/  12/01/2016  -  08/01/2019

ModernWindABS

Partners
ABO Wind AG, Bachmann electronic GmbH, Fördergesellschaft Windenergie und andere Erneuerbare Energien (FGW) e.V., Fraunhofer IML, Global Tech I Offshore Wind GmbH, Industrial Data Space e.V., Steag Energy Services GmbH, Trianel Windkraftwerk Borkum GmbH & Co. KG
Funding by

BMWi

Duration 01.12.2016 - 01.08.2019
Editers Volker Berkhout

 

Within the project ModernWindABS existing process descriptions for operation and maintenance (O&M) of wind turbines are to be extended into an data and process model which may serve as a basis for new value adding business models in the transition to an industry 4.0 environment.

Based on this model potential applications of the latest statistical, probabilistic and functional methods on the processes are to be analysed and evaluated. At least one application will be chosen and developed and tested as a demonstrator.

ModernWindABS is dedicated to show potentials and opportunities for future data based applications and business models. The project intends to pave the way for these application by identifying further standardisation needs. The start of the 2.75 year project is December 1st, 2016 and completion is planned for 31th, August 2019.

The various data sources in the operation of wind turbines are to be integrated into an information and process model based on existing scientific publications. This model may serve as reference for the horizontal and vertical integration of business processes in the transition to industry 4.0. Based on the model new services and business models are to be described and it also allows to identify challenges, research and industry collaboration requirements concerning data formats and standards.

Moreover, the application of the latest methods in data analysis on the tasks and problems is to be investigated. This includes algorithms of artificial intelligence such as  machine learning using neuronal networks or reinforcement learning. As a number of relevant input parameters in wind energy have a complex stochastic behaviour and considering the great innovation dynamic in this research area a large potential for optimisation and cost reduction is expected.