基于压力信号的循环泵故障诊断小波神经网络技术

Fault Diagnosis of Wavelet Neural Network on Reciprocating Pumps Based on Pressure Signal

以泵缸内的压力信号作为系统特征信号,将小波包分解的"频率-能量-故障识别"的模式识别故障诊断方法引入泵阀工作状态监测技术,通过改进的BP神经网络进行故障诊断。此技术已应用于循环泵实时故障诊断系统中。

A new method of fault feature is proposed by pressure signal in pump cylinder as system feature signals. A diagnosis method based on ＂frequency-energy-fauh identification＂ pattern recognition diagnosis approach is introduced to the fault detection on pump valves of reciprocating pumps. The improved BP neural network is used to diagnosis various faults of pump valves by the feature vectors constructed above.