基于AESL-GA的BN球磨机滚动轴承故障诊断方法

Fault diagnosis method of BN ball mill rolling bearing based on AESL-GA

针对基于知识的贝叶斯网络(BN)构建方法存在不完全和不精确的缺点,提出一种基于知识引导和数据挖掘的BN结构构建方法。针对单一信号故障诊断结果不精确的问题和故障信息中存在的不确定性问题,将电流信号与振动信号融合建立BN的特征节点,分别提取2种信号的故障特征参数,利用区分度指标法进行特征筛选,将其作为BN结构特征层的节点。将专家知识构建的初始BN结构结合自适应精英结构遗传算法(AESL-GA)进行结构优化,通过自适应限制进化过程中的搜索空间,减少自由参数的数量,提高其全局搜索能力,得到最优BN结构。通过MQY5585溢流型球磨机滚动轴承实测数据和Paderborn University轴承数据集对所提方法进行验证,结果证明了所提方法的有效性。

To address the imperfect and imprecise shortcomings of the knowledge-based Bayesian network(BN)construction method,this paper proposes a BN structure construction method based on knowledge guidance and data mining.Firstly,aiming at the problem of inaccurate fault diagnosis results of a single signal and the uncertainty in fault information,the current signal and the vibration signal are fused to establish the characteristic nodes of the BN.The fault characteristic parameters of the two kinds of signals are extracted respectively,and the feature selection is carried out by the distinguish index method,which is used as the node of the feature layer of the BN structure.Secondly,the initial BN structure constructed by expert knowledge is combined with the adaptive elite-based structure learner using genetic algorithm(AESL-GA)to optimize the structure.By adaptively restricting the search space in the evolution process,reducing the number of free parameters and improving its global search ability,we obtain optimal BN structure.Finally,the method is verified by the measured data of the ball mill rolling bearing of Jinchuan Company and the data set of Paderborn University,which proves the effectiveness of the proposed method.