摘要
针对传统EMD易产生模态混叠,原始SVM、RVM方法存在核函数选取困难、识别效率低等问题,提出一种基于变分模态分解(VMD)、排列熵(PE)以及混合蝙蝠算法(BA)优化的多分类相关向量机(M-RVM)的轴承故障智能诊断方法。首先,VMD分解故障信号,获得本征模态函数(IMF);然后将PE用于IMF的故障特征提取过程,形成特征序列;最后,将所得的特征序列输入基于混合BA优化的M-RVM故障诊断模型,对不同故障进行分类识别。对试验数据的分析结果表明,基于VMD-PE与M-RVM的滚动轴承故障诊断可以提高轴承故障诊断的准确度。
Aiming at the problems that the traditional EMD is easy to occur modal aliasing,the original SVM and RVM have difficulty in selecting kernel function and low recognition efficiency,based on variational mode decomposition(VMD),permutation entropy(PE)and multi-classification correlation vector machine(M-RVM)by hybrid bat algorithm(BA)optimization,an intelligent fault diagnosis method for bearing faults was proposed.First,the VMD decomposes the fault signal to obtain the eigenmode function(IMF);then converts PE into the fault feature extraction process of IMF to form the feature sequence;finally,the obtained feature sequence is input fault diagnosis model based on the M-RVM optimized by the hybrid BA to classify and identify different faults.The analysis results of the test data show that the fault diagnosis of rolling bearing based on VMD-PE and M-RVM can improve the accuracy of bearing fault diagnosis.
作者
李然
朱希安
王占刚
Li Ran;Zhu Xi’an;Wang Zhangang(School of Information and Communication Engineering,Beijing Information Science and Technology University,Beijing 100101,China)
出处
《煤矿机械》
北大核心
2020年第3期163-166,共4页
Coal Mine Machinery
基金
北京市科技创新服务能力建设-基本科研业务费(市级)(科研类)(PXM2019_014224_000026)
2018年促进高校内涵发展项目——“信息+”项目
北京市科技创新服务能力建设-提升计划项目(PXM2017_014224_000009)。