基于广义Ward聚类的汽车传动主轴系统故障诊断研究

Fault Diagnosis for Spindle System Based on General Ward Clustering

汽车传动主轴系统故障诊断对保证汽车系统的安全运行具有重要作用。针对汽车传动主轴系统故障诊断特征微弱的问题,在分析汽车传动主轴系统故障网络模型的基础上,提出一种基于广义Ward聚类的汽车传动主轴系统故障诊断方法,并对汽车传动主轴系统过载、滚动轴承元件故障进行实例验证。结果表明该方法能准确对故障类型数据进行聚类,为收集异常数据以便未知故障的发现与诊断提供了数据支持,与多元支持向量机和快速Newman算法的对比结果表明,该方法具有更高的识别精度与效率。

The fault diagnosis of spindle system plays an important role of ensuring the safe operation.According to the spindle system characteristics,this paper analyzes its failure and proposes a fault diagnosis method based on general ward clustering.The spindle overload and the rolling bearing fault are verified by the example.The results indicate that the proposed method can be use to cluster the fault samples effectively.The data support is provided for collecting unusual samples which could be used to discover and diagnose the unknown fault pattern.Compared with multi-class support machines and Fast Newman algorithm,this method is of higher accurateness and productiveness.