量化特征多粒度模型在行星齿轮箱故障诊断中的应用
Application of Valued Characteristic Multi-granularity Model in Fault Diagnosis of Planetary Gearboxes

传感器失灵、通讯迟滞或数据离散化等多种不确定因素会导致行星齿轮箱故障诊断信息不完备情况的发生，而现有的故障诊断方法已难于适用。为此，提出一种基于数据驱动量化特征多粒度模型的行星齿轮箱故障诊断方法。首先，采用数据驱动量化特征关系对行星齿轮箱的不完备故障诊断信息进行分析；其次，利用基于悲观数据驱动量化特征多粒度模型的属性约简算法提取故障诊断决策规则；最后，使用朴素贝叶斯分类器（Naive Bayesian classifier，NBC）推断待诊行星齿轮箱状态。实验研究表明，该方法可准确地判断实例间的不可分辨关系，降低计算复杂度，提高故障诊断准确率。
There are many uncertain factors that may result in incomplete diagnostic information of planetary gearboxes, such as sensor failures, communication lags and data discretization, etc. However, the existing methods are not suitable for fault diagnosis. Therefore, a fault diagnosis method of planetary gearboxes based on data-driven valued characteristic multi-granularity model is proposed. Incomplete fault diagnosis information of planetary gearbox is analyzed using data-driven valued characteristic relation. Then, the attribute reduction algorithm based on pessimistic data-driven valued characteristic multi-granularity model is employed to extract fault diagnosis decision rules. Finally, the Naive Bayesian classifier is used to determine planetary gearbox condition. The experimental results demonstrate that this method can accurately determine indiscernibility relation among cases, reduce computational complexity, and enhance fault diagnosis accuracy