Paired ensemble and group knowledge measurement for health evaluation of wind turbine gearbox under compound fault scenarios

To simultaneously identify the specific single or compound faults and evaluate the health condition of wind turbine gearbox accurately, a novel health evaluation method is proposed based on paired ensemble (PE) and group knowledge measurement (GKM). In this method, PE is constructed for the compound fault diagnosis, and the fault probability distribution is derived and translated into the status membership function to quantify the fault statue membership accurately. Then, a fuzzy derivation method named GKM is proposed to estimate the fault influence weights for gearbox's behavior, and abundant condition-based factors can be considered such as decision-making style and expert authority level. Meanwhile, the health indicator is defined by the ratio system to evaluate the health condition of wind turbine gearbox by integrating estimation information. The effectiveness of the proposed method is validated on a compound fault test platform of wind turbine gearbox. The experimental results indicate that compared with the existing methods, the proposed method is competitive in terms of diagnostic accuracy and evaluation reliability.