当前位置>主页 > 期刊在线 > 智能制造 >

智能制造2019年16期

基于PCA 和预测误差法的轴承故障预测方法研究
熊强
(广州航新航空科技股份有限公司,广东 广州 510663)

摘  要:在轴承故障诊断中,及时判断出故障具有重要的意义,针对该问题,提出一种基于主成分分析(PCA)和预测误差法的轴承故障预测方法,该方法利用主成分分析方法提取出反映轴承故障的健康监测指标,将该指标作为状态空间的输入,利用预测误差法求解状态空间模型,并对轴承健康监测指标进行预测。结果表明,预测结果与历史数据一致,通过预测值与设定的阈值的比较,可以实现提前预警的目的。


关键词:故障诊断;故障预测;主成分分析;预测误差法



中图分类号:TP181;TH133.33         文献标识码:A         文章编号:2096-4706(2019)16-0165-03


Study on Bearing Fault Prediction Method Based on PCA and Prediction Error Method

XIONG Qiang

(Guangzhou Hangxin Aviation Technology Co.,Ltd.,Guangzhou 510663,China)

Abstract:In bearing fault diagnosis,it is of great significance to judge the fault in time. In order to solve this problem,a bearing fault prediction method based on principal component analysis (PCA) and prediction error method is proposed. This method uses principal component method to extract the health monitoring indicator reflecting bearing fault. This index is used as the input of state space.The prediction error method is used to solve the state space model,and the bearing health monitoring indicator is predicted. The results show that the prediction results are consistent with the historical data,and the purpose of early warning can be achieved by comparing the predicted values with the set threshold.

Keywords:fault diagnosis;fault prediction;principal component analysis;prediction error method


参考文献:

[1] Jardine A K S,Lin D,Banjevic D. A review on machinery diagnostics and prognostics implementing condition-based maintenance [J].Mechanical Systems and Signal Processing,2006,20(7):1483-1510.

[2] 张玉. 基于振动幅域参数指标的滚动轴承故障诊断 [J]. 机械制造与自动化,2011,40(3):47-51.

[3] 李志文. 包络技术在滚动轴承早期故障诊断中的应用 [J].设备管理与维修,2017(5):113-115.

[4] 刘鲲鹏,苏涛,白云川,等. 基于小波变换与奇异值分解的滚动轴承故障诊断 [J]. 内燃机与配件,2018(24):24-25.

[5] 李亚帅,邵宗凯. 基于PEM 的三自由度直升机模型辨识 [J]. 传感器与微系统,2017,36(6):49-52+56.

[6] 王梓杰,周新志,宁芊. 基于PCA 和随机森林的故障趋势预测方法研究 [J]. 计算机测量与控制,2018,26(2):21-23+26.


作者简介:熊强(1985-),男,汉族,湖北荆门人,振动分析工程师,硕士,研究方向:健康监测与故障诊断。