一种多通道信息融合的横向减振器性能退化阶段辨别方法

对于转向架这样复杂的系统,分布在系统不同位置的传感器可以实时检测大量数据.这些数据能够反映高速列车运行过程中转向架关键部件的性能退化状态,但单一通道的振动信号存在着信息缺失、信噪比低等缺陷,无法据此实现转向架关键部件性能退化阶段的精确辨识.因此,本文以横向减振器为研究对象,通过对转向架振动数据相关性分析,提出了车体和转...

A multi-channel information fusion lateral damper performance degradation stage identification method

For a complex system such as a bogie,sensors distributed in different positions of the system detected a large amount of data in real time.These data reflected the performance degradation state of key components of the bogie during the operation of the high-speed train.However,the vibration signal of a single channel cannot be used to accurately identify the performance degradation stage of the key parts of bogie,because it has defects such as lack of information and low signal-to-noise ratio.Therefore,taking the lateral damper as example,a novel method to identify its performance degradation stage by fusing the vibration signals of multiple channels on the carbody and bogie was proposed in this paper.The correlation analysis of the vibration data was used to choose the valuable channels.The adaptive extraction and stage identification of the performance degradation characteristics of the lateral damper were realized by constructing a multi-channel information fusion model based on CNN.The results show that the identification precision of the proposed method is higher than which of the method based on a single channel under the condition that the lateral damper performance degrades at equal intervals of 10%.