基于MFE-GASVM的机载燃油泵故障诊断

机载燃油泵的健康状态是保障飞行任务完成的先决条件，实现机载燃油泵故障诊断的关键是敏感故障特征的提取。由于机械系统的复杂性，机载燃油泵振动信号的随机性表现在不同尺度上，因此需要对振动信号进行多尺度分析。基于此，在模糊熵的基础上引入尺度因子，对振动信号在不同尺度下进行复杂性度量。然后将多尺度模糊熵特征量作为支持向量机的输入参数以识别故障状态，并采用遗传算法对支持向量机的核函数参数及惩罚参数进行优化。实验结果分析表明，该方法可有效提取故障特征，实现机载燃油泵的故障诊断。

Airborne fuel pumps fault diagnosis based on MFE-GASVM

The health state of airborne fuel pumps is important for the safety of flight mission, so the fault state feature extraction and diagnosis for the pumps become an important factor. Due to the complexity of mechanical systems, the randomicity of the vibration signal behave on different scales, making it necessary to analyze the vibration signal in a multi-scale way. Multi-scale fuzzy entropy (MFE) is based on fuzzy entropy is defined to measure the complexity of time series in different scale factors. The MFE characteristic parameters are input to support vector machine for fault classification. Genetic algorithm is applied into adaptive selection of the best penalty parameter and kernel function parameter. By analysis experimental data, the results show that the proposed method can differentiate the fault categories of fuel pumps effectively.