【摘要】 针对旋转机械中滚动轴承振动信号的非平稳特性和故障信号特征的微弱性,提出一种改进的自适应白噪声的完备集合经验模态分解(CEEMDAN)结合轴承信号能量特征的故障特征提取方法,与鲸鱼优化算法(WOA)和支持向量机(SVM)模型来实现故障模式识别。结果表明,该方法不但克服了EEMD分解效率低和模态混叠问题,而且有效地提高支持向量机的分类精度,获得了更高的故障诊断准确率。更多还原

【Abstract】 Aiming at the non-stationary characteristics of rolling bearing vibration signals and the weakness of fault signal characteristics in rotating machinery,an improved fault feature extraction method with the combination of complete ensemble empirical mode decomposition with adaptive noise( CEEMDAN) and bearing signal energy characteristics is proposed. Whale optimization algorithm( WOA) and support vector machine( SVM) model are used to realize fault mode recognition. This method not only overcomes the problems of low EEMD decomposition efficiency and modal aliasing,but also effectively improves the classification accuracy of support vector machines and obtains higher fault diagnosis accuracy.更多还原