Data-Driven and Intelligent Fault Diagnosis

Data-Driven Fault Diagnosis and Fault Tolerant Control of Wind Turbines. Seminar of two hours for the University of Science & Technology Beijing - USTB.

Abstract

This presentation introduces a data-driven methodology for diagnosing and accommodating faults in modern wind turbine and wind farm systems. Motivated by the rising complexity, size, and sustainability requirements of offshore installations, as highlighted by the statistical trends shown in the introductory slides, the work proposes a comprehensive framework that integrates fault modelling, data-driven system identification, fault detection and isolation, and fault-tolerant control. The approach relies on fuzzy Takagi-Sugeno models and neural network estimators trained on noisy, uncertain data, enabling robust residual generation even in highly nonlinear, disturbance-prone operating scenarios. The methodology is validated using well-established wind turbine and wind farm benchmark models, where an extensive set of simulations, Monte Carlo analyses, comparative studies with existing techniques, and real-time Hardware-in-the-Loop experiments demonstrate high fault detectability, low false-alarm rates, and practical preservation of power-tracking under various actuator, sensor, and system faults. The results confirm the suitability of data-driven tools to enhance the sustainability, safety, and reliability of next-generation wind energy systems.

Keywords

Data-driven fault diagnosis, sustainable control, wind turbine and wind farm systems, fault-tolerant control, fuzzy and neural modelling.

Main Points

Sustainability;
Benchmark systems;
Data-driven modelling;
Neural network estimators;
Fault detection and isolation;
Fault-tolerant control;
Verification and validation.

Downloads: Talk Slide Files

Seminar Slides (PDF file, 2.55 MB).

Selected References

Simani, S., Farsoni, S., & Castaldi, P. (2015). Fault diagnosis of a wind turbine benchmark via identified fuzzy models. IEEE Transactions on Industrial Electronics, 62(6), 3775-3782.
Simani, S., Farsoni, S., & Castaldi, P. (2015). Fault-tolerant control of an offshore wind farm via fuzzy modelling and identification. IFAC-PapersOnLine, 48(21), 1345-1350.
Odgaard, P. F., Stoustrup, J., & Kinnaert, M. (2013). Fault-tolerant control of wind turbines: A benchmark model. IEEE Transactions on Control Systems Technology, 21(4), 1168-1182.
Laouti, N., Sheibat-Othman, N., & Othman, S. (2011). Support vector machines for fault detection in wind turbines. In Proceedings of the IFAC World Congress (pp. 7067-7074).
Zhang, X., Zhang, Q., Zhao, S., Ferrari, R. M., Polycarpou, M. M., & Parisini, T. (2011). Fault detection and isolation of the wind turbine benchmark: An estimation-based approach. In Proceedings of the IFAC World Congress (pp. 8295-8300).

Simani Home Page

Dipartimento di Ingegneria