摘要
针对风电机组主轴承故障率高、运维成本高的问题,提出一种基于数据采集与监视控制(SCADA)系统的风电机组主轴承故障预警方法。通过相关性分析法分析SCADA系统的历史数据,提取风速、发电机输出功率、机舱温度、主轴承(t-1)时刻温度作为主轴承故障特征变量。采用粒子群优化BP神经网络算法,建立主轴承故障预警模型,优化BP神经网络的权值和阈值,防止BP神经网络算法陷入局部极小值。基于该模型的湖南某风电场主轴承故障预测算例结果表明:该预警模型可以有效提高预测的精度,实现主轴承故障预警,为风电场运维人员提供更充足的维护时间,降低风电机组运维成本。
In view of the high failure rate and high maintenance cost of the wind turbine main bearing, a fault early warning method is put forward to the main bearing based on supervisory control and data acquisition (SCADA) system. Adopting correlation analysis method, wind speed, generator output power, cabin temperature, and main bearing ( t -1) moment temperature are extracted as fault features for main bearing of wind turbine through the analysis of the historical data from SCADA system . The particle swarm optimization (PSO) is used to establish the main bearing fault early warning model. The weight and threshold of the BP neural network are optimized to prevent the BP neural network algorithm from falling into the local minimum value. The model is applied into fault prediction of one wind turbine main bearing in Hu Nan. The results show that the model can improve the prediction accuracy on the main bearing temperature and accurately realize the early warning of main bearing fault, while providing more maintenance time for wind farm operators and reducing the operation and maintenance costs of wind turbines.
作者
向健平
凌永志
詹俊
李鹏辉
XIANG Jian-ping;LING Yong-zhi;ZHAN Jun;LI Peng-hui(School of Energy and Power Engineering, Changsha University of Science and Technology, Changsha 410114, China;Hunan Ulitech Automation System Co. Ltd., Changsha 410205, China)
出处
《电力科学与技术学报》
CAS
北大核心
2019年第3期223-228,共6页
Journal of Electric Power Science And Technology
基金
中国外国专家局高端外国专家项目(GDT20154300072)