TWEED Project

TWEED is looking for 12 talented and motivated Doctoral Candidates (DCs) with the skills, knowledge and enthusiasm to work as part of a network to advance the field of digitalistion within the wind energy sector.

The “Training Wind Energy Experts on Digitalisation (TWEED)” Doctoral Network (DN) aims to train the next generation of excellent researchers equipped with a full set of technical and complementary skills to develop high-impact careers in wind energy digitalisation. 

Co-funded by the European Commission through the Horizon Europe Marie Sklodowska Curie Doctoral Networks Programme, the TWEED network offers 12 Doctoral Candidates (DCs) positions to provide high-level training in the new emerging research field of Wind Energy Data Science and Digitalisation.

An outstanding research-for-innovation programme, and a unique training programme that combines hands-on research training, interactive schools and hackathons, innovation management and placements with industry partner organisations has been designed for the DCs who will participate in the network. Alongside the exciting research topics related to wind energy data science, the research programme also includes state-of-the-art technology to develop a new Wind Energy Data Science Hub that will facilitate a virtual research environment to foster collaboration, data sharing and testing of innovative solutions to significantly increase the value of wind energy. 

The network will provide an interdisciplinary and inter-sectoral context to foster creativity in tackling wind energy data science and digitalisation challenges by developing solutions for commercial exploitation. 

DCs will be trained in business innovation to extend their focus beyond the academic context, to be able to identify added-value products or services with the guidance from established researchers and entrepreneurs. As a result, a research-for-innovation mindset will be developed to provide enhanced career prospects for the fellows, equipping them with a complete set of thematic, technological and innovation skills.

DCs are expected to i) conduct high quality, original academic research in the fields of Wind Energy, Digitalisation, Data Science and Computer Science, ii) participate in the network’s planned training-dissemination activities and mobility plan, iii) collaborate with fellow researchers, with the goal of advancing and promoting the network's objectives.

The most talented and motivated candidates will be selected to participate in the network's interdisciplinary collaborative research training, preferably starting in February 2024. The assessment shall be carried out by the TWEED recruitment team.

DC Project: 

Internal code of the position: DC9, Start: M13,M28

Host Institution: ANNEA.ai

Brief description of the project: 

The doctoral candidate will focus on advanced operational and maintenance (O&M) strategies for wind turbines with a specific emphasis on predictive maintenance and lifetime-conscious power curtailment. Leveraging machine learning and digital twin technologies, candidates will develop innovative, data-driven approaches to enhance turbine performance and reliability.

One key area of focus is creating explainable frameworks for predictive maintenance, utilizing SCADA data to identify potential component failures. This will enable more efficient scheduling of maintenance, reducing unplanned downtime and improving operational decision-making (of which candidates will contribute to this cause).

Candidates will also design and implement digital twin frameworks that integrate real-time data for continuous health monitoring of wind turbines and their components. This proactive monitoring will contribute to optimizing turbine performance while ensuring long-term reliability.

Additionally, the role involves developing probabilistic models to assess turbine fatigue and predict their remaining operational lifespan. By blending physics-based and data-driven techniques, candidates will support efforts to extend the turbines’ operational life, contributing to the sustainability of wind energy systems.

As part of their work, candidates will collaborate on a joint research paper to present the findings and outcomes of these innovative projects, contributing to cutting-edge developments in wind energy optimization.

Secondments: 

Two academic secondments. UNIZAR for training and collaboration on data science and completing mandatory PhD courses (Prof. Julio J. Melero). TU-DELFT for joint work on data-driven Digital Twins (Prof. Simon J. Watson).

Personal Supervisory Team: 

Main Supervisor: Dr. Maik Reder

Co-Supervisors: Julio J. Melero (UNIZAR) and Simon J. Matson (TU-Delft)