RESEARCH ON BEARING FAULT DIAGNOSIS BASED ON CEEMDAN FUZZY ENTROPY AND CONVOLUTIONAL NEURAL NETWORK (MT)

XIAO JunQing; JIN JiangTao; LI Chun; XU ZiFei; SUN Kang

doi:10.16579/j.issn.1001.9669.2023.01.004

您当前的位置：

首页 >

文章列表页 >

RESEARCH ON BEARING FAULT DIAGNOSIS BASED ON CEEMDAN FUZZY ENTROPY AND CONVOLUTIONAL NEURAL NETWORK (MT)

更新时间：2023-07-28

- RESEARCH ON BEARING FAULT DIAGNOSIS BASED ON CEEMDAN FUZZY ENTROPY AND CONVOLUTIONAL NEURAL NETWORK (MT)
- Journal of Mechanical Strength Issue 1, Pages: 26-33(2023)
- 作者机构：
  
  1. 上海理工大学能源与动力工程学院
  2. 上海市动力工程多相流动与传热重点实验室
- 作者简介：
- 基金信息：
- DOI：10.16579/j.issn.1001.9669.2023.01.004
  CLC：
扫描看全文
XIAO JunQing, JIN JiangTao, LI Chun, et al. RESEARCH ON BEARING FAULT DIAGNOSIS BASED ON CEEMDAN FUZZY ENTROPY AND CONVOLUTIONAL NEURAL NETWORK (MT). [J]. Journal of Mechanical Strength (1):26-33(2023)
DOI：

XIAO JunQing, JIN JiangTao, LI Chun, et al. RESEARCH ON BEARING FAULT DIAGNOSIS BASED ON CEEMDAN FUZZY ENTROPY AND CONVOLUTIONAL NEURAL NETWORK (MT). [J]. Journal of Mechanical Strength (1):26-33(2023) DOI： 10.16579/j.issn.1001.9669.2023.01.004.

摘要

为较好地提取强噪声覆盖下滚动轴承振动信号的故障信息，提高故障诊断识别与分类精度，基于模糊熵(Fuzzy Entropy, FE)理论，提出了一种自适应白噪声平均总体经验模态分解(Complete Ensemble Empirical Mode Decomposition with Adaptive Noise, CEEMDAN)模糊熵与卷积神经网络(Convolutional Neural Network, CNN)结合的故障诊断方法，充分利用了模糊熵数据独立性、相对一致性以及模糊性与随机性优势。通过循环抽样求取原始信号模糊熵，利用CEEMDAN方法分解，再由皮尔森相关系数筛选最佳分量组，最终将其输入CNN进行故障诊断，并采用t-SNE流行学习算法进行聚类可视化。其结果证实了不同工况下，相比经验模态分解模糊熵、集合经验模态分解模糊熵方法，所提方法具有更强的鲁棒性与泛化性，且t-SNE可视化使结果更直观。

Abstract

In order to extract the fault information of rolling bearing vibration signals under strong noise coverage and improve the accuracy of fault diagnosis and classification, based on the theory of fuzzy entropy（FE）, a new method of complete ensemble empirical mode decomposition with adaptive noise（CEEMDAN） and convolutional neural network（CNN） is proposed, which make full use of the independence, relative consistency, and the advantages of fuzzy entropy and randomness. The fuzzy entropy of the original signal was obtained by cyclic sampling, decomposed by CEEMDAN method, and the optimal component group was screened by Pearson correlation coefficient. Finally, the optimal component group was input to CNN for fault diagnosis, and the t-SNE popular learning algorithm was used for clustering visualization. The results show that compared with EMD-Fuzzy Entropy and EEMD-Fuzzy Entropy under different working conditions, the proposed method has stronger robustness and generalization, and t-SNE visualization makes the results more intuitive.

关键词

卷积神经网络轴承自适应白噪声平均总体经验模态分解模糊熵故障诊断

Keywords

Convolutional neural networkBearingCEEMDANFuzzy entropyFault diagnosis

references

Views

529

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

ROLLING BEARING FAULT DIAGNOSIS BASED ON UNIFORM DISTANCE LOCAL LINEAR EMBEDDING (MT)

FAULT DIAGNOSIS OF SPIRAL BEVEL GEAR BASED ON LOCAL BISPECTRUM AND CONVOLUTIONAL NEURAL NETWORK (MT)

ENGINE FAULT DIAGNOSIS BASED ON DEEP BELIEF NETWORK IMPROVED BY ADAPTIVE CROW SEARCH ALGORITHM (MT)

RESEARCH ON FAULT DIAGNOSIS METHOD OF ROTATING MACHINERY BASED ON REFINED IMPROVED MULTISCALE FAST SAMPLE ENTROPY (MT)

FAULT DIAGNOSIS METHOD OF DIESEL ENGINE BASED ON PCA-EDT-CNN (MT)

Related Author

No data

Related Institution

School of Mechanical Engineering,Jiangxi Vocational College of Mechanical ＆ Electrical Technology

Department of Intelligent Engineering,Jiangxi University of Technology

Hunan Provincial Key Laboratory of Health Maintenance for Mechanical Equipment,Hunan University of Science and Technology

School of Mechatronic Engineering and Automation,Foshan University

Department of Computer, Sichuan Top IT Vocational Institute

⁰