基于慢特征分析和随机森林的风叶结冰故障监测

Wind Blade Icing Fault Diagnosis Based on Slow Feature Analysis and Random Forest

在风力领域方面,叶片结冰是一个世界性的难题。机理建模方法监测叶片结冰需要大量先前的理论,但在大多数情况下无法满足。随着人工智能的发展,数据驱动方法吸引了广泛的注意。提出一种慢特征(SFA)和随机森林(RF)的组合策略用于监测风机叶片结冰故障,对提高风机的可靠性和经济效益来说意义重大。首先,SFA用于选取过程中改变慢特征,然后将提取的慢特征输入随机森林模型进行故障监测。通过风电实验的验证,该方法的最低错误率为0.268,而直接放入随机森林的错误率为0.346。因此,选择慢特征的数量至关重要。

Blade icing is a worldwide problem in the field of wind power.A lot of prior knowledge is needed to detect blade icing by using mechanism modeling method,which cannot be satisfied in most cases.With the development of artificial intelligence(AI) technology,data-driven approaches have attracted widespread attention. In this paper,a combined strategy of slow feature analysis(SFA) and random forest(RF) is proposed to detect the icing fault of wind blades.It is significant to improve the reliability and economy of wind turbines.First,SFA is used to extract the features that change slowly in the process.After that,the extracted slow features are input into RF for fault detection.The lowest error rate of the proposed method is 0.268 while it is 0.346 by directly putting into RF,which is verified by wind power experiments.So it is crucial to select the number of slow features.