Image: Thampapon Shutterstock
A wind turbine predictive vibration analysis system that controls 1,400 wind turbines, 600 of them in Spain. The savings that can be obtained in a single detection can be greater than 100,000 euros per machine in the cost of repairs. This analysis system can be implemented in any wind turbine model.
Automation and “machine learning” are the key elements of this Endesa system, capable of processing up to 100,000 records per second.
Endesa is implementing a new predictive analysis system in its wind farms for the maintenance of wind turbines based on the vibration behavior of this equipment. The savings in repair costs can range from 15% to 95%.
The analysis system is carried out from Enel Green Power’s diagnostic room in Spain, from its Renewable Energy Department, which remotely supervises more than 1,400 wind turbines from Madrid, of which 600 belong to Endesa Spain and the rest of Enel Green Power and are located in Mexico, Chile, Italy, Greece, among other countries.
Predictive analysis is the early detection of failures in the main components of wind turbines, which allows the detection of failures that in some cases can be months in advance, this allows the planning of repairs to be scheduled for periods with fewer costs, minimizing losses due to turbine interruptions and thus improving the efficiency of the entire system.
Automation and “machine learning” consists of automatic machine learning, essential elements in this process, since the system supports a processing of up to 100,000 records per second.
Wind turbine components. Image: Andrea crisante Shutterstock
Endesa points out that the savings that can be achieved with just a correct detection, which can reach 100,000 euros in a single wind turbine, this in the case of defects in large components of wind turbines, in which repairs are considered large corrections and involve operations with cranes.
By having data from different models of turbines, better predictive analysis can be done in any wind farm in the world. From the “know-how” acquired, the information is shared with the manufacturers to make improvements in their models and an improvement in the learning curve is facilitated to make increasingly accurate predictions.
Endesa implemented the analysis system in all wind turbines that have less than 5 years of operation, the “Condition Monitoring System” provides supervision and control of the status of each machine.
More information: endesa.com