Fatigue Predictive Modeling of Composite Materials for Wind Turbine Blades Using Explainable Gradient Boosting Models
Source abstract
Abstract
Wind turbine blades are subjected to cyclic loading conditions throughout their operational lifetime, making fatigue a critical factor in their design. Accurate prediction of the fatigue performance of wind turbine blades is important for optimizing their design and extending the operational lifespan of wind energy systems. This study aims to develop predictive models of laminated composite fatigue life based on experimental results published by Montana State University, Bozeman, Composite Material Technologies Research Group. The models have been trained on a dataset consisting of 855 data points. Each data point consists of the stacking sequence, fiber volume fraction, stress amplitude, loading frequency, laminate thickness, and the number of cycles of a fatigue test carried out on a laminated composite specimen. The output feature of the dataset is the number of cycles, which indicates the fatigue life of a specimen. Random forest (RF), extreme gradient boosting (XGBoost), categorical boosting (CatBoost), light gradient boosting machine (LightGBM), and extra trees regressor models have been trained to predict the fatigue life of the specimens. For optimum performance, the hyperparameters of these models were optimized using GridSearchCV optimization. The total number of cycles to failure could be predicted with a coefficient of determination greater than 0.9. A feature importance analysis was carried out using the SHapley Additive exPlanations (SHAP) approach. LightGBM showed the highest performance among the models (R2 = 0.9054, RMSE = 1.3668, and MSE = 1.8682).
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Fatigue and fracture mechanics · Probabilistic and Robust Engineering Design · Wind Energy Research and Development
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Civil Engineering, Istanbul University-Cerrahpasa, 34320 Istanbul, Turkey
GameAbove College of Engineering and Technology, Eastern Michigan University, Ypsilanti, MI 48197, USA
College of IT Convergence, Gachon University, Seongnam 13120, Republic of Korea
Funding
Korea Institute of Energy Technology Evaluation and Planning (KETEP) · Ministry of Trade, Industry, and Energy, Republic of Korea
References (74)
Show source-provided references
1. Renewable and sustainable clean energy development and impact on social, economic, and environmental health10.1016/j.nexus.2022.100118 ↗
2. (2025, January 22). IRENA (2024)–Processed by Our World in Data. Installed Wind Energy Capacity. Available online: https://ourworldindata.org/grapher/cumulative-installed-wind-energy-capacity-gigawatts?country=~OWID_WRL.
3. Chaudhuri, A., Datta, R., Kumar, M.P., Davim, J.P., and Pramanik, S. (2022). Energy Conversion Strategies for Wind Energy System: Electrical, Mechanical and Material Aspects. Materials, 15.10.3390/ma15031232 ↗
4. Estimation of dynamic characteristics of a wind turbine blade10.1016/j.matpr.2022.08.025 ↗
5. World Wild Life (2025, January 23). The Energy Report. Available online: https://www.worldwildlife.org/publications/the-energy-report.
