论文部分内容阅读
齿轮是旋转机械中的关键元件。提出了一个基于支持向量机的齿轮多故障分类方法。齿轮状态被划分为正常、齿轮磨损和断齿状态。振动信号的均方根和小波包能量被选作为分类器的特征参数。分类器选用支持向量机(SVM)。SVM具有良好的实用性及多分类能力。实验结果表明:提出的方法能很好地区分齿轮故障。
Gears are the key components in rotating machinery. A multi-fault classification method based on support vector machine is proposed. Gear status is divided into normal, gear wear and broken tooth condition. The root mean square of the vibration signal and the wavelet packet energy are chosen as the characteristic parameters of the classifier. Classifier using support vector machine (SVM). SVM has good practicability and multi-classification ability. The experimental results show that the proposed method can distinguish gear failure well.