天然气压缩机耦合故障的波动熵诊断模型

Coupling fault diagnosis for gas compressor based on fluctuation entropy model

针对天然气压缩机耦合故障的定性及定量特征难以提取的问题,提出基于信息熵的故障诊断方法,提取机组振动信号构造能量谱向量,进而提取信号的波动熵特征作为识别参数建立耦合故障的波动熵诊断模型,并根据波动熵对耦合故障进行分类。研究结果表明:波动熵模型可准确诊断出压缩机的耦合故障;该模型无需提取信号局部细节特征,可解决故障特征提取及故障建模的复杂性难题,提高诊断的容错性和灵活性。

Based on the fact that the coupling fault of the gas compressor is serious and that it is difficult to carry its characteristics out, according to the mechanism and the characteristic of the coupling failure, the fluctuation entropy was extracted as the feature parameter to establish the diagnostic model. The results show that some other detail parameters do not need to be extracted in the proposed method, which is different from the traditional diagnosis techniques. The problem of failure modeling and feature extraction is solved, and the model can effectively diagnose the coupling failure.