DOCTORAL CANDIDATE 05
ML Vibration-Based Algorithms for Damage Diagnosis of Smart FRP Structures
PRIYANKA KALYANI
EDUCATION
- B.Tech in Information Technology - Anna University, India
M.S. in Data Science - University of New Haven, USA
PhD in Materials Science and Engineering - Warsaw University of Technology, Poland
ABOUT
Priyanka Kalyani’s interest in artificial intelligence began during her undergraduate studies in Information Technology in Chennai, India, where a hands-on CNN-based project on natural disaster classification introduced her to the power of machine learning in real-world applications. This early exposure sparked a deeper curiosity about data-driven intelligence that continued to shape her academic choices.
After graduating, she gained industry experience at Cognizant Technology Solutions, which provided valuable exposure to applied technology. However, her growing interest in data science led her to seek deeper academic engagement, motivating her to move to the United States, where she completed a Master’s degree in Data Science, experimenting with machine learning across diverse domains. During this period, she discovered Structural Health Monitoring (SHM), an area that resonated with her interest in safety-critical systems and preventive intelligence; ultimately guiding her to doctoral research in Poland within the Marie Skłodowska-Curie ASSESS programme, where she now develops intelligent, data-driven methods for monitoring advanced structures.
Beyond her research, Priyanka enjoys video games, photography, and traveling to new places. She also values quieter moments, often spent with a good book and a cup of coffee, exploring virtual or fictional worlds that spark creativity and imagination.
02
Objectives
- Develop ML/AI algorithms for damage detection and localization.
- Create a data-driven SHM framework for composites.
- Link signal features with structural integrity and material behaviour.
- Validate methods in aerospace and renewable energy applications.
03
Expected results:
- A validated AI-based SHM methodology for composites.
- Early fault detection improving safety and reliability.
- Contribution to safer, smarter, and cost-efficient structures.
04
Planned secondments:
BARI, F. Ciampa, months 14-15 (2 months): field tests on smart sandwich composites.
IWES, S. Czichon, months 24-31 (6 months): field tests on GFRP wind turbine blades in real EOCs.
TUD, R. Groves, months 32-35 (4 months): field tests on CFRP wing panel.

