基于改进VMD与FastICA的电梯反绳轮轴承特征提取方法  

Feature extraction method of elevator reverse rope wheel bearing based on improved VMD and FastICA

作　　者：史星航 陈治 戴博文 SHI Xinghang;CHEN Zhi;DAI Bowen(Zhejiang Province’s Key Laboratory of Reliability Technology for Mechanical and Electronic Product,Zhejiang Sci-Tech University,Hangzhou 310018,China)

机构地区：[1]浙江理工大学浙江省机电产品可靠性技术研究重点实验室,浙江杭州310018

出　　处：《电子设计工程》2025年第4期10-16,共7页Electronic Design Engineering

基　　金：国家自然科学基金面上项目(52075496,51505430)。

摘　　要：针对电梯反绳轮轴承复合故障信号中各故障特征易受到强噪声干扰导致特征提取效果欠佳的问题,该文提出了一种改进变分模态分解(VMD)与快速独立分量分析(FastICA)的反绳轮轴承特征提取方法。基于反绳轮轴承振动信号,采用综合适应度指数确定VMD最优分解参数,进行VMD分解获取多通道观测信号,利用FastICA对复合故障信号进行分离和包络解调,判断反绳轮轴承故障类型。通过搭建反绳轮轴承试验系统进行复合故障注入试验验证,结果表明,所提方法能够在强噪声背景下对复合故障信号进行分离并准确地提取了反绳轮轴承故障信号的特征。Aiming at the problem that the fault features of elevator reverse wheel bearing complex fault signals are easily disturbed by strong noise,a novel feature extraction method based on improved Variational Mode Decomposition(VMD)and Fast Independent Component Analysis(FastICA)was proposed.Based on the vibration signal of the reverse rope wheel bearing,the optimal VMD decomposition parameters were determined by the comprehensive fitness index,the multi-channel observation signals were obtained by VMD decomposition,and the composite fault signals were separated and envelope demodulated by FastICA to determine the fault type of the reverse rope wheel bearing.The results show that the proposed method can separate the compound fault signals under strong noise background and accurately extract the fault signal characteristics of the reverse rope wheel bearing.

关 键 词：特征提取 改进变分模态分解 快速独立分量分析 电梯反绳轮轴承 

分 类 号：TN911.6[电子电信—通信与信息系统]