Project description
Multi-agent system for explainable anomaly detection in collaborative wind turbine operations
Wind energy is vital to the EU’s 2050 carbon-neutrality goal but faces challenges such as low reliability and high costs. Data-driven methods offer solutions, but many rely on centralised learning, leading to transparency issues, inconsistent accuracy and data privacy concerns for independent wind farms. Supported by the Marie Skłodowska-Curie Actions programme, the MEDIC project will develop a multi-agent explainable detection and inference framework for collaborative wind turbine systems. It will establish explainable turbine-level diagnostics, cross-turbine generalisation and privacy-preserving collaborative learning. The project will also outline the required resources, including system capacity, mentorship, data needs and experimental facilities. Overall, it will enhance scientific skills and advance wind energy monitoring, predictive maintenance and EU climate goals.
Objective
Wind energy is critical to achieving the European Union's carbon neutrality goal by 2050 and has experienced rapid development. Currently, there is a great challenge to large-scale wind farms due to low reliability and high operation and maintenance costs. Datadriven methods can offer a powerful and sustainable way to monitor wind turbine health. However, existing approaches primarily reliant on centralized learning, are often inadequate in providing the necessary transparency for actionable insights, fall short in consistently delivering accurate results across diverse operating conditions, and are unable to fully accommodate data privacy concerns of independent wind farms. To address these challenges, this project aims to develop a Multi-agent Explainable Detection and Inference framework for Collaborative wind turbine systems (MEDIC). Specifically, MEDIC includes three progressive tasks: 1) explainable turbine-level diagnostics powered by knowledge-guided graph modeling; 2) robust cross-turbine generalization through causal disentangled representation learning; 3) privacy-preserving collaborative learning facilitated by multi-agent federated learning. MEDIC will empower multiple agents (wind turbines) to collaboratively contribute to and benefit from a globally optimized anomaly detection model while maintaining control over their sensitive data. MEDIC specifies the resources needed for this project, including the quality and capacity of the host, mentors, data, and experimental facilities. This project will enhance the applicant's scientific skills and innovation capability, expand research horizons, and establish research collaborations. A two-way knowledge transfer approach in energy big data, distributed modeling and energy system analysis is proposed to ensure benefits between the
applicant and the host. MEDIC will make a significant contribution to the state-of-the-art in wind energy system monitoring and predictive maintenance and the EU climate goals.
Fields of science (EuroSciVoc)
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: The European Science Vocabulary.
This project's classification has been human-validated.
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: The European Science Vocabulary.
This project's classification has been human-validated.
Programme(s)
Multi-annual funding programmes that define the EU’s priorities for research and innovation.
Multi-annual funding programmes that define the EU’s priorities for research and innovation.
-
HORIZON.1.2 - Marie Skłodowska-Curie Actions (MSCA)
MAIN PROGRAMME
See all projects funded under this programme
Topic(s)
Calls for proposals are divided into topics. A topic defines a specific subject or area for which applicants can submit proposals. The description of a topic comprises its specific scope and the expected impact of the funded project.
Calls for proposals are divided into topics. A topic defines a specific subject or area for which applicants can submit proposals. The description of a topic comprises its specific scope and the expected impact of the funded project.
Funding Scheme
Funding scheme (or “Type of Action”) inside a programme with common features. It specifies: the scope of what is funded; the reimbursement rate; specific evaluation criteria to qualify for funding; and the use of simplified forms of costs like lump sums.
Funding scheme (or “Type of Action”) inside a programme with common features. It specifies: the scope of what is funded; the reimbursement rate; specific evaluation criteria to qualify for funding; and the use of simplified forms of costs like lump sums.
HORIZON-TMA-MSCA-PF-EF - HORIZON TMA MSCA Postdoctoral Fellowships - European Fellowships
See all projects funded under this funding scheme
Call for proposal
Procedure for inviting applicants to submit project proposals, with the aim of receiving EU funding.
Procedure for inviting applicants to submit project proposals, with the aim of receiving EU funding.
(opens in new window) HORIZON-MSCA-2025-PF
See all projects funded under this callCoordinator
Net EU financial contribution. The sum of money that the participant receives, deducted by the EU contribution to its linked third party. It considers the distribution of the EU financial contribution between direct beneficiaries of the project and other types of participants, like third-party participants.
PO1 2EG PORTSMOUTH
United Kingdom
The total costs incurred by this organisation to participate in the project, including direct and indirect costs. This amount is a subset of the overall project budget.