###
工程科学与技术:2022,54(6):67-74
←前一篇   |   后一篇→
本文二维码信息
码上扫一扫!
基于注意力的工业物联网设备剩余寿命预测方法
(1.东北大学 计算机科学与工程学院,辽宁 沈阳 110169;2.秦皇岛职业技术学院 信息工程系,河北 秦皇岛 066100;3.广东外语外贸大学 语言工程与计算实验室,广东 广州 510006)
Attention-based Remaining Useful Lifetime Prediction Method for Industrial Internet of Things
(1.School of Computer Sci. and Eng., Northeastern Univ., Shenyang 110169, China;2.Dept. of Info. Eng., Qinhuangdao Vocational and Technical College, Qinhuangdao 066100, China;3.Lab. of Language Eng. and Computing, Guangdong Univ. of Foreign Studies, Guangzhou 510006, China)
摘要
图/表
参考文献
相似文献
附件
本文已被:浏览 914次   下载 441
投稿时间:2021-08-28    修订日期:2022-03-29
中文摘要: 设备剩余使用寿命预测作为工业物联网实现工业智能的重要功能之一,可基于设备的健康监测数据对其未来退化状态进行预测,以获得设备丧失运行能力前的剩余使用时间,从而制定相应的预测性维修策略,提升工业物联网设备的可靠性、可用性和安全性。提出一种基于注意力机制的设备剩余使用寿命预测方法(attention-based remaining useful lifetime prediction,ARULP)。首先,在模型训练阶段设计了一种局部注意力计算算法,构建数据驱动的局部注意力计算模型,采用训练数据计算局部注意力度量,从而获取预测模型关注的大量数据中关键信息的能力;然后,设计了一种基于局部注意力的相关向量机,通过在其隐变量学习过程中引入局部注意力机制,动态更新注意力权重,从而自适应地调整设备的状态预测模型,提升设备的剩余使用寿命预测精度;最后,在模型预测阶段,利用所构建的预测模型进行设备工作状态预测,并计算设备的剩余使用寿命。基于西安交通大学滚动轴承加速寿命试验数据集,与RVM、AR、ARIMA和LSTM 4个基准方法进行性能比较。结果表明,ARULP方法在不同工况下针对轴承外圈故障、内圈故障和保持架故障进行预测时均与轴承实际退化数据最为接近,能够较好地反映故障轴承的退化状态,最终实现对工业物联网设备剩余使用寿命进行高精度的预测。
Abstract:As one of the important functions to realize industrial intelligence in Industrial Internet of Things (IIoT), remaining useful lifetime (RUL) prediction can predict the future degradation states of industrial equipment based on monitoring data and then reckon its remaining service time. Furthermore, the corresponding predictive maintenance strategies can be formulated in advance, and the reliability, availability, and safety of the equipment can be enhanced. In this paper, an attention-based remaining useful lifetime prediction method (ARULP) for IIoT was proposed. Firstly, in the model training stage, a local attention computation algorithm was designed by constructing a data-driven local attention computation model and utilizing the training data to compute the local attention measurements. Thus, the prediction model can pay more attention to the key information within a large amount of data. Then, a relevance vector machine based on local attention was designed by introducing the local attention mechanism into the learning process of implicit variables in the prediction model. The attention weights were updated to adjust the state prediction model adaptively and improve the prediction accuracy of the RUL for IIoT device. Finally, the ARULP method was applied in the model prediction stage to predict the degradation status and reckon the RUL for IIoT device. Extensive experiments based on the dataset of life test for accelerated rolling element bearings released by Xi’an Jiaotong University were carried out to predict the RUL for bearings with outer ring failure, inner ring failure, and holder failure under different working conditions. The experiment results showed that the prediction data of the ARULP method are the closest to the actual bearing degradation data and more accurate RUL prediction results can be obtained compared with RVM, AR, ARIMA, and LSTM benchmarks.
文章编号:202100863     中图分类号:TP181    文献标志码:
基金项目:河北省自然科学基金项目(F2020501034);河北省高等学校科学研究项目(ZD2021403;ZD2019306);中央高校基本科研业务费(N2123023);秦皇岛市科学技术研究与发展计划项目(201902A017)
作者简介:第一作者:李国瑞(1980-),男,副教授,博士.研究方向:物联网;机器学习;优化理论等.E-mail:lgr@neuq.edu.cn;通信作者:王颖,讲师,E-mail:wyqhd@hotmail.com
引用文本:
李国瑞,武雅君,王颖,彭三城,王聪.基于注意力的工业物联网设备剩余寿命预测方法[J].工程科学与技术,2022,54(6):67-74.
LI Guorui,WU Yajun,WANG Ying,PENG Sancheng,WANG Cong.Attention-based Remaining Useful Lifetime Prediction Method for Industrial Internet of Things[J].Advanced Engineering Sciences,2022,54(6):67-74.