内燃机KVMD-MHD振动谱图表征与TD-2DPCA编码诊断方法研究

发布时间：2018-04-11 18:48

本文选题：故障诊断 + 内燃机　；参考：《振动工程学报》2017年04期

【摘要】：为了直接对内燃机振动谱图像进行诊断识别,提出一种基于改进变分模态分解(VMD)、Margenau-Hill(MHD)时频分析与双向二维主成分分析(Two-directional,Two-dimensional PCA,TD-2DPCA)的内燃机振动谱图像识别诊断方法。该方法首先针对VMD分解过程中的层数选取问题,提出了一种中心频率筛选的VMD分解层数改进方法(KVMD),然后将内燃机振动信号利用KVMD分解成一组单分量模态信号,并对生成的各个单分量信号进行MHD处理后表征成振动谱图像;在此基础上,对生成的内燃机KVMD-MHD振动谱图像采用双向二维主成分分析形成编码矩阵,并采用最近邻分类器(KNNC)对上述编码矩阵直接进行模式识别,以实现内燃机振动谱图像的自动诊断。最后,将该方法应用在气阀机构4种工况下的缸盖表面振动信号诊断实例中,结果表明:该方法不仅改进了传统图像模式识别中的特征参数提取方法,而且能很好地消除时频分布中的交叉干扰项,使各时频分量物理意义明确,能有效诊断出内燃机气阀机构故障,为内燃机振动诊断探索了一条新途径。
[Abstract]:In order to diagnose and recognize the vibration spectrum image of internal combustion engine directly, a method based on modified variational mode decomposition (VMD-VMD-VMD-Margenau-Hill-Hill-MHD) time-frequency analysis and Two-dimensional principal component analysis (Two-dimensional PCA-TD-2DPCAA) is proposed to identify and diagnose the internal combustion engine vibration spectrum image.To solve the problem of selecting the number of layers in the process of VMD decomposition, an improved method of VMD decomposition layer number based on center frequency selection is proposed, and then the vibration signal of internal combustion engine is decomposed into a group of single-component mode signals by using KVMD.The generated single component signals are represented as vibration spectrum image by MHD, and the generated KVMD-MHD vibration spectrum image is obtained by bidirectional two-dimensional principal component analysis (TPCA) to form coding matrix.The nearest neighbor classifier KNNCis used to recognize the coding matrix directly to realize the automatic diagnosis of the internal combustion engine vibration spectrum image.Finally, the method is applied to the vibration signal diagnosis of cylinder head surface under four working conditions of the valve mechanism. The results show that the method not only improves the traditional feature parameter extraction method in image pattern recognition.Moreover, the cross-interference in time-frequency distribution can be eliminated well, the physical meaning of each time-frequency component is clear, the fault of valve mechanism of internal combustion engine can be effectively diagnosed, and a new way for vibration diagnosis of internal combustion engine is explored.
【作者单位】：火箭军工程大学理学院;
【基金】：国家自然科学基金资助项目(51405498) 中国博士后科学基金资助项目(2015M582642) 陕西省自然科学基金资助项目(2013JQ8023)
【分类号】：TK407;TP391.41

【相似文献】