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

YANG DaLian; LEI JiaLe; JIANG LingLi

doi:10.16579/j.issn.1001.9669.2022.06.03

您当前的位置：

首页 >

文章列表页 >

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

更新时间：2023-06-09

- FAULT DIAGNOSIS OF SPIRAL BEVEL GEAR BASED ON LOCAL BISPECTRUM AND CONVOLUTIONAL NEURAL NETWORK (MT)
- Journal of Mechanical Strength Issue 6, Pages: 1286-1292(2022)
- 作者机构：
  
  1. 湖南科技大学机械设备健康维护湖南省重点实验室
  2. 佛山科学技术学院机电工程与自动化学院
- 作者简介：
- 基金信息：
- DOI：10.16579/j.issn.1001.9669.2022.06.03
  CLC：
扫描看全文
YANG DaLian, LEI JiaLe, JIANG LingLi. FAULT DIAGNOSIS OF SPIRAL BEVEL GEAR BASED ON LOCAL BISPECTRUM AND CONVOLUTIONAL NEURAL NETWORK (MT). [J]. Journal of Mechanical Strength (6):1286-1292(2022)
DOI：

YANG DaLian, LEI JiaLe, JIANG LingLi. FAULT DIAGNOSIS OF SPIRAL BEVEL GEAR BASED ON LOCAL BISPECTRUM AND CONVOLUTIONAL NEURAL NETWORK (MT). [J]. Journal of Mechanical Strength (6):1286-1292(2022) DOI： 10.16579/j.issn.1001.9669.2022.06.03.

摘要

针对传统故障诊断方法对弧齿锥齿轮故障诊断效率低的问题，提出一种基于局部双谱和卷积神经网络(Convolution Neural Network, CNN)的故障诊断方法。该方法使用包含全域信息的弧齿锥齿轮振动信号局部双谱图作为CNN的输入构造诊断模型，实现弧齿锥齿轮故障诊断，不仅降低了故障信息的冗余度，而且提高了CNN训练速度。通过与全双谱+CNN、原始振动信号+CNN、局部双谱+SVM(Support Vector Machine)、局部双谱+BP(Back Propagation)神经网络的诊断结果对比，所提出方法的平均诊断准确率为99.56%,模型训练时间为15 s,综合性能最优。

Abstract

Aiming at the problem that the traditional fault diagnosis method has a low efficiency for spiral bevel gear fault diagnosis, a fault diagnosis method based on local bispectrum and convolution neural network（CNN） is proposed. By using local bispectrum of spiral bevel gears vibration signal containing global information as the input of the CNN, a diagnosis model is constructed to realize fault diagnosis of spiral bevel gears, which not only reduces the redundancy of fault information, but also improves the speed of CNN training. Comparing with traditional diagnosis results that use bispectrum and CNN, vibration signal and CNN, local bispectrum and SVM（Support Vector Machine）, local bispectrum and BP（Back Propagation） neural network, the proposed method has an optimal comprehensive performance which has an accuracy of 99.56% and model training time of 15 seconds.

关键词

卷积神经网络局部双谱弧齿锥齿轮故障诊断

Keywords

CNNLocal bispectrumSpiral bevel gearFault diagnosis

references

Views

172

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

ANALYSIS OF DYNAMIC RESPONSE CHARACTERISTICS OF AERONAUTICAL SPIRAL BEVEL GEARS AND OPTINIZATION OF VIBRATION ABSORBING STRUCTURE OF SPOKE PLATE HOLE (MT)

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

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

Related Author

No data

Related Institution

School of Mechatronics Engineering,Henan University of Science ＆ Technology

Hunan Aviation Powerplant Research Institute,Aero Engine Corporation of China

Energy and Power Engineering Institute,University of Shanghai for Science and Technology

Shanghai Key Laboratory of Multiphase Flow and Heat Transfer in Power Engineering

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

⁰