期刊
MEASUREMENT
卷 205, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.measurement.2022.112170
关键词
Rotating machinery; Multi -domain mixed features; Spatio-temporal fusion; Health indicator; STOA-XGBoost; Status assessment
资金
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
- [51834006]
- [51875451]
- [2022MD713793]
This paper proposes a multi-domain features-based spatio-temporal fusion method called SALICAE for constructing a novel health indicator for rotating machinery. The method integrates the advantages of self-attention, long short-term memory, and an improved convolutional autoencoder. The effectiveness of the proposed method is verified and its accuracy is approximately 85.3% under different working conditions.
Rotating machinery has been applied in various industries, and weak fault feature monitoring is of great sig-nificance to constructing health indicators (HIs) and assessing their status. However, there are some challenges in HI construction and status assessment, including difficult expression of weak features, incomplete information domain, and quantification of early degradation points. To construct a novel HI of rotating machinery, this paper proposes a multi-domain features-based spatio-temporal fusion method, which integrates the spatio-temporal advantages of self-attention (SA), long short-term memory (LSTM), and an improved convolutional autoen-coder (ICAE), called SALICAE. On this basis, the sooty tern optimization algorithm (STOA) is used to auto-matically optimize the extreme gradient boosting model (XGBoost) for assessing the status of rotating machinery accurately. The effectiveness and adaptability of the proposed method are verified by the standard bearing database from Xi'an Jiaotong University, and the average accuracy under different working conditions is approximately 85.3%. Moreover, the accuracy of the proposed method is also tested by the reducer platform organized by our lab, which is 99.3%.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据