基于深度神经网络的风电机组大部件故障监测算法研究

Research on Fault Monitoring Algorithm for Large Components of Wind Turbine Based on Deep Neural Network

随着风电场使用年限的增加,风电场运维成本控制变得更加重要。风机的几个主要子系统,如齿轮箱、发电机、轴承等,都是状态监测和故障预警的主要应用对象。随着故障提前预警,风电场运营人员可以通过有效调整运行方式,提前进行设备维护更换,能显著降低运营成本。对于占有风电机组大部分成本份额的齿轮箱,发生故障会造成过多的停机时间,因此,精准并且高效的齿轮箱故障监测和预警模型的开发是必不可少的,本论文介绍齿轮箱和叶片两个大部件基于SCADA数据的相似神经网络故障监控方法及系统。

With the increase of the service life of wind farms,the control of operation and maintenance costs of wind farms becomes more important.Several main subsystems of the fan,such as gearbox,generator and bearing,are the main application objects of condition monitoring and fault warning.With the early warning of faults,wind farm operators can effectively adjust the operation mode and carry out equipment maintenance and replacement in advance,which can significantly reduce the operating costs.For the gearbox,which accounts for the majority of the cost of wind turbines,the failure will cause too much downtime.Therefore,the development of accurate and efficient gearbox fault monitoring and early warning model is essential.This paper introduces the similar neural network fault monitoring method and system of gearbox and blade based on SCADA data.