北京航空航天大学学报 ›› 2019, Vol. 45 ›› Issue (11): 2291-2300.doi: 10.13700/j.bh.1001-5965.2019.0082

• 论文 • 上一篇    下一篇

基于半监督迁移学习的轴承故障诊断方法

张振良, 刘君强, 黄亮, 张曦   

  1. 南京航空航天大学 民航学院, 南京 211106
  • 收稿日期:2019-03-11 出版日期:2019-11-20 发布日期:2019-11-30
  • 通讯作者: 刘君强.E-mail:liujunqiang@nuaa.edu.cn E-mail:liujunqiang@nuaa.edu.cn
  • 作者简介:张振良 男,硕士研究生。主要研究方向:故障诊断、机器学习;刘君强 男,博士,副教授,硕士生导师。主要研究方向:机场规划、民航发动机寿命预测;黄亮 男,硕士研究生。主要研究方向:机场规划、民航发动机寿命预测;张曦 男,硕士研究生。主要研究方向:机器学习、寿命预测。

A bearing fault diagnosis method based on semi-supervised and transfer learning

ZHANG Zhenliang, LIU Junqiang, HUANG Liang, ZHANG Xi   

  1. School of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
  • Received:2019-03-11 Online:2019-11-20 Published:2019-11-30

摘要: 针对航空发动机轴承故障诊断过程中预测精度不足以及过拟合的问题,提出基于迁移学习的半监督集成学习器(SSIT)用以发动机轴承故障预测。首先,训练改进的基于迁移学习的极限学习机(TELM)以及基于迁移学习的支持向量机(TSVM),分别迁移不同目标空间的高相似度样本加入到源样本空间进行训练。然后,与对应的基学习器集成同簇学习器来识别未标记样本,构成半监督学习器不断调整初始基学习器权重,并继续集成半监督基学习器的识别结果到SSIT中。通过此学习机识别提取特征后的,用以故障识别。实验结果清楚地表明:此种方法可以有效降低迁移学习中的负迁移效果,提升迁移精度10%左右,降低机器学习中的过拟合效果,提高半监督学习稳定性,与现有的预测方法相比可以提高精度9%以上。

关键词: 航空发动机, 故障诊断, 半监督, 迁移学习, 集成学习

Abstract: Aimed at the problems of insufficient prediction accuracy and over-fitting in the fault diagnosis process of aero-engine bearing, a semi-supervised integrated learning device based on transfer learning (SSIT) is proposed to predict engine bearing fault. First, transfer learning based improved extreme learning machine (TELM) and support vector machines (TSVM) were trained by adding the high-similarity sample of different target space to the original sample space, which is integrated to identify the tag sample with the corresponding learning. Then integrate the same cluster learner with the corresponding base learner to identify the unlabeled samples, Next, the constituted semi-supervised learning device constantly adjusts the initial learning unit weight, and continues to integrate semi-supervised learning recognition results into SSIT, which will be used to identify faults after feature identification and extraction by this learning machine. The experimental results clearly show that this algorithm can effectively reduce the negative transfer effect in transfer learning, improve the transfer accuracy by about 10%, reduce the over-fitting effect in machine learning, and improve the stability of semi-supervised learning. Compared with the existing prediction method, this algorithm can improve the accuracy by more than 9%.

Key words: aevo-engine, fault diagnosis, semi-supervision, transfer learning, integrated learning

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发