基于改进马田系统的发动机转子振动信号研究

Research on Engine Rotor Vibration Signal Based on Improved Martian System

针对发动机转子系统的振动信号分析问题,提出了一种基于改进马田系统的故障模式识别和分类方法。利用最优阈值小波包变换方法对振动信号进行降噪;对降噪后的振动信号进行小波包分解,提取时频域特征构建基准空间;然后利用岭估计回归分析消除马氏距离的复共线性,使用切比雪夫定理计算马田系统的概率阈值,运用有向非循环图方法对不同模式进行分类;将方法应用于转子振动数据中以验证算法的有效性。结果表明,基于改进的马田系统算法模式识别准确率高,是一种有效的振动信号故障模式分类方法。

Aiming at the problem of vibration signal analysis of engine rotor system,a pattern recognition and classification method based on the improved Mahalanobis Taguchi System(IMTS)is proposed.Firstly,the optimal threshold wavelet packet transform method is used to denoise the vibration signal;Secondly,the vibration signal is decomposed by wavelet packet,and its time-frequency domain features are extracted to construct the reference space;Then,ridge estimation regression analysis is used to eliminate the complex collinearity of Mahalanobis distance(MD),Chebyshev′s theorem is used to calculate the probability threshold of Martian system(MTS),and the directed acyclic Diagram(DAG)method is used to classify different patterns;Finally,the method is applied to rotor vibration data to verify the effectiveness of the algorithm.The results show that the improved Martian system algorithm has high recognition accuracy and is an effective fault mode classification method of the vibration signal.