Intelligent Fault Diagnosis of Bearing Based on Multi-Source Data Fusion and Improved Attention Mechanism

被引：0
|
作者：
Xing Z.-K. [1 ]
Liu Y.-B. [1 ]
Wang Q. [1 ]
Li J. [1 ]
机构：
[1] College of Power Engineering, Naval University of Engineering, Wuhan
来源：
Tuijin Jishu/Journal of Propulsion Technology | 2023年 / 44卷 / 05期
关键词：
Attention mechanism; Convolutional neural network; Fault diagnosis; Feature ex⁃ traction; Multi-source data fusion; Rolling bearing;
D O I：
10.13675/j.cnki.tjjs.2204017
中图分类号：
学科分类号：
摘要：
A single sensor signal cannot fully express the operating characteristics of mechanical equipment and is easily affected by its quality and performance. Therefore，an intelligent diagnosis method combining multi-source data fusion and an improved attention mechanism is proposed. Firstly，the sensor vibration signals at dif⁃ ferent positions are collected as the input vector of the model，each sensor signal is taken as a channel，and the multi-channel signals are input to the feature input layer of the model at the same time. Secondly，the improved attention mechanism is introduced to establish the dynamic weight parameters of each channel and space. With the model training，fault features are continuously enhanced，and useless features are constantly weakened. Fi⁃ nally，through the convolution and pooling of the deep convolution neural network model，the multi-sensor sig⁃ nals are further fused，the fault features are extracted，and the diagnosis results are output. In the case of rolling bearing fault diagnosis，the improved method had a diagnostic accuracy of 100%，compared with accuracy of 97.42% for the best single sensor. Compared with other methods，this method can adaptively fuse the multi-sen⁃ sor data to meet the requirements of the diagnosis task，has good adaptability and robustness，and provides a fea⁃ sible method for the fault diagnosis of rolling bearing. © 2023 Journal of Propulsion Technology. All rights reserved.
引用
收藏
相关论文
共 18 条
  • [1] 35, 17, pp. 121-126, (2016)
  • [2] 3, pp. 61-65
  • [3] (2015)
  • [4] 29, 4, pp. 469-482, (2015)
  • [5] 41, 2, pp. 362-369, (2021)
  • [6] Huang R，, Liao Y，, Zhang S，, Et al., Deep Decoupling Con⁃ volutional Neural Network for Intelligent Compound Fault Diagnosis［J］, IEEE Access, 7, pp. 1848-1858, (2019)
  • [7] Lu C, Wang Z Y，, Zhou B., Intelligent Fault Diag-Nosis of Rolling Bearing Using Hierarchical Convolutional Net⁃ work Based Health State Classification［J］, Advanced Engineering Informatics, 32, pp. 139-151, (2017)
  • [8] 34, 11, pp. 2423-2431, (2019)
  • [9] Wang L, Et al., Motor Fault Diagnosis Based on Short-Time Fourier Transform and Convolution⁃ al Neural Network［J］, Chinese Journal of Mechanical Engineering, 30, 6, pp. 1357-1368, (2017)
  • [10] Jiang P，, Ding C，, Et al., Intelligent Fault Diagno⁃ sis of Rotating Machinery Based on One-Dimensional Convolutional Neural Network［J］, Computers in Industry, 108, pp. 53-61, (2019)
12