风力发电机组故障诊断与预测技术研究综述

随着风力发电机组装机容量的快速发展,累计运行时间的持续增长,风电机组的维护问题日益突出,迫切需要研发有效的风电机组故障诊断与预测系统。从故障诊断和故障预测两个方面,归纳风力发电机组的主要故障特点;针对故障诊断难点问题,分析和总结基于振动、电气信号分析和模式识别算法的故障诊断方法的研究现状,指出各种方法的技术特点、局限性和今后的发展趋势;针对风电机组中机械结构和电子系统性能退化的各自特点,归纳当前的研究进展,提出物理失效模型和数据驱动模型融合的故障预测方法;最后,归纳了利用风力发电机组数据采集与监控系统(SCADA)数据进行故障诊断与预测的最新进展及需要进一步研究的问题。

Fault diagnosis and prognosis for wind turbines: An overview

As the installed capacity of wind turbines grows rapidly and cumulative operation time continues extending, the maintenance issue of the wind turbines becomes increasingly prominent, it is necessary to develop effective wind turbine fault diagnosis and prognosis systems urgently. In this paper, the main fault characteristics of wind turbines are summarized from two aspects of fault diagnosis and fault prognosis. Aiming at the difficult problems in fault diagnosis, the research status of the fault diagnosis approaches based on vibration, electric signal analysis and pattern recognition algorithms for wind turbine fault diagnosis are analyzed and summarized. The technical characteristics, limitations and future development trends of different approaches are pointed out. Aiming at various characteristics of mechanical structure and electronic system degradation in wind turbines, current research development of the fault prognostic approaches for wind turbines are summarized. The fault prognostic approach fusing the physics of failure model and data driven model is proposed. Finally, the new development and the problems requiring further study for the fault diagnosis and prognosis of wind turbines using supervisory control and data acquisition (SCADA) data are summarized.