融合TA-TCN和迁移学习的滚动轴承寿命预测
Rolling Bearing Life Prediction Combining TA-TCN and Transfer Learning
车鲁阳 1冷子文 2付惠琛 1张佳佳 1高军伟1
作者信息
- 1. 青岛大学自动化学院,青岛 266071;青岛大学山东省工业控制技术重点实验室,青岛 266071
- 2. 山东省特种设备检验科学研究院,日照 276826
- 折叠
摘要
针对在实际工业生产中,滚动轴承由于数据量少导致剩余寿命预测的准确度不高的问题,提出了一种时序注意力(temporal attention,TA)优化的时间卷积神经网络(time convolutional networks,TCN)与迁移学习相结合的剩余寿命预测方法.首先,通过互补集合经验模态分解(complementary ensemble empirical mode decomposition,CEEMD)将原始特征向量分解为一组子序列分量,突出特征信号、降低噪声干扰;然后,将子序列分量输入搭建好的TCN模型并添加TA进行优化,深度挖掘深度特征与退化曲线关系;最后,引入迁移学习,利用源域数据进行训练和少量目标域数据进行参数微调,得到目标网络模型.经实例验证,所提模型的稳定性、预测精度相对于其它对比模型有所提升,且在异工况条件下依然有着良好的预测能力.
Abstract
Aiming at the problem that the accuracy of remaining life prediction of rolling bearings is not high due to the small amount of data in actual industrial production,a time convolutional neural network(TCN)optimized by temporal attention(TA)and transfer learning is proposed.Firstly,the original eigen-vector is decomposed into a set of subsequence components by empirical mode decomposition of comple-mentary sets(CEEMD)to highlight the eigensignal and reduce noise interference.Then,the subsequence components are input into the built TCN model and TA is added for optimization,and the relationship be-tween the depth features and the degradation curve is deeply explored.Finally,transfer learning is intro-duced to obtain the target network model by using the source domain data for training and a small amount of target domain data for parameter fine-tuning.After example verification,the stability and prediction accu-racy of the proposed model are improved compared with other comparison models,and it still has good pre-diction ability under different working conditions.
关键词
滚动轴承/寿命预测/互补集合经验模态分解/时序注意力/时间卷积神经网络/迁移学习Key words
rolling bearing/life prediction/complementary ensemble empirical mode decomposition/tem-poral attention/temporal convolutional neural networks/transfer learning引用本文复制引用
基金项目
山东省自然科学基金(ZR2019MF063)
出版年
2024
NETL
NSTL
万方数据