Dynamic tracking of modulated components under non-stationary random excitation
Application to automatic condition monitoring of failures in wind farms
The energy produced by wind farm is becoming more and more important worldwide. Its impact on the electrical grid grows every day. The economical and ecological interests reside in the availability of the equipment. Therefore, the capacity to plan the maintenance based on a reliable condition monitoring of the equipment is a crucial challenge. The KAStrion project takes up this challenge.
My thesis is part of KAStrion project and has the objective of designing and developing a part of the condition monitoring system with signal processing methods. More precisely, I work on the non-stationarity issue due to the wind variations and on the surveillance of the system along time. In the end, the main idea is to track relevant features in order to monitor the turbine components.