摘要
针对齿轮箱振动信号的非平稳特征,将具有局域化特性的EMD方法和近似熵相结合,并用LSSVM进行分类来实现齿轮箱故障诊断。首先利用EMD将振动信号分解成若干IMF分量,再对IMF分量求取近似熵,组成特征向量矩阵,输入到LSSVM分类器中进行故障识别。结果表明,与传统SVM相比,LSSVM的识别精度更高,验证了该方法的可行性。
A method of gearbox fault diagnosis based on EMD-approximate entropy and LSSVM is proposed according to non-stationary characteristics of gearbox vibration signal.Firstly,the vibration signal was decomposed into several IMF components by EMD.And then the approximate entropies of the IMFs were taken as the eigenvectors.Finally,the eigenvectors were input into LS-SVM classifier for fault type recognition.The result shows the LSSVM has higher recognition accuracy compared with SVM and prove the method is feasible.
出处
《组合机床与自动化加工技术》
北大核心
2014年第3期111-113,共3页
Modular Machine Tool & Automatic Manufacturing Technique
基金
国家自然科学基金(51175486)
教育部高校博士点基金(20091420110002)
