESSING OF BIG DATA FOR PREDICTIVE MAINTENANCE

The objective of the project was to develop a new intelligent predictive maintenance model based on Machine Learning techniques that allows detecting the causes and estimating the time until a failure appears. Thanks to this and the adaptation of the alarm thresholds of the different parts of the monitored equipment, decisions about maintenance can be made at the most appropriate time, also advising on the most recommended operating regime according to the current state of the equipment.

It combines different supervised and unsupervised learning algorithms with maintenance indicators (equipment parameters) chosen through a rigorous procedure and innovative, patented calculation models to estimate the causes of failures and the times they appear.

It aims to change current maintenance models (preventive or corrective) for a predictive one that maximizes operating times and reduces repair periods. Furthermore, this model will be much more reliable over time, since by having an increasing amount of data available, its predictions will be more accurate and closer to reality.

This project has been co-financed by the European Regional Development Fund (ERDF) through the Pluriregional Operational Program for Smart Growth. A way of making Europe.

Budget: 464,419.00 Euros.

CDTI Aid: Refundable loan: €290,261.87; Non-refundable loan: €104,494.28