基于改进DANN迁移学习的轴承寿命预测方法  

A Bearing Life Prediction Method Based on Improved DANN Transfer Learning

作　　者：徐嘉杰 沈艳霞[1] XU Jia-jie;SHEN Yan-xia(College of IoT Engineering,Jiangnan University)

机构地区：[1]江南大学物联网工程学院

出　　处：《化工自动化及仪表》2023年第4期493-499,594,共8页Control and Instruments in Chemical Industry

基　　金：国家重点研发计划项目(2020YFB1711100,2020YFB1711102)。

摘　　要：为解决不同工况下轴承寿命预测精度受限的问题,提出一种基于Wasserstein距离改进的领域对抗网络(DANN)迁移学习的轴承寿命预测方法。在IEEE PHM Challenge 2012轴承数据集上进行实验,结果表明:对比多种迁移学习方法,笔者所提WDANN方法能够有效提高不同工况下轴承寿命预测精度。For purpose of solving limited accuracy of bearing life prediction under different operating conditions,a bearing life prediction method based on Wasserstein distance improved-domain adversarial network(DANN)migration learning was proposed.Experiments conducted on the IEEE PHM Challenge 2012 bearing dataset show that,as compared to traditional migration learning methods,the proposed method is effective in improving the accuracy of bearing life prediction under different operating conditions.

关 键 词：轴承 剩余寿命预测 迁移学习 领域对抗 Wasserstein距离 

分 类 号：TP206.3[自动化与计算机技术—检测技术与自动化装置] TP911.7[自动化与计算机技术—控制科学与工程]