An Innovative Development for Energy Security

9 February 2026

The results of a study conducted by Professor Yevgeniy Bodyanskiy of the Artificial Intelligence Department, in collaboration with colleagues from Ukraine, Poland, and Germany, have been published in the Q1 scientific journal Energies. The research focuses on an innovative real-time diagnostic method for wind turbine blades, opening new opportunities for maintaining energy infrastructure under critical conditions.

The authors propose a fundamentally new approach—the hypersector-based method grounded in fuzzy learning vector quantization (FLVQ). Unlike traditional methods, this approach models each defect class as a “hypersector” on a multidimensional sphere, significantly improving recognition accuracy and robustness to noise and disturbances.

The analysis relies on images captured by unmanned aerial vehicles (UAVs). This makes it possible to carry out regular inspections without endangering personnel or interrupting turbine operation.

The development is of strategic importance for both Ukraine and Europe. Under conditions of targeted attacks on energy infrastructure, the ability to rapidly detect and eliminate damage to restored facilities is critically important. Renewable energy—particularly wind power—is becoming a key element of resilience. This technology supports the long-term and stable operation of renewable energy sources, aligning with Ukraine’s and the EU’s course toward energy independence and sustainable development.

This work is a vivid example of how fundamental research in artificial intelligence can deliver practical solutions to global challenges, especially in the context of hybrid threats and the need for rapid adaptation of critical infrastructure.

The full text of the article “Hypersector-Based Method for Real-Time Classification of Wind Turbine Blade Defects” is available at:
https://doi.org/10.3390/en19020442

#SDG7