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

HORIZON.2.5HORIZON-RIAID: 101122329
EC Contribution
€38,974
Consortium Size
16 orgs
Summary

ICONIC aims to develop innovative physical and digital tools to achieve fundamental breakthroughs for the integrated control of wind farms, considering the whole physical system at farm, turbine, and component levels, in particular the complex aerodynamic interactions among turbines. ICONIC aims to increase farm-wide power production by 15-20% under optimal wind speeds and directions for typical wind farms suffering from wake effects, with a 3%-5% increase in annual energy production (AEP) considering all working conditions over the long term. It targets an LCOE reduction of at least 6% compared with the state-of-the-art control tools deployed in the current wind industry by improving farm-wide AEP and reducing operation & maintenance costs via leveraging the latest AI and digital technologies. Extensive validations for the integrated wind farm control solutions will be conducted via high-fidelity simulation models, experiments at a national-level wind tunnel, historical operational data at BP’s and C-Power’s wind farms, a unique collection of test rigs for critical turbine components at respective companies, and real-world wind farm field tests at C-Power. ICONIC’s integrated wind farm control system will contain (1) novel AI-based wind farm control system to unlock wind farms’ full potential; (2) novel data-enhanced wind turbine controllers to fulfil farm-level commands while balancing power generation and load mitigation; (3) an integration with digital twins (DTs) as extra support to improve control and reduce costs, which contains a first-ever farm-level DT for wind farm flow systems replicating detailed physical flow fields and an innovative turbine-level DT with critical component models for loading and lifetime estimations; (4) extensions of the solutions to future 20MW turbines. ICONIC will establish new knowledge and industrial leadership in key digital, enabling and emerging technologies, and deliver next-generation tools for wind farm operation.

Consortium (16)

Project Results (17)

Source: CORDIS, the EU research results database.

Publications (8)
Input torque estimation for wind turbine gearbox remaining useful life prediction​
Advanced structural dynamics course· 2025
Sterckx, I., Gryllias, K., Naets, F.
On the modeling errors of digital twins for load monitoring and fatigue assessment in wind turbine drivetrains
Wind Energy Science· 2025DOI
Felix C. Mehlan, Amir R. Nejad
Optimal control under safety constraints and disturbances: a multi-step, off-policy adaptive dynamic programming approach
Nonlinear Dynamics· 2025DOI
Jun Ye; Xiaowei Zhao; Yougang Bian; Manjiang Hu; Hongyang Dong
Physics-Based, Data-Augmented Model for Wind Turbine Control Design
Journal of Physics: Conference Series· 2025DOI
Jalal Heidari, Nezmin Kayedpour, Lieven Vandevelde, Guillaume Crevecoeur
Reference Model-Based Cyber-Attack Detection for Stochastically Uncertain Wind Turbine Systems
2025 IEEE Industry Applications Society Annual Meeting (IAS)· 2025DOI
Álvaro Martín Gómez, Sina Hassani, Szymon Gres, Rafal Wisniewski
Wind Farm Control via Offline Reinforcement Learning With Adversarial Training
IEEE Transactions on Automation Science and Engineering· 2025DOI
Yubo Huang, Xiaowei Zhao
Reconstruction of dynamic wind turbine wake flow fields from virtual Lidar measurements via physics-informed neural networks
Journal of Physics: Conference Series· 2024DOI
Jincheng Zhang, Xiaowei Zhao
Stochastic MPC with Focus on Probabilistic Constraints with Application to Wind Turbine Control
Torben Knudsen and Sina Hassani and Rafal Wisniewski
Deliverables (8)
Other Results (1)
Periodic Reporting for period 1 - ICONIC (Smart, Aware, Integrated Wind Farm Control Interacting with Digital Twins (ICONIC))