Remaining Useful Life Prediction Based on ConvGRU-Attention Method

被引：0

作者：

Zhao Z. ^{[1
,2
]}

Li Q. ^{[1
]}

Li C. ^{[1
]}

机构：

[1] School of Information Science and Technology, Shijiazhuang Tiedao University, Shijiazhuang

[2] State Key Laboratory of Mechanical Behavior in Traffic Engineering Structure and System Safety, Shijiazhuang Tiedao University, Shijiazhuang

来源：

Zhendong Ceshi Yu Zhenduan/Journal of Vibration, Measurement and Diagnosis | 2022年 / 42卷 / 03期

关键词：

Attention; Convolutional gated recurrent unit(ConvGRU); Deep learning; Mechanical equipment; Remaining useful life prediction;

D O I：

10.16450/j.cnki.issn.1004-6801.2022.03.023

中图分类号：

学科分类号：

摘要：

In order to directly use neural network to automatically extract feature information from the collected full-life vibration signals and avoid the dependence on manually extracted features, a remaining useful life prediction method based on convolution gated recurrent unit (ConvGRU) attention is proposed. Firstly, the collected equipment vibration signal is input into ConvGRU-attention model after preprocessing. ConvGRU extracts the spatial local features of equipment state through convolutional neural networks(CNN) and gate recurrent unit (GRU) extracts the timing feature information, so that the equipment state features can be extracted more effectively. Secondly, the attention mechanism is used to assign different weights to the feature information. Then, the visualization experiment of the feature output of the intermediate network layer is carried out, which verifies the effectiveness of the feature extraction of this research method. Finally, experiments are carried out on two mechanical equipment datasets PHM2012 bearing dataset and NASA engine dataset, and compared with existing methods. The experimental results show that the prediction accuracy of the remaining useful life prediction method based on ConvGRU-attention is better and has better generalization.

引用

页码：572 / 579

页数：7

共 27 条

[1] MOGHADDASS R, ZUO M J., An integrated framework for online diagnostic and prognostic health monitoring using a multistate deterioration process, Reliability Engineering and System Safety, 124, pp. 92-104, (2014)
[2] LIU G., A study on remaining useful life prediction for prognostic applications, (2011)
[3] LIAO L, KOTTIG F., Review of hybrid prognostics approaches for remaining useful life prediction of engineered systems, and an application to battery life prediction, IEEE Transactions on Reliability, 63, 1, pp. 191-207, (2014)
[4] CHEN Jie, DENG Erping, ZHAO Zixuan, Et al., Failure mechanism analysis of SiCMOSFET under different aging test methods, Transactions of China Electrotechnical Society, 35, 24, pp. 5105-5114, (2020)
[5] PEI Hong, HU Changhua, SI Xiaosheng, Et al., Review of machine learning based remaining useful life prediction methods for equipment, Journal of Mechanical Engineering, 10, 5, pp. 1-13, (2019)
[6] HU Changhua, HU Jintao, ZHANG Wei, Et al., Reliability assessment of performance degradation using support vector machines, Systems Engineering and Electronics, 31, 5, pp. 1246-1249, (2009)
[7] (2018)
[8] WANG Xinchun, ZHAO Jinjin, Research on IGBT life based on wavelet neural network, Electric Engineering, 10, pp. 114-116, (2020)
[9] ZHANG W, PENG G L, LI C H, Et al., A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals, Sensors, 17, 2, pp. 425-425, (2017)
[10] REN L, SUN Y, WANG H, Et al., Prediction of bearing remaining useful life with deep convolution neural network, IEEE Access, 6, pp. 13041-13049, (2018)

← 1 2 3 →