基于粗糙集和支持向量机的水电机组振动故障诊断

Vibration Fault Diagnosis of Hydro-Turbine Generating Unit Based on Rough Sets and Support Vector Machine

提出应用粗糙集和支持向量机水电机组振动的故障诊断模型。运用粗糙集理论对水电机组振动信号的属性特征进行预处理,在约简去除其冗余属性后得到决策表,将决策表作为支持向量机的学习样本,通过训练,使构建的支持向量机多分类器能够反映属性特征和故障类型的映射关系,从而达到故障诊断的目的。测试结果表明,与常规方法相比,应用粗糙集和支持向量机相结合的方法进行故障诊断具有简单有效、诊断速度快和良好的鲁棒性等优点,是一种有效的诊断方法。

A model of the vibration fault diagnosis of hydro-turbine generating unit was investigated by the method of combining rough sets （RS） theory and support vector machine （SVM） multi-classifier, according to complementary strategy. Using RS to preprocess the attribute character of vibration signal of hydro-turbine generating unit, and then a key decision table was obtained after deducting redundant attributes. The key decision table was acted as a learning sample to train the constructed SVM multi-classifier, thus the mapping relationship between the fault and the attribute character was formed and the fault diagnosis was realized by the trained SVM multi-classifier. This method of combining RS and SVM is efficiently for the diagnosis of the unit faults in comparison with the traditional method. The simulation experimental results show that the proposed method is simpler, faster and more robust.