J. Garcke, R. Iza-Teran, M. Marks, M. Pathare, D. Schollbach, and M. Stettner.
Dimensionality Reduction for the Analysis of Time Series Data from
In M. Griebel, A. Schüller, and M. A. Schweitzer, editors,
Scientific Computing and Algorithms in Industrial Simulations: Projects and
Products of Fraunhofer SCAI, pages 317-339. Springer International
Publishing, Cham, 2017.
[ bib | DOI | http | .pdf 1 ]
We are addressing two related applications for the analysis of data from wind turbines. First, we consider time series data arising from virtual sensors in numerical simulations as employed during product development, and, second, we investigate sensor data from condition monitoring systems of installed wind turbines. For each application we propose a data analysis procedure based on dimensionality reduction. In the case of virtual product development we develop tools to assist the engineer in the process of analyzing the time series data from large bundles of numerical simulations in regard to similarities or anomalies. For condition monitoring we develop a procedure which detects damages early in the sensor data stream.