基于频谱相关性分析的齿轮早期磨损诊断

基于振动分析的齿轮故障检测已被证明在故障识别中是有效的，但对表征早期磨损的振动信号的提取和识别仍没有得到很好的解决.本文提出一种基于频谱相关性分析的变分模态分解(VMD)和核支持向量机(SVM)相结合的齿轮早期磨损诊断方法，对能够揭示早期磨损状态的微弱齿轮振动信号采用近似完全重构的准则来初始化模式数，并采用信号功率谱密度最大值对应的频率初始化VMD方法的中心频率，用以有效提取齿轮磨损信息，进而结合核支持向量机进行齿轮的早期磨损诊断.实验结果表明，所提方法可有效克服背景噪声大无法预设模式数的问题，对噪声具有更好的鲁棒性，诊断准确率达到94.4%,可为齿轮早期磨损检测提供解决方法.

Early Wear Diagnosis of Gears Based on Spectrum Correlation Analysis

Gear fault detection based on vibration analysis has been proven to be effective in fault identification. However， the extraction and identification of vibration signals characterizing early wear have not been solved well. This paper proposes a method for early wear diagnosis of gears， combining variational mode decomposition (VMD) based on spectrum correlation analysis with kernel support vector machine (SVM). For weak gear vibration signals that can characterize early wear， the modal numbers are initialized by an approximate complete reconstruction criterion. Meanwhile， the frequency corresponding to the maximum value of the signal power spectral density is used to initialize the center frequency of the VMD method. It is used to effectively extract gear wear information from gear vibration signals and then be combined with kernel support vector machines for early wear diagnosis of gears. The experimental results show that the proposed method can effectively overcome the problem that the modal numbers cannot be preset with large background noise， be with better robustness to noisy situations， and achieve a diagnostic accuracy of 94.4%， which provides a solution for early wear detection of gears.