|UK Students, EU Students, International Students
|5th December 2023
|5th March 2024
Supervised by: Rasa Remenyte-Prescott (Faculty of Engineering, Resilience Engineering Research Group)
Aim: Explore how to integrate data-driven and analytical models for failure prognostics in wind energy applications
Harnessing wind energy through wind turbines has emerged as a vital element in the global shift towards sustainable and renewable energy sources. Wind turbines play a crucial role in the generation of clean and eco-friendly power, positioning them as integral components in the future energy landscape. Ensuring the long-term sustainability and cost-effectiveness of wind energy necessitates a dedicated focus on the structural integrity of wind turbines. Wind turbines, perpetually exposed to environmental elements such as wind, rain, sand, and other particulate matter, undergo natural wear and tear over time. This damage can lead to decreased energy output and increased operational costs due to reduced energy yields, potentially impacting the overall lifespan of turbines without preventive maintenance measures. Consequently, understanding the progression of damage and accurately predicting the service life of wind turbines are crucial considerations for operators and manufacturers in the wind energy industry. Various models, including physics-based and data-driven approaches, are employed to address these challenges. However, each approach has its limitations, with physics-based models being inherently incomplete, and data-driven models facing constraints related to the representativeness of training datasets. Combining the strengths of these approaches holds promise in mitigating their respective drawbacks, paving the way for more accurate and reliable predictions in wind turbine health condition and management.
The goal of this project is to construct a failure prognostics framework that integrates both physics-based and data-driven models. This developed framework will facilitate predictions related to the progression of various defects and the performance of wind turbines, such as how erosion damage growth affects annual energy production, or forecasting the overall life-expectancy of wind turbine components, for example. The integration will potentially be based on the utilization of failure data from periodic inspection and condition monitoring of wind turbines and the usage in asset management models.
Benefits of joining this project
This project provides an excellent opportunity for students to dig into the realm of wind energy from a holistic perspective. The incorporation of data-driven techniques, such as machine learning approaches, will enrich the scope of the project. Students engaged in this project will potentially have the chance to collaborate with industry partners in the wind energy sector, gaining valuable practical experience and fostering connections within the industry.
Summary: Open to UK/EU/overseas students. Look for funding sources at https://www.nottingham.ac.uk/pgstudy/funding/postgraduate-funding.aspx
Entry Requirements: Starting October 2024, we require an enthusiastic graduate with a 1st class degree in engineering, maths or a relevant discipline, preferably at Masters level (in exceptional circumstances a 2:1 degree can be considered).
For any enquiries about the project and the funding please email Rasa Remenyte-Prescott (email@example.com)
This studentship is open until filled. Early application is strongly encouraged.
Type / Role: