电子测量与仪器学报

韩莹,陈熙.一种基于融合特征聚类和随机配置网络的轴承剩余寿命预测方法[J].电子测量与仪器学报,2024,38(4):128-139

一种基于融合特征聚类和随机配置网络的轴承剩余寿命预测方法

Bearing residual life prediction method based on fusion feature clustering andstochastic configuration networks

DOI：

英文关键词:bearing residual life prediction feature clustering first predicting time stochastic configuration networks offline prediction

基金项目:国家自然科学基金（62203197）项目资助

作者	单位
韩莹	辽宁工程技术大学电气与控制工程学院葫芦岛125105
陈熙	辽宁工程技术大学电气与控制工程学院葫芦岛125105

Author	Institution
Han Ying	Faculty of Electrical and Control Engineering, Liaoning Technical University, Huludao 125105, China
Chen Xi	Faculty of Electrical and Control Engineering, Liaoning Technical University, Huludao 125105, China

摘要点击次数: 260

全文下载次数: 12962

中文摘要:

针对轴承剩余寿命（remaining useful life, RUL）预测中故障始发时刻（first predicting time, FPT）基于人为主观选择以及预测滞后带来的维护风险的问题，提出了一种基于融合特征和随机配置网络（stochastic configuration networks, SCNs）的轴承剩余寿命预测方法。首先，采用互补集合经验模态分解（complementary ensemble empirical mode decomposition, CEEMD）对原始轴承水平振动信号进行分解，再提取其时域、频域信号，构建融合特征。最后，使用小波聚类划分健康状态，找到合适的FPT，并结合能反应轴承退化的特征构建健康数据集，通过SCNs网络离线建模进行预测，并根据拟合曲线的斜率以及RMSE指标对预测结果进行校正。通过实验分析，所提方法的综合得分高达0.83，误差百分比的平均绝对误差（mean absolute deviation, MAD）和标准偏差（standard deviation, SD）分别为5.26和3.38；与其他预测方法相比，本文所提方法有较高的预测精度。

英文摘要:

Aiming at the problems for which the first predicting time (FPT) of bearing remaining useful life (RUL) is based on subjective selection and maintenance risks caused by predictive lag. A stochastic configuration networks (SCNs)-based bearing residual life prediction method is proposed. Firstly, the complementary ensemble empirical mode decomposition (CEEMD) is used to decompose the original bearing horizontal vibration signal, then extract its time-domain and frequency-domain signals to construct fusion features. Secondly, the health state is divided by wavelet clustering to find the appropriate FPT, and the health data set is constructed by combining the characteristics of the energy response bearing degradation. The prediction is made by SCNs network offline modeling, and the prediction results are corrected according to the slope of the fitted curve and the RMSE index. Through experimental analysis, the comprehensive score of the proposed method is as high as 0.83, and the mean absolute deviation (MAD) and standard deviation (SD) of the error percentage are 5.26 and 3.38. Compared with other prediction methods, the proposed method has higher prediction accuracy.

查看全文查看/发表评论下载PDF阅读器