Increase of reliability of condition prognosis of offshore wind turbines by using data mining algorithms

Theme
XXL products
Project title Increase of reliability of condition prognosis of offshore wind turbines by using data mining algorithms (SteigProg)
Project duration 01.07.2010 – 30.06.2012
Project website http://www.steigprog.xxl-produkte.net
Download
The reliability of offshore wind turbines can be increased by condition prognosis using data-mining. By learning patterns of disturbances in existing data, these methods allow a multi-criteria prognosis of the machine condition. In the field of XXL products, the use of data-mining algorithms is useful instead of analytical methods. The large dimensions of XXL components are complicated for an analytic modeling, because they affect physical and geometric dependencies in a strong way (e.g. temperature-dependent expansion of components). XXL products are characterized by a large number of components and parameters that should be monitored simultaneously. In addition to that, there are dependencies regarding the maintenance strategy between the components. For example, in case of offshore wind turbines, gearbox, generator and wind load as well as interactions (e.g. influence of bearing lifetime inside the generator is affected by bearing damage in the gearbox) between these components have to be controlled. An analytical modeling is not suitable in this case. Data-mining algorithms can learn both, the geometric-physical and the maintenance-relevant dependencies without explicit modeling of human experts. For this reason, data-mining is an appropriate solution for a reliable, multi-criteria condition prognosis of offshore wind turbines.

Publications about the project

The range of structure sizes for industrial products produced today is increasingly expanding. This trend is evident in both small-scale (e.g. semiconductor applications) and large-scale (e.g. wind turbine rotors) products. While definitions already exist for smaller scale device structures, the conceptual distinction between conventional large products and large scale products is currently insufficient. In this study, we present a potential basis for the definition of large scale products. To achieve this, we derive hypotheses and examine these in the context of an empirical study using the examples of several sample products. It is shown that the transition from conventional products to large scale products is characterized by a disproportionate increase in product costs due to the augmentation of a characteristic product feature. Eventually we derive a proposed definition which characterizes large scale products in the field of production engineering.

xxl-product, large-scale, xxl, definition

A breakdown of a wind turbine entails high costs. The more reliable the prognosis of the condition of every single component is carried out, the better the maintenance can be planned. For example the maintenance could run in a time with low wind yield. Furthermore, impending breakdowns can be detected and avoided. Within the project “SteigProg” data-mining algorithms were analyzed for their ability to condition prognosis in wind turbines. An improved condition prognosis contributes a more efficient operation of wind turbines. Measurable savings result by minimizing downtimes, improved planning and shortening of maintenance operations.

condition prognosis, wind turbines

To meet the growing demand for energy, further developments are necessary in the field of renewable energies. In two research projects, engineers of IPH - Institut für Integrierte Produktion Hannover have investigated how to increase the efficiency of wind turbines.

xxl products, large-scale products, wind turbines, data mining

Sponsor

The project no. 11.2-76221-99-2/10 was part of the joint research project Innovations for the manufacturing of large scale products funded by the Ministry for the Economy, Labour and Transport of Lower Saxony and the Ministry for Science and Culture of Lower Saxony.

Your contact person

Benjamin Küster
M.Sc.

Manager production automation

Recommend us