基于数学形态分形维数与模糊C均值聚类的滚动轴承退化状态识别

Rolling Bearing Performance Degradative State Recognition Based on Mathematical Morphological Fractal Dimension and Fuzzy Center Means

针对滚动轴承的退化状态识别问题,融合数学形态学与模糊聚类理论,提出一种基于数学形态分形维数与模糊C均值聚类的退化状态识别方法。以数学形态分形维数作为滚动轴承的性能退化特征,从分形角度定量描述其复杂度与不规则度。鉴于不同退化状态边界的模糊性,将模糊C均值聚类方法应用于对退化状态的模糊聚类中,根据最大隶属度原则识别轴承性能退化状态。依托杭州轴承试验研究中心进行滚动轴承疲劳寿命强化试验,采集了滚动轴承从完好到失效的整套全寿命数据,将该方法应用于滚动轴承全寿命周期振动信号中,总体状态识别成功率达到96%.研究结果表明:该方法计算代价小、效率高,能够有效地识别出滚动轴承的性能退化状态。

In allusion to the degenerative state recognition of rolling bearing,a performance degenerative recognition method based on mathematical morphological fractal dimension（ MMFD） and fuzzy center means（ FCM） is proposed by combining mathematical morphology and fuzzy assemble theory. MMFD is calculated for the performance degenerative feature of rolling bearing to describe its complexity and irregularity in the view of fractal. In consideration of the fuzziness among different performance degradation boundaries,FCM is introduced into fuzzy clustering for characteristic index,and the performance degradation could be recognized effectively in line with maximum subordinate principle. The fatigue life enhancement test of rolling bearing was carried out to gather the whole life data at Hangzhou Bearing Test Research Center. The method is applied to the whole life data of rolling bearing,the overall state successful recognition rate reachs 96%. The results show that the method has a small calculating cost and ahigh efficiency,and can efficiently identify the performance degenerative state of rolling bearings.