6. A critical review on environmental impacts of renewable energy systems and mitigation strategies: Wind, hydro, biomass and geothermal10.1016/j.scitotenv.2020.144505 ↗
7. Wind turbine vibration management: An integrated analysis of existing solutions, products, and Open-source developments10.1016/j.egyr.2024.03.014 ↗
8. Burton, T., Jenkins, N., Sharpe, D., and Bossanyi, E. (2011). Wind Energy Handbook, John Wiley & Sons Ltd.10.1002/9781119992714 ↗
9. Wind Turbine Blade Design10.3390/en5093425 ↗
10. Wind turbines dynamics loads alleviation: Overview of the active controls and the corresponding strategies10.1016/j.oceaneng.2023.114070 ↗
11. Wang, J., Liu, Y., and Zhang, Z. (2024). Fatigue Damage and Reliability Assessment of Wind Turbine Structure During Service Utilizing Real-Time Monitoring Data. Buildings, 14.10.3390/buildings14113453 ↗
12. Study of damage and repair of blades of a 300 kW wind turbine10.1016/j.energy.2008.02.002 ↗
13. Long-term mechanical properties of FRP tendon–anchor systems—A review10.1016/j.conbuildmat.2019.117017 ↗
14. Machine Learning Applications for a Wind Turbine Blade under Continuous Fatigue Loading10.4028/www.scientific.net/KEM.588.166 ↗
15. A machine learning-based fatigue loads and power prediction method for wind turbines under yaw control10.1016/j.apenergy.2022.120013 ↗
16. Miao, Y., Soltani, M.N., and Hajizadeh, A. (2022). A Machine Learning Method for Modeling Wind Farm Fatigue Load. Appl. Sci., 12.10.3390/app12157392 ↗
17. Yuan, X., Huang, Q., Song, D., Xia, E., Xiao, Z., Yang, J., Dong, M., Wei, R., Evgeny, S., and Joo, Y.-H. (2024). Fatigue Load Modeling of Floating Wind Turbines Based on Vine Copula Theory and Machine Learning. J. Mar. Sci. Eng., 12.10.3390/jmse12081275 ↗
18. Wind turbine fatigue reduction based on economic-tracking NMPC with direct ANN fatigue estimation10.1016/j.renene.2019.09.092 ↗
19. Estimation of probability distribution of long-term fatigue damage on wind turbine tower using residual neural network10.1016/j.ymssp.2023.110101 ↗
20. Long-term fatigue estimation on offshore wind turbines interface loads through loss function physics-guided learning of neural networks10.1016/j.renene.2023.01.093 ↗
21. Wu, J., Yang, Q., and Jin, N. (2023, January 29–31). Fatigue Load Prediction of Large Wind Turbine by Big Data and Deep Learning. Proceedings of the 2023 IEEE International Conference on Electrical, Automation and Computer Engineering (ICEACE), Changchun, China.10.1109/ICEACE60673.2023.10442226 ↗
22. Neural Network Optimization Algorithms to Predict Wind Turbine Blade Fatigue Life under Variable Hygrothermal Conditions10.3390/eng2030018 ↗
23. Reliability Analysis of Fatigue Failure of Cast Components for Wind Turbines10.3390/en8042908 ↗
24. Essential structure of S-N curve: Prediction of fatigue life and fatigue limit of defective materials and nature of scatter10.1016/j.ijfatigue.2020.106138 ↗
25. Yena Engineering (2025, January 20). Metal Fatigue–Wöhler Plot and Mechanisms. Available online: https://yenaengineering.nl/metal-fatigue-wohler-plot-and-mechanisms/.
26. Investigation of Fatigue Behavior of Glass Fiber Polyester Composites Reinforced at Different Ratios under Sea Water Effect
27. Hernandez-Sanchez, B.A., Miller, D., and Samborsky, D. (2018). SNL/MSU/DOE Composite Material Fatigue Database-Environmental Version 28E, Sandia National Lab.(SNL-NM).10.2172/1481599 ↗
28. Sarath, P., Reghunath, R., Haponiuk, J.T., Thomas, S., and George, S.C. (2023). Introduction: A journey to the tribological behavior of polymeric materials. Tribology of Polymers, Polymer Composites, and Polymer Nanocomposites, Elsevier.10.1016/B978-0-323-90748-4.00010-8 ↗
29. Effect of Fiber Orientation on the Fatigue Behavior of Steel Fiber-Reinforced Concrete Specimens by Performing Wedge Splitting Tests and Computed Tomography Scanning10.1186/s40069-023-00639-8 ↗
