基于WPT-SVM电动调节阀故障诊断研究

Research on Fault Diagnosis of Electric Control Valve Based on WPT-SVM

电动调节阀发生故障时,振动信号各频带的能量会相应发生变化。采用小波包对信号进行能量分解,通过小波包信息特征分析对支持向量机进行优化,得到诊断模型最佳参数,可以有效地对电动调节阀信号进行故障诊断并进行分类。实例表明,WPT优化SVM模型可以更加高效地对燃汽轮机进行故障诊断,提高了故障诊断的分类准确率,为电动执行机构信号的故障诊断提供了可行有效的方法。

When the electric control valve fails,the energy of each frequency band of the vibration signal will change accordingly.The wavelet packet is used to decompose the signal energy,and the support vector machine is optimized through the wavelet packet information feature analysis to obtain the best parameters of the diagnosis model,which can effectively diagnose and classify the electric control valve signal.Examples show that the WPT optimized SVM model can diagnose gas turbine faults more efficiently,improve the classification accuracy of fault diagnosis,and provide a feasible and effective method for fault diagnosis of electric actuator signals.