The School of Engineering, Mathematics and Physics at the University of East Anglia (UEA) invites applications for a PhD Studentship titled “AI-Driven Fault Diagnosis for Wind Turbine Generators.” Primary supervision will be provided by Dr. Salman Abdi Jalebi.

Project Overview: Reliability is critical to the continued expansion of wind power, particularly for offshore installations, which contribute significantly to the UK’s electricity generation and are central to achieving net-zero targets and national grid resilience. Preventive maintenance enabled by condition monitoring systems (CMSs) plays a vital role in improving turbine reliability and availability while reducing operational costs and the levelised cost of energy.

However, the drivetrain—comprising the gearbox, generator, and power electronics—remains a primary source of failures, accounting for roughly one third of incidents and nearly half of maintenance costs in offshore turbines. Existing CMS solutions rely heavily on vibration measurements from accelerometers, which often suffer from low fault detection rates, false alarms, and an inability to detect faults early or identify electrical faults effectively. Interpreting electrical signatures of mechanical faults in real time presents an inherent complexity, creating a clear gap for advanced monitoring solutions.

This PhD project aims to address this gap by developing hybrid fault diagnosis methods that integrate analytical approaches based on drivetrain physical properties with AI-driven data analysis techniques. The work will encompass analytical studies, computer simulations, finite element (FE) analysis, and experimental development and validation to enhance fault detection and classification accuracy.

Programme & Mode of Study:

• Mode of Study: Full-time or part-time. • Target Start Date: February 1, 2027.

• Additional Information: UEA alumni may be eligible for a postgraduate tuition fee discount.

Eligibility Criteria:

• Minimum academic entry requirement: Upper Second-Class 2:1 Honours degree or equivalent in Electrical and Electronics Engineering, Mechanical Engineering, or Physics.

• Funding Status: Offered on a self-funded basis open to applicants worldwide who are self-funded or in the process of securing external funding

Required expertise/skills:

• Educational background in Electrical and Electronics Engineering, Mechanical Engineering, Physics, or a closely related discipline.

• Strong foundation or interest in condition monitoring systems, artificial intelligence/machine learning data analysis, and signal processing.

• Computational and modeling skills including finite element (FE) analysis, computer simulations, and analytical problem-solving.

• Practical capability or interest in conducting experimental development and validation.

Salary details: Not Specified / Self-Funded A bench fee is payable in addition to standard tuition fees to cover the cost of specialist equipment and laboratory facilities required for the research. Applicants should contact the primary supervisor for details regarding the applicable bench fee.

Application Deadline: November 30, 2026

Application Link