首页|基于决策树的电气设备异常振动信号智能分类方法

基于决策树的电气设备异常振动信号智能分类方法

扫码查看
当前,电气设备异常振动信号智能分类方法效果不佳.为此,提出基于决策树的电气设备异常振动信号智能分类方法.提取振动频率、幅值、相位差及信号变化峰值点4个特征参量,通过权函数叠加拟合获取综合特征.采用决策树算法构造信号弱分类器,再用支持向量机优化为强分类器,输入信号特征,输出异常振动信号类别,由此实现对电气设备异常振动信号的智能分类.实例应用结果显示,所提方法可以有效识别设备异常振动信号类型,分类精度较高.
Intelligent Classification Method of Abnormal Vibration Signal of Electrical Equipment Based on Decision Tree
The current intelligent classification method for abnormal vibration signals of electrical equipment is not effective.Therefore,an intelligent classification method of abnormal vibration signal of electrical equipment based on decision tree is proposed.Four characteristic parameters of vibration frequency,amplitude,phase difference and peak point of signal change are extracted,and the comprehensive features are obtained by weight function superposition fitting.The decision tree algorithm is used to construct a weak signal classifier,and then the support vector machine is optimized to a strong classifier to input the signal characteristics and output the abnormal vibration signal category,so as to realize the intelligent classification of abnormal vibration signals of electrical equipment.The application results show that the proposed method can effectively identify the types of abnormal vibration signals of equipment,and the classification accuracy is high.

decision treeelectrical equipmentabnormal vibration signalintelligent classification

吴明泽

展开 >

盐城工学院优培学院,江苏盐城 224051

决策树 电气设备 异常振动信号 智能分类

2024

信息与电脑
北京电子控股有限责任公司

信息与电脑

影响因子:1.143
ISSN:1003-9767
年,卷(期):2024.36(6)