30. Fatigue response dependence of thickness measurement methods for additively manufactured E-PBF Ti-6Al-4 V10.1111/ffe.13461 ↗
31. Machine Learning: Algorithms, Real-World Applications and Research Directions10.1007/s42979-021-00592-x ↗
32. Aydın, Y., Işıkdağ, Ü., Bekdaş, G., Nigdeli, S.M., and Geem, Z.W. (2023). Use of Machine Learning Techniques in Soil Classification. Sustainability, 15.10.3390/su15032374 ↗
33. Optimizing artificial neural network architectures for enhanced soil type classification
34. Interpretable machine-learning models for maximum displacements of RC beams under impact loading predictions10.1016/j.engstruct.2023.115723 ↗
35. Explainable machine learning models for predicting the axial compression capacity of concrete filled steel tubular columns10.1016/j.conbuildmat.2022.129227 ↗
36. Phan, V.-T., Tran, V.-L., Nguyen, V.-Q., and Nguyen, D.-D. (2022). Machine Learning Models for Predicting Shear Strength and Identifying Failure Modes of Rectangular RC Columns. Buildings, 12.10.3390/buildings12101493 ↗
37. Aydın, Y., Bekdaş, G., Nigdeli, S.M., Isıkdağ, Ü., Kim, S., and Geem, Z.W. (2023). Machine Learning Models for Ecofriendly Optimum Design of Reinforced Concrete Columns. Appl. Sci., 13.10.3390/app13074117 ↗
38. Cakiroglu, C., Aydın, Y., Bekdaş, G., and Geem, Z.W. (2023). Interpretable Predictive Modelling of Basalt Fiber Reinforced Concrete Splitting Tensile Strength Using Ensemble Machine Learning Methods and SHAP Approach. Materials, 16.10.3390/ma16134578 ↗
39. Prediction of optimum design of welded beam design via machine learning10.20528/cjsmec.2024.03.001 ↗
40. Hu, T., Zhang, H., and Zhou, J. (2023). Prediction of the Debonding Failure of Beams Strengthened with FRP through Machine Learning Models. Buildings, 13.10.3390/buildings13030608 ↗
41. Aydın, Y., Cakiroglu, C., Bekdaş, G., and Geem, Z.W. (2024). Explainable Ensemble Learning and Multilayer Perceptron Modeling for Compressive Strength Prediction of Ultra-High-Performance Concrete. Biomimetics, 9.10.3390/biomimetics9090544 ↗
42. Shen, L., Shen, Y., and Liang, S. (2022). Reliability Analysis of RC Slab-Column Joints under Punching Shear Load Using a Machine Learning-Based Surrogate Model. Buildings, 12.10.3390/buildings12101750 ↗
43. Cooling load prediction of a double-story terrace house using ensemble learning techniques and genetic programming with SHAP approach10.1016/j.enbuild.2024.114254 ↗
44. Bekdaş, G., Aydın, Y., Işıkdağ, U., Nigdeli, S.M., Hajebi, D., Kim, T.-H., and Geem, Z.W. (2025). Shear Wave Velocity Prediction with Hyperparameter Optimization. Information, 16.10.3390/info16010060 ↗
45. Bekdaş, G., Aydın, Y., Nigdeli, S.M., Ünver, I.S., Kim, W.-W., and Geem, Z.W. (2025). Modeling Soil Behavior with Machine Learning: Static and Cyclic Properties of High Plasticity Clays Treated with Lime and Fly Ash. Buildings, 15.10.3390/buildings15020288 ↗
46. Random forests10.1023/A:1010933404324 ↗
47. Alpaydin, E. (2025, January 29). Introduction to Machine Learning. MIT Press. Available online: https://books.google.com.tr/books?id=NP5bBAAAQBAJ.
48. Zeini, H.A., Al-Jeznawi, D., Imran, H., Bernardo, L.F.A., Al-Khafaji, Z., and Ostrowski, K.A. (2023). Random Forest Algorithm for the Strength Prediction of Geopolymer Stabilized Clayey Soil. Sustainability, 15.10.3390/su15021408 ↗
49. Chen, T., and Guestrin, C. (2016, January 13–17). XGBoost. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA. Available online: https://dl.acm.org/doi/10.1145/2939672.2939785.10.1145/2939672.2939785 ↗
50. Wang, W., Chakraborty, G., and Chakraborty, B. (2020). Predicting the Risk of Chronic Kidney Disease (CKD) Using Machine Learning Algorithm. Appl. Sci., 11.10.3390/app11010202 ↗
51. Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A.V., and Gulin, A. (2018, January 2–8). CatBoost: Unbiased boosting with categorical features. Proceedings of the 32nd International Conference on Neural Information Processing Systems, Montréal, QC, Canada.
