针对旋转机械故障诊断方法中信号处理和模式识别的不足,即端点效应和判别片面性问题,提出一种基于互相关匹配延拓局部特征尺度分解(Cross-correlation matching endpoint Extension Local Characteristic scale Decomposition,CELCD)和...针对旋转机械故障诊断方法中信号处理和模式识别的不足,即端点效应和判别片面性问题,提出一种基于互相关匹配延拓局部特征尺度分解(Cross-correlation matching endpoint Extension Local Characteristic scale Decomposition,CELCD)和改进多变量预测模型(Variable Predictive Model based Class Discriminate,VPMCD)的智能故障诊断方法,首先探索待分解信号前后端的数据规律,选取匹配波形完成端点延拓,然后利用局部特征尺度分解(Local Characteristic scale Decomposition,LCD)得到各去除端点效应的内禀尺度分量(Intrinsic Scale Component,ISC),最后输入到基于多模型融合的多变量预测模型(Multi-model Fusion-Variable Predictive Model based Class Discriminate,MFVPMCD)分类器中进行概率状态判定.实验分析结果表明,所提方法能有效地对滚动轴承的工作状态进行识别.展开更多
In view of the usefulness of Empirical Mode Decomposition (EMD), Artificial Neural Networks ( ANN), and Most Relevant Matching Extension (MRME) methods in dealing with nonlinear signals, we pro- pose a new way o...In view of the usefulness of Empirical Mode Decomposition (EMD), Artificial Neural Networks ( ANN), and Most Relevant Matching Extension (MRME) methods in dealing with nonlinear signals, we pro- pose a new way of combining these methods to deal with signal prediction. We found the results of combining EMD with either ANN or MRME to have higher prediction precision for a time series than the result of using EMD alone.展开更多
文摘针对旋转机械故障诊断方法中信号处理和模式识别的不足,即端点效应和判别片面性问题,提出一种基于互相关匹配延拓局部特征尺度分解(Cross-correlation matching endpoint Extension Local Characteristic scale Decomposition,CELCD)和改进多变量预测模型(Variable Predictive Model based Class Discriminate,VPMCD)的智能故障诊断方法,首先探索待分解信号前后端的数据规律,选取匹配波形完成端点延拓,然后利用局部特征尺度分解(Local Characteristic scale Decomposition,LCD)得到各去除端点效应的内禀尺度分量(Intrinsic Scale Component,ISC),最后输入到基于多模型融合的多变量预测模型(Multi-model Fusion-Variable Predictive Model based Class Discriminate,MFVPMCD)分类器中进行概率状态判定.实验分析结果表明,所提方法能有效地对滚动轴承的工作状态进行识别.
基金supporteal by the Notional Natural Scince Foundation of Hebei Province(D201000921)
文摘In view of the usefulness of Empirical Mode Decomposition (EMD), Artificial Neural Networks ( ANN), and Most Relevant Matching Extension (MRME) methods in dealing with nonlinear signals, we pro- pose a new way of combining these methods to deal with signal prediction. We found the results of combining EMD with either ANN or MRME to have higher prediction precision for a time series than the result of using EMD alone.