空军工程大学学报2025，Vol.26Issue(2)：81-88,8.DOI:10.3969/j.issn.2097-1915.2025.02.010
基于深度学习的导航装备轴承剩余使用寿命预测
A Navigational Equipment Bearing Remaining Useful Life Prediction Based on Deep Learning
党慧莹 1李海林 2吴北苹 3余佳宇 4庄银传5
作者信息
- 1. 空军工程大学信息与导航学院,西安,710077||31401部队,吉林通化,134000
- 2. 空军工程大学信息与导航学院,西安,710077
- 3. 空军工程大学信息与导航学院,西安,710077||空军通信士官学校,辽宁 大连,116000
- 4. 空军工程大学信息与导航学院,西安,710077||95486部队,成都,610041
- 5. 93127部队,北京,100834
- 折叠
摘要
Abstract
As a crucial component of navigation equipment,bearings affect the positioning accuracy and safeguarding capability of the navigation equipment.In predicting the remaining useful life(RUL)of e-quipment,traditional machine learning algorithms are limited to dealing with the problems of complex nonlinear characteristic signals.For the above-mentioned reasons,a new prediction framework for RUL of bearing based on attention mechanism(AM)and bidirectional long short-term memory(Bi-LSTM)is pro-posed(Bi-LSTM-A).First,a one-dimensional convolution neural network(CNN)is added to the front of the structure to extract local features from the original signal sequence,and then,the signals are analyzed and predicted by combining bidirectional long short-term memory network with attention mechanism.fi-nally,the predicted results are output through the fully connected layers at the end of the network.in comparison with the similar algorithms,the results show that the proposed method can accurately predict the equipment remaining useful life,and is good in predicting efficiency and accuracy.关键词
轴承/深度学习/长短期记忆网络/注意力机制/剩余使用寿命Key words
bearing/deep learning/long short-term memory/attention mechanism/remaining useful life分类
机械工程引用本文复制引用
党慧莹,李海林,吴北苹,余佳宇,庄银传..基于深度学习的导航装备轴承剩余使用寿命预测[J].空军工程大学学报,2025,26(2):81-88,8.
