(UoM – IIT KGP) Developing Online FRA Transformer Winding Mechanical Incipient Fault Detection Methods through Transient Monitoring and Machine Learning

Power transformers in electrical power networks experience operational stresses such as short circuit currents and associated electromagnetic forces, making their reliable operation crucial for ensuring uninterrupted power supply. The excessive electromagnetic forces can lead to winding mechanical deformation and/or dislocations — termed as mechanical faults, responsible for over 50% of transformer failures globally, as reported in various international studies. Since the downtime associated with in-service transformer failure is costly, early detection of winding mechanical faults is paramount. The Frequency Response Analysis (FRA) method so far has demonstrated unparalleled sensitivity for fault detection in this regard. FRA is currently practiced offline, its online application could unlock significant potential, by enabling real-time transformer monitoring.

In an offline and onsite FRA test, the transformer’s frequency response is measured across a wide frequency range (typically from 2 Hz to 2 MHz) and compared to a healthy or reference trace, known as the transformer’s signature. Any deviation between the two responses indicates a potential mechanical fault. Faults locally alter the inductance and capacitance of the transformer equivalent circuit, causing changes in the measured frequency response, which forms the basis of fault detection by FRA

The fundamental approach to fault detection in the online FRA monitoring techniques to be developed, is likely to remain the same; however, its implementation presents several key technical challenges as outlined below, hence renders a PhD research project:

1) Developing wide frequency band sensors and measuring transients at high voltage terminals of a transformer

2) Exploring the constraints of network configurations on online FRA measurements, in contrast to offline transformer standalone test mode

3) Extracting the frequency response of transformer winding from online FRA measurements

4) Improving the quality and reliability of online FRA data, which is susceptible to noise and interference from the network connected

5) Extracting key features from online FRA data to enhance fault detection sensitivity

Exploring methods for online FRA measurements and developing a fault-detection algorithm using Machine-Learning (ML) are key objectives of this project. While significant research has advanced FRA offline testing, efforts to implement online FRA testing remain very limited. First, to address challenges in online FRA measurements at high voltage terminals, the approach should explore utilising system transient voltages and currents. Insights from offline measurements, both for a transformer in isolation and with external networks connected to transformer can help develop Machine Learning algorithms for extracting the transformer windings’ true frequency responses, denoising and data preparation for fault analysis.

Developing an online FRA transformer winding deformation detection method can prevent in-service transformer mechanical failures and significantly reduce the downtime of transformer and ensure uninterrupted electrical energy supply.

Before you apply  

We recommend you contact the supervisor(s) for this project before applying

How to apply 

Submit an online application through the IIT Kharagpur’s website https://international.iitkgp.ac.in/admission/jdp-uoman/ The site also lists required documents

Any questions about an application, please contact the team(s) by email: 

– University of Manchester: fse.doctoralacademy.specialistprogrammes@manchester.ac.uk

– IIT Kharagpur: ir-office@adm.iitkgp.ac.in 

 Eligibility 

1. Candidates may only apply for projects approved by the Joint Academic Board. 

2. For Indian residents, the programme is open to graduates B.Tech. or M.Sc./M.Tech. graduate from any Indian Institute of Technology (IIT) with a minimum CGPA of 7.5 on a scale of 10. 

3. For residents of other countries, it is open to graduates of Institutes/Universities within QS WUR of 500 (published in 2024) [link: https://www.topuniversities.com/world-university-rankings/2024]. 

4. Candidates must be able to undertake PhD studies at IIT Kharagpur from July 2025 or as soon as possible thereafter with no requirement for a (further) visa to study in India. 

5. Willingness to travel to the UK to undertake 2 years of study based at The University of Manchester if such travel is permitted by UK and India governments. 

6. Holds or expects to obtain a 2:1 class honours undergraduate degree or higher (or international equivalent – contact the Admissions Team for details). 

7. Ideally Preferably holds a master’s-level qualification at merit or distinction (or international equivalent – contact the Admissions Team for details). 

8. Demonstrable excellent communication skills, including in English language, a proficiency in which should be demonstrably indicated by meeting the requirements as indicated our English language requirements page [https://www.manchester.ac.uk/study/international/admissions/language-requirements/], and in particular securing an IELTS score of at least 6.5 overall with a minimum of 6.0 in each component OR securing a TOEFL iBT score of 90 with no less than 20 in each component equivalent or equivalent. The TOEFL/IELTS exam may be taken after the final selection and award of scholarship, and prior to joining IIT Kharagpur. 

9. For some projects an ATAS certificate may also be required by them. 

10. Demonstrate to fulfil The University of Manchester Faculty of Science and Engineering Postgraduate Researcher person specification: 

* Educational background matches research project. 

* Potential to form effective working relationships with a diverse range of people, including working inclusively and as part of a team. 

* Potential to take the initiative, lead on projects, and be proactive in prioritising a dynamic, agile and diverse workload. 

* Potential to develop understanding of complex problems, evaluate the strengths and weaknesses of a given scenario, and apply in-depth knowledge to address them. 

* Potential to develop expertise in new areas of the subject. 

* Evidence of an understanding of the proposed area of research, including knowledge of current challenges and opportunities. 

* An interest in continuous personal and professional development. 

* Potential to communicate ideas and conclusions, verbally and in writing, clearly and effectively to specialist and non-specialist audiences. 

* Preliminary knowledge of research techniques/track record of engaging with research. 

Equality, Diversity and inclusion 

Equality, diversity, and inclusion are fundamental to the success of The University of Manchester and central to our activities. Diversity strengthens our research community, enhancing creativity, productivity, quality, and societal impact. We encourage applicants from diverse backgrounds and all community sections, regardless of age, disability, ethnicity, gender, sexual orientation, or transgender status.

We also welcome those returning from career breaks or other roles and consider flexible study arrangements.

FSE_dualawards 

FSE_Kharagpur