Smart, Aware, Integrated Wind Farm Control Interacting with Digital Twins (ICONIC)

Informations projet

ICONIC

N° de convention de subvention: 101122329

DOI

10.3030/101122329

Date de signature de la CE 30 Août 2023

Date de début 1 Decembre 2023

Date de fin 30 Novembre 2027

Financé au titre de

• Climate, Energy and Mobility

Coût total

€ 3 897 447,51

Contribution de l’UE

€ 3 897 447,50

Coordonné par

UNIVERSITEIT GENT
Belgium

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Livrables

Documents, reports (10)

Degradation models of critical components to assess their lifetime

Degradation models of critical components to assess their lifetime. It corresponds to T4.3: Degradation models to assess lifetime of critical components.

Physics-based, data-augmented model for WF control design

Physics-based, data-augmented model for WF control design. It corresponds to T3.1 Physics-based, data-augmented model for wind turbine control design.

A wind farm ancillary service algorithm with optimal fatigue distribution

A wind farm ancillary service algorithm with optimal fatigue distribution. It corresponds to T2.3: Ancillary service support with optimal fatigue distribution.

A multi-agent multi-layer DRL-based WF control framework

A multi-agent multi-layer DRL-based WF control framework. It corresponds to T2.2: A multi-agent, multi-layer, robust DRL framework to maximise farm-wide power production.

High-fidelity models of WT and its critical components

High-fidelity models of WT and its critical components. It corresponds to T4.2: High-fidelity models to predict the response of each wind turbine and each critical component to external wind/control loads.

A cybersecurity mechanism in wind farm control

A cybersecurity mechanism in wind farm control. It corresponds to T2.6: Solutions to ensure cybersecurity in wind farm control.

A control-oriented 3D dynamic WF wake model via CFD and deep learning with onshore & offshore case studies

A control-oriented 3D dynamic WF wake model via CFD and deep learning with onshore & offshore case studies. It corresponds to T2.1 with the same title.

A wind farm (WF) digital twin solution via physics-informed deep learning

A wind farm (WF) digital twin solution via physics-informed deep learning. It corresponds to T4.1: Wind farm flow digital twin via physics-informed deep learning.

ICONIC project identity, website, D&E&C plan

ICONIC project identity, website, D&E&C plan. It corresponds to T6.1. Stakeholder involvement, clustering and liaising activities, T6.2. Dissemination of innovation and research results, T6.3. Management and exploitation of innovation results and T6.4. Communication and outreach activities.

Stochastic and Tube MPCs for turbine control

Stochastic and Tube MPCs for turbine control. It corresponds to T3.2: Stochastic and tube MPCs for turbine control with load reduction.

Data sets, microdata, etc (1)

Flow field measurement dataset used for DT validations from wind tunnel experiments

Flow field measurement dataset used for DT validations from wind tunnel experiments. It corresponds to T5.1: Validation of the wind farm flow DT via wind tunnel experiments.

Publications

Peer reviewed articles (3)

Optimal control under safety constraints and disturbances: a multi-step, off-policy adaptive dynamic programming approach

Auteurs: Jun Ye; Xiaowei Zhao; Yougang Bian; Manjiang Hu; Hongyang Dong
Publié dans: Nonlinear Dynamics, 2025, ISSN 1573-269X
Éditeur: Springer
DOI: 10.1007/S11071-025-11329-3

On the modeling errors of digital twins for load monitoring and fatigue assessment in wind turbine drivetrains

Auteurs: Felix C. Mehlan, Amir R. Nejad
Publié dans: Wind Energy Science, Numéro 10, 2025, ISSN 2366-7451
Éditeur: Copernicus GmbH
DOI: 10.5194/WES-10-417-2025

Wind Farm Control via Offline Reinforcement Learning With Adversarial Training

Auteurs: Yubo Huang, Xiaowei Zhao
Publié dans: IEEE Transactions on Automation Science and Engineering, Numéro 22, 2025, ISSN 1545-5955
Éditeur: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TASE.2025.3548565

Conference proceedings (6)

Reference Model-Based Cyber-Attack Detection for Stochastically Uncertain Wind Turbine Systems

Auteurs: Álvaro Martín Gómez, Sina Hassani, Szymon Gres, Rafal Wisniewski
Publié dans: 2025 IEEE Industry Applications Society Annual Meeting (IAS), 2025
Éditeur: IEEE
DOI: 10.1109/IAS62731.2025.11061699

Reconstruction of dynamic wind turbine wake flow fields from virtual Lidar measurements via physics-informed neural networks

Auteurs: Jincheng Zhang, Xiaowei Zhao
Publié dans: Journal of Physics: Conference Series, Numéro 2767, 2024, ISSN 1742-6588
Éditeur: IOP Publishing
DOI: 10.1088/1742-6596/2767/9/092017

Estimating Tower Vibrations with Data-Driven Models: Possibility of Optimizing Control Actions to Reduce Loads on Wind Turbine

Auteurs: Jalal Heidari, Nezmin Kayedpour, Lieven Vandevelde and Guillaume Crevecoeur
Éditeur: Wind Energy Science Conference (WESC) 2025

Input torque estimation for wind turbine gearbox remaining useful life prediction​

Auteurs: Sterckx, I., Gryllias, K., Naets, F.
Publié dans: Advanced structural dynamics course, 2025
Éditeur: Technical University of Denmark (DTU)

Physics-Based, Data-Augmented Model for Wind Turbine Control Design

Auteurs: Jalal Heidari, Nezmin Kayedpour, Lieven Vandevelde, Guillaume Crevecoeur
Publié dans: Journal of Physics: Conference Series, Numéro 3025, 2025, ISSN 1742-6588
Éditeur: IOP Publishing
DOI: 10.1088/1742-6596/3025/1/012008

Stochastic MPC with Focus on Probabilistic Constraints with Application to Wind Turbine Control

Auteurs: Torben Knudsen and Sina Hassani and Rafal Wisniewski
Éditeur: 2025 American Control Conference (ACC)