Abstract：In response to the problem of the conventional cooling early warning of wind turbine generator, this paper puts forward the cooling early warning method of wind turbine generator based on multiple linear regression, which makes effective use of the existing new energy centralized control system environment, adopts Pearson coefficient analysis and establishes the early warning framework, and forms the early warning model by multiple linear regression calculation. At the same time, according to different models and different working conditions, different evaluation indexes of generator cooling warning threshold are established, which makes the warning model more flexible and more accurate. The verification results of the example show that this method can correctly achieve the cooling early warning for wind turbine generators.
姜凯, 金岩磊, 秦冠军. 基于多元线性回归的风机发电机散热健康度评估方法[J]. 电气技术, 2025, 26(3): 49-52.
JIANG Kai, JIN Yanlei, QIN Guanjun. Research on the early warning of cooling time sequence of wind turbine generator based on multiple linear regression. Electrical Engineering, 2025, 26(3): 49-52.
2025, Vol. 26 
