【摘要】 针对传统滚动轴承故障诊断方法在噪声或故障数据不平衡条件下，其故障特征提取能力不足导致其诊断性能较差等问题，提出了一种基于卷积神经网络(CNN)和集成支持向量机(SVM)故障诊断方法。首先利用卷积神经网络逐层提取代表性的故障特征，然后将各层特征分别送入支持向量机(SVM)进行故障分类，通过集成策略将多个故障分类结果融合成一个更加稳定且识别精度更高的诊断结果。最后，采用滚动轴承数据集验证其有效性，并与其他故障诊断方法比较，实验结果表明所提方法具有更好的故障诊断性能。更多还原

【Abstract】 This paper propose a novel fault diagnosis method based on convolutional neural network(CNN) and ensemble support vector machine(SVM) to address the poor diagnosis performance of traditional rolling bearing fault diagnosis methods due to the lack of fault feature extraction ability under the condition of noise or unbalanced fault data. Firstly, a CNN is used to extract representative fault features layer by layer, and then the features of each layer are fed into an SVM for fault classification. Finally, multiple fault classification results are fused into a more stable and more accurate diagnosis result through integration strategy. The effectiveness of this method is verified using a rolling bearing dataset, and experimental results show that it outperforms other fault diagnosis method.更多还原