A Novel Multi-task Learning Method with Attention Mechanism for Wind Turbine Blades Imbalance Fault Diagnosis

With the rapid development of wind power generation in recent years, wind power plays a more and more important role in the modern power system. Accurate and efficient condition monitoring and fault diagnosis of wind turbines (WTs) is essential to ensure the safe and stable operation of wind farm and the stability of power system. Because of the characteristic of wind power, the imbalance fault caused by ice accretion on WT blades poses a threat to the reliable operation of WT. To this end, a multi-task learning method with attention mechanism has been proposed in this paper to address the problem of imbalance fault diagnosis of WT. The proposed model can complete the diagnosis of fault type and ice accretion level at the same time. The performance of the proposed model is evaluated on a simulation dataset. The diagnosis results show that the proposed framework can reach a state-of-the-art performance compared with other approaches, which can strongly illustrate that the proposed multi-task framework with attention mechanism can improve the effectiveness of each task.