水电厂水轮发电机励磁碳刷温度异常自动预警

Automatic Warning of Abnormal Temperature of Excitation Carbon Brushes for Hydroelectric Generators in Hydropower Plants

水轮发电机励磁碳刷最为显著的故障表征就是温度异常升高,因此提出了水电厂水轮发电机励磁碳刷温度异常自动预警方法。利用可变窗的Kendall-f算法分析水电厂水轮发电机励磁碳刷传感器回传的温升趋势,判别励磁碳刷温升趋势特征。结合温升趋势特征与弗雷歇距离算法,对比理想温升曲线与实时温升曲线之间的差异,将该差值与数据异常预警阈值进行比较,判断励磁碳刷是否出现温度异常升高情况,实现励磁碳刷温度异常自动预警。实验结果表明,所提方法可以得到精准的预警结果,避免水轮发电机发生严重的故障,实际应用效果好。

The most significant fault characteristic of the excitation carbon brush of a hydroelectric generator is abnormal temperature rise.Therefore,an automatic warning method for abnormal temperature of the excitation carbon brush of a hydroelectric generator is proposed.The Kendall-f algorithm with variable windows is used to analyze the temperature rise trend of excitation carbon brushes in hydroelectric power plants,and identify the characteristics of the temperature rise trend of excitation carbon brushes.By combining the characteristics of temperature rise trend with the Frechet distance algorithm,the difference between the ideal temperature rise curve and the real-time temperature rise curve is compared.The difference is compared with the data anomaly warning threshold to determine whether the excitation carbon brush has experienced an abnormal temperature rise,and to achieve automatic temperature anomaly warning for the excitation carbon brush.The experimental results show that the proposed method can obtain accurate warning results and avoid serious faults in hydroelectric generators,with good practical application results.