Data-driven asset management and decision support for maintenance
[Open soon]
Work description
The work is framed within the AI4WIND project and focuses on asset management associated with wind turbine blades, which are characterised by demanding operating conditions and high criticality in terms of availability, safety, and energy performance. The central objective is to develop data-driven approaches to support decision-making in the monitoring and management of wind energy assets, by exploiting operational data, structural condition data, and advanced sensing data to improve reliability, availability, and economic efficiency throughout the life cycle of the blades. The work integrates the analysis of failure modes and structural degradation, the use of monitoring data from optical sensors, SCADA systems, and inspection reports, as well as the development of artificial intelligence models for early damage detection, prediction of degradation evolution, and estimation of the remaining useful life of the assets. Additionally, it includes the development of user-oriented alerting and decision-support strategies, including dashboards and intuitive interfaces, with the aim of facilitating the interpretation of information by operators, maintenance managers, and decision-makers. In particular, the aim is to assess the impact of these solutions on the overall performance of wind energy assets, including availability, annual energy production, operation and maintenance costs, risk of unplanned failures, and extension of blade lifetime. The project will thus contribute to the development of advanced capabilities in condition monitoring, predictive maintenance, decision support, and asset management in the context of renewable energy systems.
Academic Qualifications
PhD degree in Industrial Engineering and Management, Mechanical Engineering, Electrical Engineering, Systems Engineering, or a related field.
Minimum profile required
PhD diploma certified by DGES.Experience in programming for data analysis, including the handling and analysis of real-world data, using tools such as Python, R, or equivalent. Experience in Project management.Proficiency in Portuguese and English.
Preference factors
- Experience with quantitative methods applied to engineering problems (e.g., optimisation, simulation, statistical analysis, or applied machine learning). - Participation in R&D projects with links to real-world or industrial contexts. - Relevant scientific publications in the areas of asset management, maintenance, reliability, or related fields.
Application Period
Since 06 Aug 2026 to 19 Aug 2026
[Open soon]
Centre
Industrial & Systems Engineering and Management