轴承是旋转机械设备中的重要部件,由于工况、材质、加工方式等原因,轴承寿命时长相差许多。传统的并行或串行神经网络预测方式,对数据集有一定要求。因此,需要一种能够适用于不同数据长短的轴承剩余使用寿命预测网络。为此提出了一种能够预测不同寿命时长的Transformer-LSTM串并行神经网络预测模型。通过将Transformer解码层进行重构,并与长短期记忆时序神经网络(long short-term memory, LSTM)网络结构融合,实现轴承寿命数据的串并行预测处理。实验结果表明Transformer-LSTM神经网络能够精准预测长、中、短不同寿命时长的轴承失效时间,具有较强的模型泛化能力,提升轴承寿命预测精度与模型的泛化能力。
Abstract
Bearing is an important component in rotating machinery. Due to the working conditions, materials, and processing methods, the lifetimes of bearing have large fluctuations. Traditional parallel or serial neural network prediction methods have seriously dependent on the data sets. Therefore, there is a need for bearings RUL prediction network that can be applied to different data lengths. To overcome this challenge, a Transformer-LSTM serial-parallel neural network prediction model is proposed, which can predict the RUL for bearings with different lifetimes. By reconfiguring the Transformer decoding layer and fusing it with the LSTM network structure, the serial-parallel prediction processing of bearing life data is achieved. The experimental results show that the Transformer-LSTM neural network can accurately predict the bearing failure time for different lifetimes, including: long, medium, and short. Moreover, the model has a stronger generalization ability which also indicates that the proposed method can improve the prediction accuracy of bearing life.
关键词
滚动轴承 /
轴承寿命预测 /
Transformer神经网络 /
LSTM神经网络 /
非线性时间序列预测
{{custom_keyword}} /
Key words
rolling bearings /
bearing remaining useful life prediction /
Transformer neural network /
LSTM neural network /
Non-linear time series forecasting
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 王立炜,栾孝驰,沙云东,袁琳.基于快速ICA的复杂路径下 滚棒轴承外圈划伤故障特征提取[J].机械设计与制造, 2021(12):77-81.
Wang Liwei, Luan Xiaochi, Sha Yundong, Yuan, Lin. Fault Extraction of Roller Bearing Outer Ring Scratch in Complex Path Based on Fast ICA[J]. Journal of machinery design and manufacture, 2021(12):77-81.
[2] Arinez J F, Chang Q, Gao R X, et al. Artificial intelligence in advanced manufacturing: Current status and future outlook[J]. Journal of Manufacturing Science and Engineering, 2020, 142(11).
[3] 刘恒畅, 姚德臣, 杨建伟, 张骄.基于多分支深度可分离卷积神经网络的滚动轴承故障诊断研究[J].振动与冲击, 2021,40(10):95-102.
Liu Hengchang, Yao Dechen, Yang Jianwei, Zhang Jiao. Fault Diagnosis of Rolling Bearing Based on Multi Branch Depth Separable Convolutional Neural Network[J]. Journal of Vibration and Shock, 2021,40(10):95-102.
[4] Liu K, Shang Y, Ouyang Q, et al. A data-driven approach with uncertainty quantification for predicting future capacities and remaining useful life of lithium-ion battery[J]. IEEE Transactions on Industrial Electronics, 2020, 68(4): 3170-3180.
[5] Lecun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521(7553):436.
[6] Chen Y, Peng G, Zhu Z, et al. A novel deep learning method based on attention mechanism for bearing remaining useful life prediction[J]. Applied Soft Computing, 2020, 86: 105919.
[7] Lei Ren, Yaqiang Sun, Jin Cui, et al. Bearing remaining useful life prediction based on deep autoencoder and deep neural networks[J]. Journal of Manufacturing Systems, 2018, 48:71-77.
[8] Ahmed Zakariae Hinchi, Mohamed Tkiouat. Rolling element bearing remaining useful life estimation based on a convolutional long-short-term memory network[J]. Procedia Comput Sci, 2018,127:123-132.
[9] Ahmed Elsheikh, Soumaya Yacout, Mohamed-Salah Ouali. Bidirectional handshaking lstm for remaining useful life prediction[J]. Neurocomputing, 2018,323:148- 156.
[10] 姚德臣, 李博阳, 刘恒畅, 姚娟, 皮雁南. 基于注意力GRU算法的滚动轴承剩余寿命预测[J]. 振动与冲击, 2021,40(17):116-123.
YAO Dechen, LI Boyang, LIU Hengchang, YAO Juan, PI Yannan. Residual life prediction of rolling bearings based on attention GRU algorithm[J]. Journal of Vibration and Shock, 2021, 40(17):116-123.
[11] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//31st International Conference on Neural Information Processing Systems. Long Beach: ACM, 2017.
[12] Yu Mo, Qianhui Wu, Xiu Li, et al.Remaining useful life estimation via transformer encoder enhanced by a gated convolutional unit[J]. Journal of Intelligent Manufacturing, 2021(prepublish):1-10.
[13] Hao W, Li Z, Qin G, et al. A Novel Prediction Method Based on Bi-Channel Hierarchical Vision Transformer for Rolling Bearings’ Remaining Useful Life[J]. Processes, 2023, 11(4): 1153.
[14] Ding Y, Jia M. Convolutional Transformer: An Enhanced Attention Mechanism Architecture for Remaining Useful Life Estimation of Bearings[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-10.
[15] LI shiyang, JIN xiaoyong, XUAN yao, et al. Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting. [J]. CoRR,2019.
[16] Huixin Tian, Daixu Ren, Kun Li, et al. An adaptive update model based on improved long short term memory for online prediction of vibration signal[J]. Journal of Intelligent Manufacturing, 2020, 32(prepublish):1-13.
[17] YAO Dechen, LI Boyang, LIU Hengchang, et al. Remaining useful life prediction of roller bearings based on improved 1d-cnn and simple recurrent unit[J]. Measurement, 2021, 175.
[18] QIU H, LEE J, LIN J, et al. Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics[J]. Journal of Sound and Vibration, 2006, 289(4/5):1066-1090.
[19] WANG biao, LEI Yaguo, LI Naipeng, et al. A hybrid prognostics approach for estimating remaining useful life of rolling element bearings[J]. IEEE Transactions on Reliability, 2020, 69(1):401-412.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}