Fault severity identification of roller bearings using flow graph and non-naive Bayesian inference

Abstract

In order to address the problem that redundant condition attribute nodes and poor reasoning ability of flow graph may lead to high computational burden and low diagnosis accuracy, a fault severity identification method of roller bearings using flow graph and non-naive Bayesian inference is put forward in this paper. First, a normalized flow graph constructed according to fault features of roller bearings extracted from training samples is used to represent and describe the causal relationship among attributes. Then, the significance degree of condition attribute node with respect to the decision attribute node set is defined to quantitatively measure the impact of the node on the decision-making abilities of the flow graph. A node reduction algorithm based on significance degree of condition attribute node is developed to delete redundant or irrelevant condition attribute nodes, which can improve clustering distribution and reduce computational complexity. Finally, non-naive Bayesian inference is utilized to extend the flow graph to make it applicable in the tasks of reasoning, and an non-naive Bayesian inference algorithm based on flow graph is presented to identify roller-bearing conditions in test samples. The effectiveness of the proposed method is validated through a fault severity identification experiment of roller bearings. Fault severity identification results show that the proposed method can intuitively and accurately recognize fault severities of roller bearings.