Skip to main content


Photo of Dr Ravi Pandit

Dr Ravi Pandit

Personal Homepage

Dr Ravi Pandit is an experienced researcher and currently working as a Research Felllow at the University of Exeter. Before that, I was working on EU H2020 projects: ROMEO & AWESOME. My PhD thesis titled “Gaussian Process Models for SCADA Data Based Wind Turbine Performance/Condition Monitoring”. I also won various prestigious grants/fellowships such as Marie Curie Fellowship (of value £224,325.00), Erasmus Mundas (of value € 129,000). My expertise includes data-driven frameworks for offshore wind such as big data analysis, condition monitoring, predictive maintenance, machine learning & deep learning and forecasting & predictions and as of now, has published more than 12 papers in highly ranked journals and has presented my research at several international conferences and workshops in these areas.  My PhD was on Gaussian Process models for SCADA data based Wind turbine performance/condition monitoring from the Wind Energy Systems CDT, hosted at the University of Strathclyde. Previously, I worked in AWESOME project funded by H2020 as Marie Curie Early Stage Researcher. I also worked as Visting Researcher in Wood group and University of Castilla-La Mancha (UCLM). Overall, I have more than 9 years of academics and research exepriences; with various reputed academics and industries through number of projects.

My further experience includes the role of Assistant Professor in Vellore Institute of Technology, Vellore and Jadavpur University where I used to teach and supervise the Undergraduate courses related to Electrical and Instrumentation Engineering.


Research Interests My research focuses on the wind energy area, both onshore and offshore. I have a particular interest in:  - Data-Driven Predictive maintenance  - Condition monitoring  -  Big data analysis  - Wind turbine performance optimizing.  - Wind turbine component failure predictions  - Machine learning for early failure predictions  - O&M cost modelling  - Wind turbine reliability