摘要
齿轮箱振动信号具有非线性冲击特征,其有效特征信息易于被振动信号其他干扰成分所淹没。针对如何有效提取其冲击特征这一热点和难点问题,通过构建直齿锥齿轮动力学模型,研究其典型故障振动机理,提出了一种基于改进型极点对称模态分解(ESMD)和支持向量机(SVM)相结合的故障诊断方法。该方法通过改进型ESMD将振动信号自适应分解为多个IMF分量,然后利用最大峭度-包络谱指标选取一定量的分量并提取每个分量的奇异值,构建特征向量集合并输入SVM进行故障模式识别。动力学仿真模拟和齿轮箱实验研究表明,改进型ESMD-SVM法能够有效提取并识别齿轮箱故障信息。
The gearbox vibration signal contains nonlinear impact characteristics, and the significant feature information tends to be overwhelmed with other interference components. Aiming at the key issue of how to effectively extract its impact characteristics, a fault diagnosis method based on an improved extreme symmetric mode decomposition(ESMD) and support vector machine(SVM) as well as a dynamics model of spur bevel gear for investigating typically gearbox fault mechanism is proposed. In this method, the vibration signal is adaptively decomposed into multiple IMF components by the improved ESMD, and then a certain number of components are selected with the maximum kurtosis-envelope spectrum index. Meanwhile, the singular values of each selected IMF are extracted to construct the feature vector set, which is input into the SVM for the fault pattern recognition finally. Dynamic simulation and gearbox experimental research show that the improved ESMD-SVM method can extract and identify gearbox fault information effectively.
作者
谷晟
别锋锋
缪新婷
赵威
郭越
Gu Sheng;Bie Fengfeng;Miao Xinting;Zhao Wei;Guo Yue(School of Mechanical Engineering,Changzhou University,Changzhou 213164,China)
出处
《机械传动》
北大核心
2023年第1期155-162,169,共9页
Journal of Mechanical Transmission
基金
国家自然科学基金(52105141)
江苏省高等学校自然科学研究重大项目(19KJA430004)。
