《机电工程》杂志社科技期刊核心期刊论文投稿机电一体化机械、仪表电工自动化、计算机浙江大学主办

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

Fault diagnosis method of reciprocating compressor based on AO-VMD

Published:2023-07-18 author:LI Ying, WANG Peng, WU Shi-hu, et al. Browse: 473 Check PDF documents

Fault diagnosis method of reciprocating compressor based on AO-VMD

LI Ying, WANG Peng, WU Shi-hu, BA Peng

(School of Mechanical Engineering, Shenyang Ligong University, Shenyang 110159, China )

Abstract: When the original VMD method is used to diagnose the faults of reciprocating compressors, the vibration signals of vulnerable parts of reciprocating compressors are non-stationary and nonlinear.Therefore, a fault feature extraction method of reciprocating compressor using Aquila optimizer (AO) is proposed, which takes the minimum entropy of each component sample as the fitness function, and optimizes the decomposition of variational modal decomposition (VMD).Firstly, the vibration signal of the reciprocating compressor sliding bearing was analyzed and processed in different states by analyzing the fault of the bearing. Then, the vibration signal was denoised using wavelet noise elimination, and band-limite dintrinsic mode functions(BLIMF)components were respectively obtained by using the original VMD and the new decomposition method of AO-VMD. Finally, the multi-scale sample entropy(MSE) values of each component of the two decomposition methods were calculated, and the multi-scale sample entropy values of different states were compared and analyzed to achieve the diagnosis of various types of faults of reciprocating compressors. The research results show that the AO-VMD method utilizes the powerful rapid search and development capability of AO, and the fault classification performance is significantly better than that of the original VMD decomposition method, and the multi-scale sample entropy values of various fault signals are clearly distinguished. The time saving effect is significant, and the decomposition time of the genetic algorithm optimization-based VMD method takes 427 s while that of the AO-VMD method only takes 165 s, which can meet the requirements of the fault diagnosis decomposition.

Key words: positive displacement compressor; variational modal decomposition(VMD); Aquila optimizer(AO); fault diagnosis; multiscale sample entropy (MSE); sliding bearing failure

Advanced Search

Online Office System

Chinese Core Periodicals
Chinese Sci-tech Core Periodicals
SA, INSPEC Indexed
CSA: T Indexed
UPD:Indexed