The EDI+ Fellowship Programme is open to participants in organisations engaged in research in the energy sector, including Higher and Further Education Institutions, businesses, government organisations, industry and third sector organisations.https://www.ediplus.ac.uk/training-programme/

Member, EPSRC Peer Review College

Dr Ravi Pandit is currently a Lecturer in Instrumentation and AI at the Centre for Life-cycle Engineering and Management within the School of Aerospace, Transport and Manufacturing, Cranfield University.Teaching: 1. Module leader of 'Through-life System Effectiveness' in the through-life System Sustainment MSc course. 2. Module leader of 'System availability and maintainability' in the Maintenance Engineering and Asset Management MSc courseResearch Areas/Interest Probabilistic machine learning, Bayesian non-parametric predictive models (e.g., Gaussian Process) Data analytics/ML for clean energy technologies (offshore winds, solar) Predictive maintenance & condition monitoring Forecasting and Prediction: long-term and short-term Big data statistical analysis: time-series, modelling

Topics Board Editors for 'Wind, Wave and Tidal Energy'

Dr Ravi Pandit was a Research Fellow in the Institute of Data Science and Artificial Intelligence (IDSAI) of the Computer Science Department. In this role, I am going to work closely with Turing Fellows to develop interdisciplinary research ideas (e.g, Energy, Transport, policy and so on) in collaboration with domain experts around the university, and will underpin early-stage studies leading to future bids for research funding.

I was a Research Associate in the department of Naval Architecture, Ocean and Marine Engineering. This post relates to the EU funded ROMEO project. The Romeo Project (Reliable OM decision tools and strategies for high LCoE reduction on offshore wind) is an initiative backed by the EU through its H2020 programme that fosters research and innovation, which aims to develop advanced technological solutions that enable the O&M costs of offshore wind power facilities to be reduced.My roles includes associated with ROMEO includes, - A flexible and interoperable Cloud and Internet of Things (IoT) platform will provide an advanced analytics ecosystem for failure diagnosis and prognosis models to better understand the real time behaviour of the main components of WTGs under operational conditions; - maximizing their life span and minimizing O&M costs. - Additionally, the project will develop third-generation condition monitoring systems for some WTG components and low-cost structural condition monitoring systems.- Actively coordinate and collaborate with partners Industries.

Ravi Pandit is a Marie Curie Early Stage Researcher employed at Electronic and Electrical Engineering department, University of Strathclyde, UK. He is working for AWESOME project (Horizon 2020) where, existing techniques of data analysis will be refined and new techniques developed. Particular emphasis will be given to the synthesis of results from different methods to provide enhanced reliability. Techniques will be assessed by application to large SCADA data sets supported by maintenance records. Key responsibilities associated with this work are as follows, 1. Wind turbine SCADA data set analysis. 2. Wind Turbine condition monitoring using SCADA data. 3. Developing a predictive model based on SCADA for improving reliability and fault detections. 4. Wind Turbine prognostics and health management. 5. Wind Turbine Asset management and Improvements. 6. Writing report (includes procedures, specifications and so on) & presenting to stakeholders.

Ravi, was a visiting researcher at the Renewable Energy Research Institute, Universidad de Castilla-La Mancha (UCLM), Spain. During this visit, Ravi worked with interdisciplinary teams (includes academics and industries) in a complex wind turbine condition monitoring problems that leads to improve the capabilities of algorithms to predict the failure quickly without any false positives. The key works completed during this visit are, 1. Use of SCADA data to develop advanced machine learning algorithms to find patterns and relationships among turbine operation parameters (e.g., rotor speed, blade pitch angle, wind shear and turbulence intensity) for the purpose of effective condition monitoring. 2. Improving the wind turbine reliability. 3. Wind Turbine O&M activities. 4. Extension of current knowledge to predict the deterioration and remaining useful life of wind turbines.

Ravi work closely related to wind resource assessment in which in depth analysis of large SCADA data set involves such as wind data gathering, data analyses, energy estimation .He is using Gaussian Process (a machine learning approach )for analysing these SCADA data and developing a effective GP model for anomaly detection under the guidance of Dr. Peter Clive (Senior scientist at wood group clean energy). Summary of nature of work Ravi involves are as follows, 1. Wind Turbine power performance assessment based on Gaussian Process; 2. Power curve modeling and verification; 3. Uncertainty analysis for anomaly detection and to assess risks; 4. Developing effective Power forecasting GP model for judging the energy potential of the new wind farm sites. 5. Developing effective Anomaly detection GP based model for the purpose of Condition monitoring of a wind turbine.

Ravi was a assistant Professor in Instrumentation and Electronics department where his area ofresearch and teachings are : Electrical measurements , Power Instrumentation, Sensors & itsapplicationsand Electrical machines.

Ravi was a assistant Professor in School of Electrical Engineering where his area of research andteachings are : Electrical Machines, Embedded system, Digital Electronics and Sensors and itsapplications .

Project title : Microcontroller based Patient monitoring system using wireless sensorsSummary : The aim of this study is to design and develop a low-power wireless patient monitoring system that should be easy to integrate with other technologies or infrastructures at a low cost, this transmitting unit should be able to replace many of the signal wires between biomedical sensors used for monitoring the patient and the sampling unit or supervision equipment. The model of hardware solution is combination of microcontroller (Atmega 32), Xbee & distance sensor. The communication between computer to computer or between computer to Xbee controlled by the Atmega 32 microcontroller. The results indicate that it is possible to continuously transmit a signal from shoe sensor through Atmega 32 by Xbee module without losing data. Apart from this the movement of patient can be monitored with the help of distance sensor. Here we use a sonar distance sensor which gives the distance of the object from the ground in terms of voltage.