邻域知识图算法在旋转机械设备故障诊断中的应用

Application of Neighborhood Knowledge Graph Algorithm in Fault Diagnosis of Rotating Machinery

摘要:

旋转机械应用过程中极易出现内环故障、外环故障、滚动体故障的情况,而这也直接影响机械部件的使用寿命。为准确诊断设备元件的故障行为,达到延长旋转机械设备寿命水平的目的,针对邻域知识图算法在旋转机械设备故障诊断中的应用展开研究。求解邻域知识图算法的函数表达式,并以此为基础,完成对故障数据的推荐,再通过预处理的方式,实现对旋转机械设备故障数据的深度挖掘。融合关键故障数据,并对其进行降维处理,根据核特征定义条件,完善具体的故障诊断流程,完成基于邻域知识图算法的旋转机械设备故障诊断算法的设计。实验结果表明,上述方法的应用,可以准确诊断出内环故障、外环故障、滚动体故障三种故障表现行为,通过适当方法对所诊断出故障行为加以处理,可以达到延长旋转机械设备使用寿命的目的。

Abstract:

In the application of rotating machinery, inner ring failure, outer ring failure and rolling element failure are easy to occur, which also directly affects the service life of mechanical parts. In order to accurately diagnose the fault behavior of equipment components and extend the life level of rotating machinery equipment, the application of neighborhood knowledge graph algorithm in fault diagnosis of rotating machinery equipment is studied. The function expression of the neighborhood knowledge graph algorithm is solved, and based on this, the fault data is recommended, and the deep mining of the rotating machinery equipment fault data is realized by the way of preprocessing. The key fault data is fused and dimensionally reduced, and the specific fault diagnosis process is improved according to the definition conditions of kernel characteristics, and the fault diagnosis algorithm of rotating machinery equipment based on neighborhood knowledge graph algorithm is designed. The experimental results show that the application of the above method can accurately diagnose the inner ring fault, the outer ring fault and the rolling element fault. The purpose of prolongating the service life of the rotating machinery equipment can be achieved by dealing with the diagnosed fault behavior appropriately.