针对旋转机械振动故障特征复杂的特点,提出采用基于K-L变换的故障提取方法.改进支持向量机的多分类算法,将支持向量机分类方法用于旋转机械振动分析,利用其模式辨别和系统建模能力对典型故障的初始征兆、发生、发展进行动态分析,为旋转机械的故障诊断提供新的思路和方法.%For the complex characteristics of rotating machinery vibration faults, a fault extraction method is proposed based on the K-L transformation. Multi-classification algorithm of support vector machine (SVM) is improved. And the support vector machine regression algorithm is used for rotating machinery vibration analysis. Using the capabilities of the improved SVM in model identification and system modeling, the initial symptom, occurrence and development of the typical faults are dynamically analyzed. This work provides new ideas and methods for fault diagnosis of rotating machinery.
展开▼