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

Prediction model of friction factor of friction pair lubricated by graphene lubricating oil
Published:2023-05-25 author:ZHANG Li-xiu, LI Shuang, WEI Xiao-yi, et al. Browse: 1348 Check PDF documents
Prediction model of friction factor of friction pair lubricated 
by graphene lubricating oil


ZHANG Li-xiu1,2, LI Shuang3, WEI Xiao-yi4, WANG Jun-hai1, LI Song-hua2,3


(1.Analysis and Detection Technology Research Center, Shenyang Jianzhu University, Shenyang 110000, China;

2.National and Local Joint Engineering Laboratory for High Grade Stone NC Processing Equipment and Technology, 

Shenyang Jianzhu University, Shenyang 110000, China; 3.College of Mechanical Engineering, Shenyang Jianzhu 

University, Shenyang 110000, China; 4.College of Materials Science and Engineering, Shenyang 

Jianzhu University, Shenyang 110000, China)


Abstract: The friction state of bearing is very complex, and the rolling friction is the main one. It is difficult to calculate or measure the rolling friction coefficient accurately.Aiming at the problem that the rolling friction factor of bearing was difficult to be measured, the sliding friction factor which was closely related to the rolling friction factor was measured and predicted. A prediction network model of optimal sliding friction coefficient was proposed. Firstly, the friction and wear tests of Si3N4-GCr15 friction pair under graphene lubrication were carried out to obtain the sliding friction factor under different graphene mass fraction under different working conditions. Then, the generalized regression neural network (GRNN) was proposed, and the genetic algorithm (GA) was used to optimize the smoothing factor (σ), and the prediction network model of the best sliding friction factor was obtained. Finally, the prediction results of the test set and the prediction results of other prediction models were verified, and the application of the prediction model was verified by combining the prediction results of the validation set. The results show that, comparing with the conventional GRNN model and back propagation( BP )neural network model, the GA-GRNN model has significantly higher prediction accuracy and less prediction error. The predicted value of the validation set of GAGRNN model is very close to the real value, the average accuracy of the predicted value is 92.30%, and the relative error of the prediction is within the range of ［0.00099017, 0.0083249］. The prediction effect of the sliding friction factor is good, which can provide a basis for the prediction of the bearing rolling friction factor.

Key words: bearing; rolling/sliding friction factor; generalized regression neural network (GRNN); genetic algorithm (GA); friction and wear test; prediction error; prediction accuracy
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