This chapter presented a robust data-driven fault detection scheme with the application to a wind turbine benchmark. The proposed scheme is based on robust residual generators constructed directly from available process measurements. For this purpose, a parity space is first identified from the measured data, and optimal parity vectors are selected from the parity space according to a given performance index and an optimization criterion to generate a robust residual vector. A proper evaluation approach as well as a suitable decision logic is further given to make a correct final decision. The effectiveness of the proposed scheme is finally demonstrated by the results obtained from the simulation of a wind turbine benchmark model.
Health monitoring of wind turbine: Data-based approaches
Karimi H. R.
2018-01-01
Abstract
This chapter presented a robust data-driven fault detection scheme with the application to a wind turbine benchmark. The proposed scheme is based on robust residual generators constructed directly from available process measurements. For this purpose, a parity space is first identified from the measured data, and optimal parity vectors are selected from the parity space according to a given performance index and an optimization criterion to generate a robust residual vector. A proper evaluation approach as well as a suitable decision logic is further given to make a correct final decision. The effectiveness of the proposed scheme is finally demonstrated by the results obtained from the simulation of a wind turbine benchmark model.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.