基于灰关联理论的滚动轴承故障诊断研究

On Fault Diagnosis of Rolling Bearing Based on Grey Relevancy Theory

针对实际工程中滚动轴承故障的复杂灰特性以及不确定性问题,提出了基于灰关联理论故障诊断方法。灰关联理论具有"小样本、贫信息、不确定性"问题处理能力强、计算复杂度低等优点。通过对灰关联原理、灰关联系数与分辨系数的关系,以及分辨系数的性质和取值原则的研究,成功地将灰关联理论应用于滚动轴承的故障诊断。仿真实例研究结果表明,灰关联故障诊断方法计算简单、诊断结果与定性分析结论一致,便于形成知识库中的规则,对工程实践具有理论指导作用,且对样本数量及其分布规律没有特殊要求,有较大实用价值。

A fault diagnosis method is proposed based on grey relevancy theory to deal with the complicated grey characteristics and uncertainty problems of the running roiling bearing. The grey relevancy theory has advantages of simplified computation and more capability of dealing with the problems with uncertainty, small samples and lack of information. The grey relevancy theory, the relationship between the grey relational coefficient and the distinguishing coefficient, and the property and the selection theory of the distinguishing coeffieient axe studied. The grey relevancy theory is applied to the fault diagnosis problems of rolling bearing. Results of the practical application show that the fault diagnosis method based on grey relevancy analysis has the advantages of simplified computation, consistency to the quality analysis result, convenient for form knowledge base rides, and no special requirements for the quantity and distribution of samples, furthermore, it also provide theoretical guidance for the practical engineering or maintenance of the equipment.