基于精细化改进多尺度快速样本熵的旋转机械故障诊断方法研究  

RESEARCH ON FAULT DIAGNOSIS METHOD OF ROTATING MACHINERY BASED ON REFINED IMPROVED MULTISCALE FAST SAMPLE ENTROPY

作　　者：周付明 刘武强 杨小强 申金星 陈赵懿 ZHOU FuMing;LIU WuQiang;YANG XiaoQiang;SHEN JinXing;CHEN ZhaoYi(School of Field Engineering,Army Engineering University of PLA,Nanjing 210001,China;National Defense Key Laboratory of Science and Technology on Vessel Integrated Power Technology,Naval University of Engineering,Wuhan 430033,China)

机构地区：[1]陆军工程大学野战工程学院,南京210001 [2]海军工程大学舰船综合电力技术国防科技重点实验室,武汉430033

出　　处：《机械强度》2023年第1期1-8,共8页Journal of Mechanical Strength

摘　　要：为了解决现有多尺度样本熵(Multiscale Sample Entropy, MSE)方法提取复杂序列特征时存在的计算效率低及幅值信息缺失等问题,提出精细化改进多尺度快速样本熵(Refined Improved Multiscale Fast Sample Entropy, RIMFSE)方法。首先使用快速样本熵代替传统样本熵,通过改进重构向量匹配机制大幅降低了计算成本,而后使用改进的多尺度拓展方法代替传统的粗粒化方法,避免了幅值信息的丢失。在此基础上,结合最大相关最小冗余(Max-relevance and Min-redundancy, mRMR)方法及支持向量机(Support Vector Machine, SVM)分类器提出一种新的旋转机械故障诊断方法。使用齿轮箱和轴承两个故障数据集对提出方法的性能进行验证,同时将提出的方法与MSE,复合MSE(Composite Multiscale Sample Entropy, CMSE)及精细化复合MSE(Refined Composite Multiscale Sample Entropy, RCMSE)等现有方法进行对比。结果表明,相较于MSE、CMSE及RCMSE,提出的方法在鲁棒性、计算效率及识别精度等方面均具有明显优势,为基于熵特征提取的旋转机械故障诊断提供了一种新的思路。To solve the problems of low computational efficiency and missing amplitude information existing in the current multiscale sample entropy(MSE) method when extracting features of complex series, refined improved multiscale fast sample entropy(RIMFSE) is presented. Firstly, fast sample entropy is employed to substitute traditional sample entropy, and the calculation cost is greatly reduced by improving the matching mechanism of reconstructed vectors. After that, the improved multiscale expansion method is applied to replace the traditional coarse-grained method, thereby avoiding the loss of amplitude information. Based on this, a new rotating machinery fault diagnosis method is proposed in combination with the max-relevance and min-redundancy(mRMR) method and the support vector machine(SVM) classifier. Two fault data sets of gearbox and bearing are used to verify the performance of the presented method;meanwhile, the presented method is compared with existing methods such as MSE, composite MSE(CMSE) and refined composite MSE(RCMSE). The results show that compared with MSE, CMSE and RCMSE, the proposed method enjoys significant advantages in terms of robustness, calculation efficiency and recognition accuracy, thereby providing a new idea for rotating machinery fault diagnosis based on entropy feature.

关 键 词：精细化改进多尺度快速样本熵 最大相关最小冗余 支持向量机分类器 旋转机械 故障诊断 

分 类 号：TH165.3[机械工程—机械制造及自动化]