52. Abdullah, M., and Said, S. (2024). Performance Evaluation of Machine Learning Regression Models for Rainfall Prediction. Iran. J. Sci. Technol. Trans. Civ. Eng., 1–20.10.1007/s40996-024-01691-4 ↗
53. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T. (2017, January 4–9). LightGBM: A highly efficient gradient boosting decision tree. Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’17), Long Beach, CA, USA.
54. Light Gradient Boosting Machine: An efficient soft computing model for estimating daily reference evapotranspiration with local and external meteorological data10.1016/j.agwat.2019.105758 ↗
55. Rufo, D.D., Debelee, T.G., Ibenthal, A., and Negera, W.G. (2021). Diagnosis of Diabetes Mellitus Using Gradient Boosting Machine (LightGBM). Diagnostics, 11.10.3390/diagnostics11091714 ↗
56. Wang, Y., and Wang, T. (2020). Application of Improved LightGBM Model in Blood Glucose Prediction. Appl. Sci., 10.10.3390/app10093227 ↗
57. Extremely randomized trees10.1007/s10994-006-6226-1 ↗
58. Predictive modelling for solar thermal energy systems: A comparison of support vector regression, random forest, extra trees and regression trees10.1016/j.jclepro.2018.08.207 ↗
59. Throughput prediction based on ExtraTree for stream processing tasks10.2298/CSIS200131031C ↗
60. On lines and planes of closest fit to systems of points in space10.1080/14786440109462720 ↗
61. Analysis of a complex of statistical variables into principal components10.1037/h0071325 ↗
62. Various dimension reduction techniques for high dimensional data analysis: A review10.1007/s10462-020-09928-0 ↗
63. Krabbe, P.F. (2017). Validity. The Measurement of Health and Health Status, Elsevier.10.1016/B978-0-12-801504-9.00007-6 ↗
64. Diagnosis of defects by principal component analysis of a gas turbine10.1007/s42452-020-2796-y ↗
65. PCA-KL: A parametric dimensionality reduction approach for unsupervised metric learning10.1007/s11634-020-00434-3 ↗
66. On hyperparameter optimization of machine learning algorithms: Theory and practice10.1016/j.neucom.2020.07.061 ↗
67. Advancing Software Vulnerability Scoring: A Statistical Approach with Machine Learning Techniques and GridSearchCV Parameter Tuning10.1007/s42979-024-02942-x ↗
68. Sun, Y., Wang, J., Wang, T., Li, J., Wei, Z., Fan, A., Liu, H., Chen, S., Zhang, Z., and Chen, Y. (2024). Post-Fracture Production Prediction with Production Segmentation and Well Logging: Harnessing Pipelines and Hyperparameter Tuning with GridSearchCV. Appl. Sci., 14.10.3390/app14103954 ↗
69. Alhakeem, Z.M., Jebur, Y.M., Henedy, S.N., Imran, H., Bernardo, L.F.A., and Hussein, H.M. (2022). Prediction of Ecofriendly Concrete Compressive Strength Using Gradient Boosting Regression Tree Combined with GridSearchCV Hyperparameter-Optimization Techniques. Materials, 15.10.3390/ma15217432 ↗
70. Aravind, K.R., Maheswari, P., Raja, P., and Szczepański, C. (2020). Crop disease classification using deep learning approach: An overview and a case study. Deep Learning for Data Analytics, Elsevier.10.1016/B978-0-12-819764-6.00010-7 ↗
71. Determining Seepage Loss Predictions in Lined Canals Through Optimizing Advanced Gradient Boosting Techniques10.1007/s41101-024-00306-3 ↗
72. Root mean square error or mean absolute error? Use their ratio as well10.1016/j.ins.2021.11.036 ↗
73. RMSE is not enough: Guidelines to robust data-model comparisons for magnetospheric physics10.1016/j.jastp.2021.105624 ↗
74. A Unified Approach to Interpreting Model Predictions