idw – Informationsdienst Wissenschaft

Nachrichten, Termine, Experten

Grafik: idw-Logo
Science Video Project
idw-Abo

idw-News App:

AppStore

Google Play Store



Instance:
Share on: 
09/16/2025 10:19

Optimizing the performance potential of wind turbines: LATODA and Fraunhofer IWES develop AI analysis method

Inna Eck Presse- und Öffentlichkeitsarbeit
Fraunhofer-Institut für Windenergiesysteme IWES

    In the "WindKI" research project, the Fraunhofer Institute for Wind Energy Systems IWES and the AI company LATODA are developing a new method that detects performance losses in wind turbines at an early stage. The aim of the multi-year project is to implement an AI-supported diagnostic system that will enable objective and data-driven performance optimization of the turbines. The project is funded by the German Federal Ministry of Research, Technology and Space.

    Wind turbines do not always generate the amount of electricity predicted prior to their construction. There can be many reasons for this, such as unfavorable wind conditions, incorrect rotor blade angle settings, or aerodynamic effects in the wake of other wind turbines. To date, there is no reliable method for automatically detecting the causes of underperformance.

    Innovative solution using AI methods
    The WindKI project partners are specifically addressing these challenges: By combining measurement data, simulations, and artificial intelligence, they are creating a diagnostic system that uses heuristic algorithms and machine learning models to detect anomalies in the data set. The first models are based on high-resolution SCADA data sets from the 8-megawatt Adwen AD8 research turbine, which Fraunhofer IWES is providing for the project. On this basis, LATODA is developing an AI-based analysis system that automatically determines whether a turbine is operating as expected or is underperforming and suggests relevant parameters for optimization.

    The AI not only reports anomalies, but also provides clues as to their probable causes – from rotor blade settings to unfavorable operating conditions. This gives operators a tool that helps them identify and rectify problems more quickly. The methodology enables the wind industry to develop customer-oriented AI models based on any time series data.

    "The results of the project improve our understanding of the overall turbine dynamics," says Philipp Thomas, Group Manager Global Turbine Dynamics at Fraunhofer IWES. “The combination of expert knowledge and AI opens up new possibilities for the wind industry."

    LATODA Managing Director Daniel Hein also emphasizes the importance of the cooperation: "With our algorithm for analyzing sensor data, we are creating the basis for fast and reliable fault diagnosis. This will significantly reduce failures and reduced performance."

    The "WindKI" research project offers the opportunity to build a bridge between advanced AI techniques and conventional approaches in the field of wind energy. By linking domain knowledge from wind energy research with state-of-the-art machine learning methods, not only a concrete technical problem is solved, but also a framework for future, interdisciplinary research projects is created.
    ___

    About Fraunhofer IWES
    The Fraunhofer Institute for Wind Energy Systems IWES conducts application-oriented research for a sustainable future. The focus topics of the Fraunhofer IWES are offshore, hydrogen, test infrastructure and digitalization. The research work in these future-oriented key technologies plays a central role in the innovation process and strengthens the business location for the benefit of our society by transferring the research results to industry. More than 400 employees at nine locations are developing innovative methods to accelerate the expansion of the wind energy and hydrogen economy, minimize risks, and increase cost efficiency.

    About LATODA
    LATODA is a German AI pioneer specializing in the development of complex AI solutions. The company is a spin-off of the Philipps University of Marburg. The WindKI core team combines expertise from the fields of artificial intelligence, business informatics, business administration, wind energy and certification. LATODA has experience in the development of complex AI models, which are used, for example, in the detection and evaluation of damage to wind turbine blades.

    ___
    Contact persons Fraunhofer Institute for Wind Energy Systems IWES
    Dipl.-Ing. Philipp Thomas
    Group Manager Global Turbine Dynamics
    Phone +49 471 14290-381
    philipp.thomas@iwes.fraunhofer.de

    Yvonne Schink
    Manager Science Communications
    Phone +49 471 14290-189
    yvonne.schink@iwes.fraunhofer.de

    Contact persons LATODA
    Dr. Olaf Mager
    Press officer
    LATODA
    Phone +49 172 4039172
    olaf.mager@latoda.de

    Daniel Hein
    CEO
    LATODA
    Daniel.hein@latoda.de


    Contact for scientific information:

    Dipl.-Ing. Philipp Thomas
    Group Manager Global Turbine Dynamics, Fraunhofer IWES
    Phone +49 471 14290-381
    philipp.thomas@iwes.fraunhofer.de


    Images

    Fraunhofer IWES is providing data sets from previous measurement campaigns with the 8-megawatt Adwen AD8 research turbine for the development of the AI diagnostic method.
    Fraunhofer IWES is providing data sets from previous measurement campaigns with the 8-megawatt Adwen ...

    Copyright: © Fraunhofer IWES

    The diagnostic method flags anomalies in the operation of a wind turbine: The upper diagram shows anomaly detection using complex AI-supported methods. The Shap diagram (below) shows the influence of variables on AI decisions.
    The diagnostic method flags anomalies in the operation of a wind turbine: The upper diagram shows an ...

    Copyright: © LATODA


    Criteria of this press release:
    Journalists, Scientists and scholars
    Energy, Environment / ecology, Information technology, Oceanology / climate
    transregional, national
    Research projects, Transfer of Science or Research
    English


     

    Fraunhofer IWES is providing data sets from previous measurement campaigns with the 8-megawatt Adwen AD8 research turbine for the development of the AI diagnostic method.


    For download

    x

    The diagnostic method flags anomalies in the operation of a wind turbine: The upper diagram shows anomaly detection using complex AI-supported methods. The Shap diagram (below) shows the influence of variables on AI decisions.


    For download

    x

    Help

    Search / advanced search of the idw archives
    Combination of search terms

    You can combine search terms with and, or and/or not, e.g. Philo not logy.

    Brackets

    You can use brackets to separate combinations from each other, e.g. (Philo not logy) or (Psycho and logy).

    Phrases

    Coherent groups of words will be located as complete phrases if you put them into quotation marks, e.g. “Federal Republic of Germany”.

    Selection criteria

    You can also use the advanced search without entering search terms. It will then follow the criteria you have selected (e.g. country or subject area).

    If you have not selected any criteria in a given category, the entire category will be searched (e.g. all subject areas or all countries).