中文摘要：

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.

英文摘要：

To suppress end effects of signal processing and judgment contingency of pattern recognition in the rotating machinery fault diagnosis method,an intelligent fault diagnosis method is proposed based on the cross-correlation matching endpoint extension local characteristic scale decomposition（ CELCD） and the improved variable predictive model based class discriminate（ VPMCD）. Firstly,the characteristic of the decomposed signal is explored and the matched waveform is selected to complete the endpoint extension. Then the extension waveform is decomposed by the local characteristic scale decomposition（ LCD）,at the same time,and the intrinsic scale components（ ISCs） with removed endpoint effect are obtained. Finally,the features of each ISC are extracted and input to the multi-model fusion-variable predictive model based class discriminate（ MFVPMCD） classifier for the judgment of state probability. Experimental results showthat the proposed method can effectively identify the running state of roller bearing.