[1]刘康宁,徐遵义*,李 晨,等.基于 NLMS 和 Autoformer 的滚动轴承 RUL 预测[J].计算机技术与发展,2024,34(03):177-184.[doi:10. 3969 / j. issn. 1673-629X. 2024. 03. 026]
　LIU Kang-ning,XU Zun-yi*,LI Chen,et al.RUL Prediction of Rolling Bearing Based on NLMS and Autoformer[J].,2024,34(03):177-184.[doi:10. 3969 / j. issn. 1673-629X. 2024. 03. 026]

点击复制

基于 NLMS 和 Autoformer 的滚动轴承 RUL 预测()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:

34

期数:

2024年03期

页码:

177-184

栏目:

人工智能

出版日期:

2024-03-10

文章信息/Info

Title:

RUL Prediction of Rolling Bearing Based on NLMS and Autoformer

文章编号:

1673-629X(2024)03-0177-08

作者:

刘康宁; 徐遵义* ; 李 晨; 闫春相

山东建筑大学 计算机科学与技术学院,山东 济南 250101

Author(s):

LIU Kang-ning; XU Zun-yi* ; LI Chen; YAN Chun-xiang

School of Computer Science and Technology,Shandong Jianzhu University,Jinan 250101,China

关键词:

滚动轴承; 剩余使用寿命预测; Autoformer 模型; NLMS 自适应滤波器; 数据预处理

Keywords:

rooling bearing; remaining useful life; Autoformer model; NLMS adaptive filter; data preprocessing

分类号:

TP183;TH133. 33

DOI:

10. 3969 / j. issn. 1673-629X. 2024. 03. 026

摘要:

准确预测滚动轴承剩余使用寿命( Remaining Useful Life,RUL) 对维护建筑机械设备稳定运行、保障生产安全具有重要的现实需求和应用价值。 为提升滚动轴承 RUL 预测准确率,

提出一种基于归一化最小均方( Normalized Least MeanSquare,NLMS)自适应滤波器和 Autoformer 长序列预测模型的滚动轴承 RUL 预测新方法。 使用 NLMS 自适应滤波器对滚

动轴承原始振动信号进行降噪,从降噪振动信号中分段提取初始时域特征,采用 Spearman 相关系数进行特征筛选,经归一化后形成多维特征集;利用 Autoformer 模型中序列分解模块

与自相关机制建立多维特征集与滚动轴承 RUL 之间的分段非线性映射,实现滚动轴承 RUL 预测;在 PHM 2012 数据集与 XJTU-SY 数据集上进行对比实验,结果表明该方法与已有方法相比可取得最低预测误差,均方根误差( Root Mean Squared Error,RMSE)与平均绝对误差( Mean Absolute Error,MAE) 分别提升 24. 4% 与 47. 2% ,证明了该方法在滚动轴承 RUL 预测的有效性。

Abstract:

For maintaining the stable operation of construction machinery equipment and ensuring production safety,accurately predictingRemaining Useful Life ( RUL) of rolling bearing?

has significant practical needs and application value. Based on Normalized Least MeanSquare ( NLMS) adaptive filter and long-term series forecasting model Autoformer,a new method was proposed in order to improve theRUL prediction accuracy of rolling bearing. The NLMS adaptive filter was used to denoise the original vibration signal of rolling　bearing. The Spearman correlation coefficient was used for feature selection from the denoised signal,and the multidimensional feature setwas created. In order to forecast the rolling bearing RUL, the series decomposition block and auto - correlation mechanism in theAutoformer model were used to establish the piecewise mapping relationship between the multi-dimensional feature sets and the rollingbearing RUL. Experimental results on the PHM 2012 dataset and XJTU-SY dataset showed that the proposed method could achieve thelowest prediction error compared with the existing methods, and the Root Mean Squared Error ( RMSE ) and Mean Absolute Error( MAE) performance were improved by 24. 4% and 47. 2% respectively,which proved the effectiveness of the proposed method in thefield of rolling bearing RUL prediction.

常用功能