文献类型：期刊文献

英文题名：Remaining Useful Life Prediction Method of Offshore Equipment Bearings Based on Convolutional Neural Network-Bidirectional Gated Recurrent Unit-Squeeze and Excitation

作者：Jin, Yan[1,2];Xin, Wang[1];Dapeng, Zhang[1];Zhiqiang, Liao[1];Ximing, Wu[3]

机构：[1]Guangdong Ocean Univ, Zhanjiang 524088, Guangdong, Peoples R China;[2]Guangdong Ocean Univ, Shenzhen Res Inst, Shenzhen 518120, Guangdong, Peoples R China;[3]CNOOC Energy Dev Co Ltd, Zhanjiang Oil Prod Serv, Wenchang Branch, Zhanjiang 524057, Guangdong, Peoples R China

年份：2022

卷号：17

期号：10

起止页码：1343

外文期刊名：JOURNAL OF NANOELECTRONICS AND OPTOELECTRONICS

收录：SCI-EXPANDED(收录号：WOS:000936049200001)、、WOS

基金：The authors gratefully acknowledge the support provided for this research by National Natural Science Foundation of China (52201355) and Natural Science Foundation of Guangdong Province (2022A1515011562) and is also financially supported by Guangdong Provincial Special Fund for promoting high quality economic development (GDNRC [2021] 56, Yuerong Office Letter [2020] 161) .

语种：英文

外文关键词：Rolling Bearing; Remaining Useful Life (RUL) Prediction; Attention Mechanism; Convolutional Neural Network; Bidirectional Gated Recurrent Unit (BIGRU)

外文摘要：The remaining useful life forecast (RUL) of rolling bearings, a crucial part of offshore equipment, is one of the most troublesome equipment because it may avoid equipment failure and lessen equipment failure loss. This paper proposes a method to build CNN-BIGRU bearing health indicators based on the SE attention mechanism, and combines primary linear regression to predict the RUL of bearings in order to address the issues of low accuracy and poor generalization performance in the current bearing RUL prediction. The proposed method combines the spatial feature extraction capability of convolutional neural networks with the temporal feature extraction capability of bidirectional gated recurrent units, allowing it to effectively use feature information from the spatial and temporal dimensions of vibration signals to improve prediction accuracy and stability. The suggested technique is validated in this research using experimental data from the 2012 IEEE IP: 2038 109 10 On Thu 16 Feb 2023 14:3824 PHM Challenge for the whole life cycleCopyright:bearing. AmericanThe expermentalScientific Publshefindings sreveal that the approach can more accurately estimate the RUL of the bearing than thstandard model, proving the usefulness and viability of Delivere d by Ingenta the suggested method.