Computer Engineering and Applications ›› 2024, Vol. 60 ›› Issue (13): 338-344.DOI: 10.3778/j.issn.1002-8331.2304-0143

• Engineering and Applications • Previous Articles     Next Articles

Gearbox Fault Diagnosis Based on Improved Time Series Gray Scale Image and Deep Learning

XIE Fengyun, LI Gang, WANG Linglan, LIU Hui, WANG Gan   

  1. School of Mechatronics & Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China
  • Online:2024-07-01 Published:2024-07-01

改进时序灰度图和深度学习的齿轮箱故障诊断

谢锋云,李刚,王玲岚,刘慧,汪淦   

  1. 华东交通大学 机电与车辆工程学院,南昌 330013

Abstract: A gear box fault diagnosis method based on improved time series gray image and deep learning is put forward in order to solve the problems such as complex actual working environment of gear box, inadequate performance of extracting features by traditional methods and gray image extraction features. After the vibration signal is decomposed into several intrinsic mode components (IMFs) by EEMD, the IMFs are divided into high-frequency and low-frequency components by cumulative mean criterion, in which the high-frequency components are denoised by wavelet threshold. The high frequency IMFs and low frequency IMFs after noise reduction are reconstructed, and the reconstructed signal is coded by gray image method. Two-dimensional improved time series gray image is sent to convolution neural network for training, so as to exert the advantages of convolution network in feature extraction of pictures and display the results by confusion matrix. Finally, the model results and different gray scale images are compared with traditional diagnosis methods. The results show that compared with common gray image and global denoising gray image, the method proposed in this paper improves the accuracy of gear box fault diagnosis by 4 and 1.8 percentage points respectively, and the convergence speed is significantly faster. Compared with BP neural network and ELM diagnosis method, the method proposed in this paper significantly improves the accuracy of gear box fault diagnosis.

Key words: ensemble empirical mode decomposition, fault diagnosis, improved time series gray scale image, deep learning

摘要: 针对齿轮箱实际工作环境复杂、传统方法提取特征以及灰度图提取特征性能不足,提出了一种基于改进时序灰度图和深度学习的齿轮箱故障诊断方法。用EEMD(ensemble empirical mode decomposition)将振动信号分解为若干个本征模态分量(IMF)后,通过累计均值准则将IMFs划分为高频和低频分量,其中高频分量采用小波阈值降噪进行处理;重构降噪后的高频IMFs与低频IMFs,并利用灰度图方法对重构信号进行编码。将二维改进时序灰度图送入卷积神经网络进行训练,以发挥卷积网络对图片特征提取优势,并由混淆矩阵显示结果。最后将模型结果和不同灰度图与传统诊断方法进行对比。结果表明:相对于普通灰度图、全局去噪灰度图,所提方法对齿轮箱故障诊断准确率分别提高4、1.8个百分点,且收敛速度明显加快;相对于BP神经网络以及ELM诊断方法,所提方法对齿轮箱故障诊断准确率显著提高。

关键词: 集合经验模态分解, 故障诊断, 改进时序灰度图, 深度学习