Introduction

International Standard Serial Number:

ISSN 1001-4551

Sponsor:

Zhejiang University;

Zhejiang Machinery and Electrical Group

Edited by:

Editorial of Journal of Mechanical & Electrical Engineering

Chief Editor:

ZHAO Qun

Vice Chief Editor:

TANG ren-zhong,

LUO Xiang-yang

Tel:

86-571-87041360,87239525

Fax:

86-571-87239571

Add:

No.9 Gaoguannong,Daxue Road,Hangzhou,China

P.C:

310009

E-mail:

meem_contribute@163.com

Health status diagnosis of tunnel fan based on convolutional neural network
Published:2023-09-20 author:PUMI Shi-hang, DING Hao, YANG Meng, et al. Browse: 1120 Check PDF documents
Health status diagnosis of tunnel fan based on convolutional neural network


PUMI Shi-hang1, DING Hao2,3, YANG Meng2,3, CHEN Jian-zhong2,3

(1.College of Civil Engineering, Chongqing Jiaotong University, Chongqing 400074, China; 

2.Chongqing Communications Research and Design Institute Co., Ltd., Chongqing 400067, China; 

3.National Engineering-Research Center for Road Tunnel, Chongqing 400067, China)


Abstract:  Regular condition assessment and fault diagnosis of the fans in the tunnel can ensure the safe operation of the tunnel. It is difficult to obtain the health status of tunnel fans by traditional manual methods, which leads to the failure to effectively ensure the quality of tunnel ventilation and brings hidden dangers to the safe operation of tunnels. 
Aiming at the problem, a health status diagnosis algorithm based on convolutional neural network(CNN) was proposed. Firstly, according to the idea of Kalman data fusion, a filtering method for fan bearing vibration signal was proposed. The continuous wavelet transform method was used to transform the filtered fan bearing vibration signal into time-frequency image. Then, the fault diagnosis model of tunnel fan bearing was constructed, the time-frequency image was taken as the input of the diagnosis model, and the evaluation index was selected to evaluate the diagnosis results of the model. Finally, the experimental verification was carried out by using the experimental data of the tunnel fan bearing. The research results show that the accuracy, recall, and F-measure of the diagnostic model are respectively 99.3 %, 99.2 %, and 99.2 %, and the diagnostic speed is only 0.04 s. The accuracy and diagnostic speed are significantly better than support vector machine (SVM), K-nearest neighbor (KNN) and other diagnostic models. The diagnosis results can provide a new idea for studying the health status of tunnel fan and improve the operational safety of tunnel.

Key words:  convolutional neural network(CNN); fan bearing; filtering processing; time-frequency image; diagnostic model
Advanced Search
Online Office System
  • Chinese Core Periodicals
  • Chinese Sci-tech Core Periodicals
  • SA, INSPEC Indexed
  • CSA: T Indexed
  • UPD:Indexed


2010 Zhejiang Information Institute of Mechinery Industry

Technical Support：Hangzhou Bory science and technology

You are 1895221 visit this site