Researchers at Groningen University have developed a low-cost, scalable method for detecting faults in wind turbine blades using 3D printing models, vibration analysis, and machine learning. This study demonstrates how to use scaled replicas of NREL 5MW blades manufactured in PLA to simulate damage scenarios and accurately classify support vector machines and K-nearest Neighbors with accuracy of 94% or more.
Wind turbine blades can withstand continuous mechanical stress and harsh environmental conditions, ensure structural integrity and reduce maintenance costs, and early damage detection is important. Traditional testing methods are often expensive and labor intensive. In this study, researchers used a Bambu Lab 3D printer to manufacture a 300 mm scaled version of the NREL 5MW blade, introducing five types of crack-like damage to critical areas such as root, midspan and transition zones.
To assess the structural impact of the failure, the team conducted finite element method (FEM) simulations and validated the results through experimental modal analysis using a hammer test setup. The resonant frequencies of vibration modes 3, 4, and 6 were found to be particularly sensitive to structural abnormalities. Frequency shifts of up to 3 Hz were observed in these modes when compared to healthy blades.
Functional extraction and machine learning
The researchers extracted features from the time and frequency domains and selected the one with the highest statistical significance through the ANOVA test. These features were then used to train several machine learning models, including Random Forest, Support Vector Machine, K-Nearth Neighbors, and Naive Bayes Classifiers. Among them, KNN and SVM achieved the highest classification accuracy of over 94%.
By combining 3D printing, simulation and machine learning, this study provides a reproducible and cost-effective method for structural health monitoring of wind turbine blades. The team plans to extend the methodology to multi-blade systems and more complex fault configurations, and aims to integrate it into real-time monitoring systems for predictive maintenance.
3D printing in wind energy research
This study is in line with recent developments in Wind Energy Research, including NREL's Made3D project. This explores how to enhance the structural and aerodynamic performance of turbine blades with additives and aerodynamic performance.
Furthermore, 3D printing is increasingly being used to extend the life cycle of wind turbine components. In recent cases, abolished wind turbine blades were reused in modular footbridges using additive manufacturing. The project introduced how reused blade materials and 3D printed connectors form sustainable private infrastructure, further highlighting the intersection of wind energy and digital manufacturing.
As additive technologies gain traction in large wind components, research into digital tools for fault detection and design optimization is increasingly relevant to the renewable energy sector
what 3D printing trends Do you need to be careful in 2025?
What do you think? The future of 3D printing Shape it up?
Don't forget to sign up to stay up to date with the latest 3D printing news 3D Printing Industry Newsletter Or follow us Twitteror like our page Facebook.
Why not subscribe to us while you're here YouTube channel? It features discussions, debriefs, video shorts and webinar replays.
The featured image shows the blade geometry of the scaled NREL 5MW blade. Images via Groningen University.
