基于频域特征波形模式匹配的故障诊断方法研究  

Approach for Fault Diagnosis Based on Pattern Match of Characteristic Waveforms in Frequency Domain

作　　者：焦卫东 丁祥满[2] 严天宇 闫莹莹 Jiao Weidong;Ding Xiangman;Yan Tianyu;Yan Yingying(Key Laboratory of Intelligent Operation and Maintenance Technology&Equipment for Urban Rail Transit of Zhejiang Province;School of Engineering,Zhejiang Normal University,Jinhua 321004,China)

机构地区：[1]浙江省城市轨道交通智能运维技术与装备重点实验室 [2]浙江师范大学工学院,浙江金华321004

出　　处：《华东交通大学学报》2021年第2期73-81,共9页Journal of East China Jiaotong University

基　　金：国家自然科学基金项目(51575497);浙江省城市轨道交通智能运维技术与装备重点实验室自主研究项目(ZSDRTZZ2020002)。

摘　　要：利用同一模式类振动观测样本在FFT幅值谱特征波形上的整体相似性,提出一种基于频域特征波形模式匹配的故障诊断方法,应用于滚动轴承故障诊断并与一些典型的模式识别诊断法进行了对比研究。研究发现:当测试样本所属模式类与训练样本相同时,频域特征波形模式匹配的余弦相似度、相关相似度或互信息相似度均达到最大值。据此确定用于模式分类的特征相似度阈值,分类准确性达到100%。研究结果表明:基于频域特征波形模式匹配的故障诊断方法不需要繁琐的特征提取,也不需要复杂的分类器设计,仅仅通过简单的频域特征波形模式匹配、特征阈值比较即可实现多个复杂模式的准确分类。此外,该方法适于解决小样本分类问题,而且分类效率高,自学习能力强,明显优于一些典型的模式识别诊断法,在构建在线的自动故障分类系统方面具有较大的应用潜力。An approach for fault diagnosis based on pattern match of characteristic waveforms in frequency domain was proposed.It used the principle of global similarity on the characteristic waveforms of FFT-based amplitude spectrum of the vibration observation samples belonging to the identical pattern class.It was then applied to fault diagnosis of rolling element bearings,and compared with some typical diagnosis approaches based on pattern recognition.It was found that the cosine similarity,correlation similarity or mutual information similarity from pattern match of the characteristic waveforms in frequency domain reached the maximum respectively,when the test sample belonged to the identical pattern class as the training samples.According to this,the characteristic similarity threshold for pattern classification was determined,which contributed to 100%classification accuracy.The results show that the proposed approach for fault diagnosis needs neither sophisticated feature extraction nor complicated classifier design.It can accurately classify multiple complex patterns only by simple pattern match on characteristic waveforms in frequency domain and feature threshold comparison.In addition,it is suitable for solving the problem of small-sample classification with high classification efficiency and strong self-learning ability.It is obviously superior to some typical diagnosis approaches based on pattern recognition,and has great application potential in constructing on-line automatic fault classification system.

关 键 词：机械工程 滚动轴承 故障诊断 模式匹配 频域特征波形 

分 类 号：U279[机械工程—车辆工程]