Martin Bach-Andersen: Data are collected minute by minute from wind turbines around the world. This thesis represents a focused research effort into discovering new ways of processing these data streams in order to gain insights which can be used to lower the maintenance costs of wind turbines and increase the turbine availability.
First, it is demonstrated how simple sensor data streams can be leveraged based on more advanced data modeling techniques to provide warnings of a critical turbine bearing failure more than a month earlier compared to existing alarm systems.
Second, deep-learning based machine intelligence is shown to solve one of the most complex tasks for remote diagnostics on wind turbines, namely early fault identification based on analysis of complex vibration patterns. The system is in some cases able to detect the fault months earlier than human experts.
Wind farm owners and operators can utilize the outputs of such systems directly, to optimize the maintenance and keep the turbines running, which in the long term will make an addition to the effort in reducing the price of wind energy.
Effective start/end date 01/03/2014 → 15/11/2017
Published as PhD report: A Diagnostic and Predictive Framework for Wind Turbine Drive Train Monitoring
DTU Compute supervisor: Ole Winther