欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
在监测高速列车转向架工作状态时,针对列车运动自由度数目多、不同监测点数据相关性强的特点,提出了多元经验模态分解和排列熵相结合的故障特征提取方法。首先利用多元经验模态分解对高速列车转向架7种不同工况的振动信号进行多通道同步联合分析,获取不同数据通道间的共同模式。利用相关系数选取反映故障信号特征的有效本征模态函数来重构原始故障信号,计算重构信号的排列熵作为故障特征。最后采用支持向量机进行故障状态分类识别。实验结果表明,列车在各种运行速度下均能达到85%以上的分类效果,验证了该方法的有效性。
英文摘要：
In monitoring of high-speed train bogie working state, aiming at many freedoms of motion and strong correlation characteristics of different monitored data points of train, this paper puts forward fault feature extraction method by combination of multivariate empirical mode decomposition（ MEMD） and permutation entropy. After the multi-channel synchronous joint analysis of vibration signals of seven kinds of working conditions of high-speed train bogie by using MEMD, the common pattern between different data channels can be accessed. Sensitive intrinsic mode functions（ IMFs） that reflect the characteristics of fault signals are used to reconstruct the original fault signal via correlation coefficient, and the permutation entropy of reconstructed signal are calculated and taken as the fault feature. Finally, the support vector machine（ SVM） is used to identify the fault state classification. Various experimental results show that the recognition rate can reach more than 85 % of the classification results at various speeds, verifying the effectiveness of the proposed method.
同期刊论文项目
同项目期刊论文
期刊信息
位置：