摘要
液压泵振动信号具有非线性、非平稳性的特点,熵算法在该类信号分析方面有着独到的优势,但传统的熵算法在液压泵振动信号特征提取中有计算速度慢、熵值不准确、不稳定等不足,为了更有效地提取故障特征信息并提高故障诊断准确性,将精细复合多尺度波动散布熵(refined composite multiscale fluctuation dispersion entropy,RCMFDE)引入到液压泵的故障特征提取中,提出了一种基于RCMFDE和粒子群优化支持向量机结合的液压泵故障诊断方法。计算不同故障振动信号的RCMFDE,并选取合适尺度下的多个RCMFDE值作为特征向量形成特征样本,输入粒子群优化支持向量机中进行故障分类识别。通过仿真信号和液压泵故障实测信号进行分析,并将所提出的方法与基于多尺度样本熵(multiscale sample entropy,MSE)、多尺度排列熵(multiscale permutation entropy,MPE)、多尺度符号动态熵(multiscale symbolic dynamic entropy,MSDE)、多尺度散布熵(multiscale dispersion entropy,MDE)、精细复合多尺度散布熵(refined composite multiscale dispersion entropy,RCMDE)、多尺度波动散布熵(multiscale fluctuation dispersion entropy,MFDE)的故障特征提取方法进行对比。试验结果表明,该方法能够更加准确地识别多类液压泵故障并能对液压泵性能退化程度进行有效评估。
The vibration signal of hydraulic pump has the characteristics of non-linearity and non-stationarity.Entropy algorithms have a unique advantage in this kind of signal analysis.However,the traditional entropy algorithms still have shortcomings of slow calculation speed,inaccurate entropy value and unstable entropy value in hydraulic pump vibration signal feature extraction.To extract fault feature information more effectively and improve fault diagnosis accuracy,the refined composite multiscale fluctuation dispersion entropy(RCMFDE)was introduced into the fault feature extraction of hydraulic pumps.A hydraulic pump fault diagnosis method based on RCMFDE and the particle swarm optimization support vector machine(PSO-SVM)algorithm was proposed.Firstly,the RCMFDE values of different fault vibration signals were calculated and the multi-RCMFDE values were selected at appropriate scales as feature vectors to form feature samples.Then the feature samples were input to PSO-SVM for fault diagnosis.Through analyzing the simulation signals and hydraulic pump experiments signals,the proposed method was compared with the fault diagnosis methods based on multiscale sample entropy(MSE),multiscale permutation entropy(MPE),multiscale symbolic dynamic entropy(MSDE),multiscale dispersion entropy(MDE),refined composite multiscale dispersion entropy(RCMDE),and multiscale fluctuation dispersion entropy(MFDE).Experimental results show that the proposed method can accurately identify multiple types of hydraulic pump faults and effectively evaluate the performance degradation degree of hydraulic pump.
作者
姜万录
赵亚鹏
张淑清
李满
JIANG Wanlu;ZHAO Yapeng;ZHANG Shuqing;LI Man(Hebei Provincial Key Laboratory of Heavy Machinery Fluid Power Transmission and Control,Yanshan University,Qinhuangdao 066004,China;Key Laboratory of Advanced Forging&Stamping Technology and Science,Ministry of Education of China,Yanshan University,Qinhuangdao 066004,China;Institute of Electrical Engineering,Yanshan University,Qinhuangdao 066004,China)
出处
《振动与冲击》
EI
CSCD
北大核心
2022年第8期7-16,共10页
Journal of Vibration and Shock
基金
国家自然科学基金项目(51875498)
河北省自然科学基金重点项目(E2018203339,F2020203058)。
关键词
波动散布熵
精细复合多尺度波动散布熵(RCMFDE)
粒子群优化支持向量机
故障诊断
液压泵
fluctuation dispersion entropy
refined composite multiscale fluctuation dispersion entropy(RCMFDE)
particle warm optimization support vector machine
fault diagnosis
hydraulic pump
