基于软竞争Yu范数自适应共振理论的轴承故障诊断方法

传统自适应共振理论网络模型利用硬竞争机制对故障类边界处的样本进行分类时易造成误分类，为此，提出了基于软竞争Yu范数自适应共振理论的轴承故障诊断方法。将基于模糊竞争学习的软竞争方法引入Yu范数自适应共振理论模型中，根据模式节点与输入样本间隶属度的大小，对竞争层多个节点进行训练和学习。通过对轴承故障试验数据的诊断分析可知，该方法不但能有效识别不同类型的故障，而且能识别不同严重程度故障，且诊断精度优于自适应共振理论模型和模糊C均值聚类模型。

Fault Diagnosis Method of Bearings by Yu's Norm ART Based on Soft Competition

Fault interfaces were categorized wrongly by ART with hard competition. A new fault diagnosis method by Yu's norm ART was proposed based on soft competition. The soft competition method of fuzzy competitive learning(FCL) was introduced into Yu's norm ART, neural nodes in the competition layer were trained according to the degree of membership among the mode nodes and the inputs. Bearing fault data were used to validate the fault diagnosis model, which proves that the fault diagnosis model may distinguish different faults, and distinguish different fault degrees under the same fault types. Comparing with other methods for fault diagnosis, such as ART and fuzzy C-means clustering, the proposed method has higher diagnostic accuracy.