基于极端随机树的火电厂再热器故障预警算法研究

Research on Fault Early Warning Algorithm of Reheater in Thermal Power Plant Based on Extreme Random Tree

针对火电厂锅炉再热器欠温问题存在的故障隐患,研究了随机森林、极端随机树和梯度提升决策树3种集成学习算法对再热蒸汽温度的预测效果。再通过预测值与真实值之间存在的残差,可以在一定程度上反映故障隐患信息。采用滑动窗口法精确计算预警阈值,分别对3种算法的预警效果进行了对比分析,确定了极端随机树与滑动窗口法相结合的预警模型初始报警时刻最早,预测效果最为准确。

Aiming at the hidden troubles of under-temperature problems of boiler reheaters in thermal power plants,the prediction effects of three integrated learning algorithms,extreme random tree,gradient boost and random forest,on the temperature of reheated steam were studied.The residual between the predicted value and the real value reflects the hidden danger information to a certain extent;at the same time,the sliding window method is used to accurately calculate the warning threshold,and the early warning effects of the three algorithms are compared and analyzed,and the extreme random tree and sliding windoware determined.