Predictive Modelling for Optimizing Wind Turbine Performance and Structural Health Monitoring: Adapting Turkish SCADA Data for Sub-Saharan Africa

Abstract:

This research investigates the application of AI-enhanced structural health monitoring (SHM) systems to predict and optimize the performance and reliability of wind turbines in Sub-Saharan Africa power generation. Supervisory Control and Data Acquisition (SCADA) systems data from a Turkish wind turbine were leveraged to develop a predictive model using the eXtreme gradient boosting (XGBoost) algorithm. Wind speed data from the Turkish wind turbine was substituted with wind speed data of some selected locations in Sub-Saharan Africa (Katsina, Nigeria; Addis Ababa, Ethiopia; Dakar, Senegal; and Cape Town, South Africa). The performance of the models was evaluated using Mean Absolute Percentage Error (MAPE) and the coefficient of determination (R²). The findings show a 0.95% decrease in predicted power output for all the selected locations. The adapted model achieved a MAPE of 1.1% for Addis Ababa, 1.25% for both Cape Town and Katsina, and 1.17% for Dakar, while achieving a high R² of 0.96 for all the locations, indicating high predictive accuracy. In scenarios with high wind speed, Dakar has the highest prediction of 3691.09kW, achieving a 1.03% increase compared to Turkey with a predicted power output of 3583.69kW. Cape Town achieved better prediction accuracy, with a MAPE of 0.78% and R² of 0.98, while yielding a power output of 3545.67 kW. The model achieved F1-Score, Accuracy, sensitivity, precision, and selectivity scores of 99.87%, 99.75%, 99.93%, 99.81%, and 4.85% respectively. This study shows there is vast potential for employing machine learning models in enhancing the operational efficiency of wind turbines. Future study is recommended to incorporate local SCADA data across different wind farms in Sub-Saharan Africa.

• Periodical: Advances in Science and Technology (Volume 160)
• Pages: 155-164
• DOI: https://doi.org/10.4028/p-7EveuY
• Online since: February 2025
• Authors: Sikiru Abdulganiyu Siyanbola*, Olamide Mercy Oluwatade, Emmanuel Emeka Okafor
• Keywords: Machine Learning, Predictive Modelling, Structural Health Monitoring, Wind Turbine, XGBoost Algorithm

References

[1] Chen, Z. (2021). Wind power: an important source in energy systems. Wind, 1(1), 90–91

DOI: 10.3390/wind1010006

[2] Jie, W., & Rabnawaz, K. (2024). Renewable energy and CO2 emissions in developing and developed nations: a panel estimate approach. Frontiers in Environmental Science, 12

DOI: 10.3389/fenvs.2024.1405001

[3] Veers, P., Dykes, K., Basu, S., Bianchini, A., Clifton, A., Green, P., Holttinen, H., Kitzing, L., Kosovic, B., Lundquist, J. K., Meyers, J., O'Malley, M., Shaw, W. J., & Straw, B. (2022). Grand Challenges: Wind energy research needs for a global energy transition. Wind Energy Science

DOI: 10.5194/wes-2022-66

[4] Vieira, M., Snyder, B., Henriques, E., White, C., & Reis, L. (2023). Economic viability of implementing structural health monitoring systems on the support structures of Bottom-Fixed Offshore Wind. Energies, 16(13), 4885

DOI: 10.3390/en16134885

[5] Heibati, R., Alipour-Sarabi, R., & Bathaee, S. M. T. (2023). A survey on data acquisition methods in conditional monitoring of wind turbines. Scientia Iranica, 0(0), 0

DOI: 10.24200/sci.2023.62909.8100

[6] Elavarasan, R. M., Shafiullah, G., Padmanaban, S., Kumar, N. M., Annam, A., Vetrichelvan, A. M., Mihet-Popa, L., & Holm-Nielsen, J. B. (2020). A comprehensive review on renewable energy development, challenges, and policies of leading Indian states with an international perspective. IEEE Access, 8, 74432–74457

DOI: 10.1109/access.2020.2988011

[7] Daenens, S., Vervlimmeren, I., Verstraeten, T., Daems, P., Nowé, A., & Helsen, J. (2024). Power prediction using high-resolution SCADA data with a farm-wide deep neural network approach. Journal of Physics Conference Series, 2767(9), 092014

DOI: 10.1088/1742-6596/2767/9/092014

[8] Le, T., Luu, T., Nguyen, H., Nguyen, T., Ho, D., & Huynh, T. (2022). Piezoelectric Impedance-Based Structural Health Monitoring of wind turbine Structures: Current status and Future Perspectives. Energies, 15(15), 5459

DOI: 10.3390/en15155459

[9] Pandit, R., Astolfi, D., Hong, J., Infield, D., & Santos, M. (2022). SCADA data for wind turbine data-driven condition/performance monitoring: A review on state-of-art, challenges and future trends. Wind Engineering, 47(2), 422–441

DOI: 10.1177/0309524x221124031

[10] Maetz, T., Kappel, J., Wiemann, M., Bergmannshoff, D., Hägelen, M., Jetten, R., Schmidt, M., Käsgen, J., Jackel, M., Moll, J., Kraemer, P., & Krozer, V. (2023). Microwave Structural Health monitoring of the grouted connection of a Monopile-Based offshore wind turbine: fatigue testing using a scaled laboratory demonstrator. Structural Control and Health Monitoring, 2023, 1–18

DOI: 10.1155/2023/1981892

[11] Lydia, M., & Kumar, G. E. P. (2021). Machine learning applications in wind turbine generating systems. Materials Today Proceedings, 45, 6411–6414. https://doi.org/10.1016/j.matpr. 2020.11.268

DOI: 10.1016/j.matpr.2020.11.268

[12] Lützen, U., & Beji, S. (2024). Predictive Maintenance for Offshore Wind Turbines through Deep Learning and Online Clustering of Unsupervised Subsystems: A Real-World Implementation. Research Square (Research Square)

DOI: 10.21203/rs.3.rs-3906932/v1

[13] Yang, W., Wang, J., Lu, H., Niu, T., & Du, P. (2019). Hybrid wind energy forecasting and analysis system based on divide and conquer scheme: A case study in China. Journal of Cleaner Production, 222, 942–959

DOI: 10.1016/j.jclepro.2019.03.036

[14] Liu, X., Yue, Y., Huang, X., Xu, W., & Lu, X. (2022). A review of Wind Energy Output Simulation for new power System Planning. Frontiers in Energy Research, 10

DOI: 10.3389/fenrg.2022.942450

[15] Al-Hajj, R., Assi, A., Neji, B., Ghandour, R., & Barakeh, Z. A. (2023). Transfer Learning for Renewable Energy Systems: A survey. Sustainability, 15(11), 9131

DOI: 10.3390/su15119131

[16] Stackhouse, P. (n.d.). POWER | DAV. https://power.larc.nasa.gov/data-access-viewer/