基于流向图和非朴素贝叶斯推理的滚柱轴承故障程度识别

A Fault severity identification of roller bearings based on flow graph and NNBI

针对流向图分类推理能力较弱、计算成本较高的问题,提出一种基于流向图和非朴素贝叶斯推理的滚柱轴承故障程度识别方法。提取训练样本中滚柱轴承的故障特征构建标准化流向图,用于直观地表示属性间的因果关系;采用基于征兆属性节点重要度的节点约简算法删除冗余的征兆属性节点,以降低分类推理的计算复杂度;利用基于流向图的非朴素贝叶斯推理算法识别待诊样本中滚柱轴承的状态。通过实验验证了所提方法在直观和准确识别滚柱轴承故障程度方面的有效性。

To address the issue of poor reasoning ability and the high computational burden of flow graphs,a fault severity identification method of roller bearings using flow graph and Non-naive Bayesian inference(NNBI)was put forward.A normalized flow graph constructed according to fault features of roller bearings extracted from training samples was used to represent the causal relationship among attributes in an intuitive manner.Then a node reduction algorithm based on SDCAN was developed to delete redundant condition attribute nodes,which could reduce computational complexity of mode identification.An NNBI algorithm based on flow graph was presented to identify roller bearing conditions in test samples.Experimental results demonstrated that the proposed method could intuitively and accurately recognize fault severities of roller bearings.