Nikolaos Dervilis
Papers
2
Total Citations
82
H-Index
2
About
Dr. Nikolaos Dervilis is a leading researcher at the intersection of structural health monitoring (SHM) and non-destructive evaluation (NDE), with a growing reputation for pioneering the use of machine learning to automate damage detection in engineering structures. His highly cited 2020 paper, “Machine learning at the interface of structural health monitoring and non-destructive evaluation” (58 citations), provides a foundational framework for understanding how these two fields can be unified through data-driven approaches, particularly in ultrasonic and guided-wave inspection. Dr. Dervilis is also at the forefront of autonomous inspection, as demonstrated in his work “Autonomous ultrasonic inspection using Bayesian optimisation and robust outlier analysis” (24 citations). This research addresses the critical challenge of efficiently processing the vast datasets generated by robotic NDE systems, using Bayesian optimisation to intelligently guide data collection and robust outlier analysis to identify damage. By integrating machine learning with robotics, his work is making inspection faster, more reliable, and less dependent on human interpretation. Dr. Dervilis’s contributions are shaping the future of smart infrastructure, enabling structures to self-diagnose damage and ensuring safer, more resilient engineering systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2