Fault Diagnosis of Reciprocating Compressor Valve Based on Triplet Siamese Neural Network

A fault diagnosis method for reciprocating compressor valves suitable for variable operating conditions is presented in this paper. Firstly, a test bench is independently constructed to simulate fault scenarios under diverse operating conditions and with various faults. The two types of p-V diagrams...

Full description

Saved in:
Bibliographic Details
Main Authors: Zixuan Zhang, Wenbo Wang, Wenzheng Chen, Qiang Xiao, Weiwei Xu, Qiang Li, Jie Wang, Zhaozeng Liu
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Machines
Subjects:
Online Access:https://www.mdpi.com/2075-1702/13/4/263
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850180776604205056
author Zixuan Zhang
Wenbo Wang
Wenzheng Chen
Qiang Xiao
Weiwei Xu
Qiang Li
Jie Wang
Zhaozeng Liu
author_facet Zixuan Zhang
Wenbo Wang
Wenzheng Chen
Qiang Xiao
Weiwei Xu
Qiang Li
Jie Wang
Zhaozeng Liu
author_sort Zixuan Zhang
collection DOAJ
description A fault diagnosis method for reciprocating compressor valves suitable for variable operating conditions is presented in this paper. Firstly, a test bench is independently constructed to simulate fault scenarios under diverse operating conditions and with various faults. The two types of p-V diagrams are gathered, and the improved logarithmic p-V diagram acquisition method is used for logarithmic transformation to obtain the multi-conditional logarithmic p-V diagram dataset and the fault logarithmic p-V diagram dataset. Subsequently, to predict the fault-free logarithmic p-V diagram under different operating conditions, a BP neural network is trained with the multi-condition logarithmic p-V diagram dataset. Next, the fault sequence is derived by subtracting the fault logarithmic p-V diagram from the fault-free logarithmic p-V diagram acquired under the same operating condition. Ultimately, the feature extraction of the fault sequence and the fault classification are accomplished by the employment of a triplet Siamese neural network (SNN). The results indicate that the fault classification accuracy of the method presented in this paper can attain 100%, which confirms that differential processing on the logarithmic p-V diagram is effective for fault feature preprocessing. This study not only improves the accuracy and efficiency of valve fault diagnosis in reciprocating compressors but also provides technical support for maintenance and fault prevention.
format Article
id doaj-art-0aa2183b6d4b4b92bc8bd38ce55af1fd
institution OA Journals
issn 2075-1702
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Machines
spelling doaj-art-0aa2183b6d4b4b92bc8bd38ce55af1fd2025-08-20T02:18:03ZengMDPI AGMachines2075-17022025-03-0113426310.3390/machines13040263Fault Diagnosis of Reciprocating Compressor Valve Based on Triplet Siamese Neural NetworkZixuan Zhang0Wenbo Wang1Wenzheng Chen2Qiang Xiao3Weiwei Xu4Qiang Li5Jie Wang6Zhaozeng Liu7College of New Energy, China University of Petroleum (East China), Qingdao 266580, ChinaChina Petroleum Technology and Development Corporation, No. 8 Taiyanggongjinxingyuan, Chaoyang District, Beijing 100028, ChinaChina Petroleum Technology and Development Corporation, No. 8 Taiyanggongjinxingyuan, Chaoyang District, Beijing 100028, ChinaCNPC JCPC Chengdu Compressor Branch, No. 3 Century Avenue, Longquanyi District, Chengdu 610100, ChinaCollege of New Energy, China University of Petroleum (East China), Qingdao 266580, ChinaCollege of New Energy, China University of Petroleum (East China), Qingdao 266580, ChinaCollege of New Energy, China University of Petroleum (East China), Qingdao 266580, ChinaCollege of New Energy, China University of Petroleum (East China), Qingdao 266580, ChinaA fault diagnosis method for reciprocating compressor valves suitable for variable operating conditions is presented in this paper. Firstly, a test bench is independently constructed to simulate fault scenarios under diverse operating conditions and with various faults. The two types of p-V diagrams are gathered, and the improved logarithmic p-V diagram acquisition method is used for logarithmic transformation to obtain the multi-conditional logarithmic p-V diagram dataset and the fault logarithmic p-V diagram dataset. Subsequently, to predict the fault-free logarithmic p-V diagram under different operating conditions, a BP neural network is trained with the multi-condition logarithmic p-V diagram dataset. Next, the fault sequence is derived by subtracting the fault logarithmic p-V diagram from the fault-free logarithmic p-V diagram acquired under the same operating condition. Ultimately, the feature extraction of the fault sequence and the fault classification are accomplished by the employment of a triplet Siamese neural network (SNN). The results indicate that the fault classification accuracy of the method presented in this paper can attain 100%, which confirms that differential processing on the logarithmic p-V diagram is effective for fault feature preprocessing. This study not only improves the accuracy and efficiency of valve fault diagnosis in reciprocating compressors but also provides technical support for maintenance and fault prevention.https://www.mdpi.com/2075-1702/13/4/263fault diagnosisp-V diagramreciprocating compressortriplet Siamese neural network (SNN)valve
spellingShingle Zixuan Zhang
Wenbo Wang
Wenzheng Chen
Qiang Xiao
Weiwei Xu
Qiang Li
Jie Wang
Zhaozeng Liu
Fault Diagnosis of Reciprocating Compressor Valve Based on Triplet Siamese Neural Network
Machines
fault diagnosis
p-V diagram
reciprocating compressor
triplet Siamese neural network (SNN)
valve
title Fault Diagnosis of Reciprocating Compressor Valve Based on Triplet Siamese Neural Network
title_full Fault Diagnosis of Reciprocating Compressor Valve Based on Triplet Siamese Neural Network
title_fullStr Fault Diagnosis of Reciprocating Compressor Valve Based on Triplet Siamese Neural Network
title_full_unstemmed Fault Diagnosis of Reciprocating Compressor Valve Based on Triplet Siamese Neural Network
title_short Fault Diagnosis of Reciprocating Compressor Valve Based on Triplet Siamese Neural Network
title_sort fault diagnosis of reciprocating compressor valve based on triplet siamese neural network
topic fault diagnosis
p-V diagram
reciprocating compressor
triplet Siamese neural network (SNN)
valve
url https://www.mdpi.com/2075-1702/13/4/263
work_keys_str_mv AT zixuanzhang faultdiagnosisofreciprocatingcompressorvalvebasedontripletsiameseneuralnetwork
AT wenbowang faultdiagnosisofreciprocatingcompressorvalvebasedontripletsiameseneuralnetwork
AT wenzhengchen faultdiagnosisofreciprocatingcompressorvalvebasedontripletsiameseneuralnetwork
AT qiangxiao faultdiagnosisofreciprocatingcompressorvalvebasedontripletsiameseneuralnetwork
AT weiweixu faultdiagnosisofreciprocatingcompressorvalvebasedontripletsiameseneuralnetwork
AT qiangli faultdiagnosisofreciprocatingcompressorvalvebasedontripletsiameseneuralnetwork
AT jiewang faultdiagnosisofreciprocatingcompressorvalvebasedontripletsiameseneuralnetwork
AT zhaozengliu faultdiagnosisofreciprocatingcompressorvalvebasedontripletsiameseneuralnetwork