基于SVM和广义粗糙度特征的航空发动机振动故障诊断方法

Research on aeroengine vibration fault diagnosis based on support vector machine and generalized roughness feature

通过对航空发动机振动信号进行小波分解,依据多尺度空间局部能量分布和粗糙性提取基于子带信号能量加权广义粗糙度特征实现对振动情况的描述.然后将上述特征送入支持向量机(support vectormachine,简称SVM)分类器进行训练,根据分类器的输出结果判断航空发动机的工作状态和故障类型.通过对实测航空发动机试车时得到的振动信号的实验分析结果表明,该算法可以有效地识别发动机的振动故障.

The signal was decomposed based on wavelet transform and the generalized roughness vector of the signal was formed by making use of the local energy distributions and the roughness of the sub-band signal.Then the desired parameters serve as the fault characteristic vectors to be input to the support vector machine classifier and the work conditions and fault patterns were identified by the output of the classifier.The analysis results from the aeroengine vibration signals show that the fault diagnosis method can classify working conditions and fault patterns effectively.