Leakage Fault Diagnosis of Two Parallel Cylinders in Pneumatic System with a Minimal Number of Sensors
The low investment cost is one of the core competitiveness advantages of pneumatic power systems. With increasingly pressing intelligent manufacturing, it is meaningful to investigate the feasibility of implementing fault diagnoses of pneumatic systems with a minimal number of low-cost sensors. In t...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-07-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/12/15/3261 |
_version_ | 1797586875925397504 |
---|---|
author | Hongwei Zhu Zhiwen Wang Hu Wang Zecheng Zhao Wei Xiong |
author_facet | Hongwei Zhu Zhiwen Wang Hu Wang Zecheng Zhao Wei Xiong |
author_sort | Hongwei Zhu |
collection | DOAJ |
description | The low investment cost is one of the core competitiveness advantages of pneumatic power systems. With increasingly pressing intelligent manufacturing, it is meaningful to investigate the feasibility of implementing fault diagnoses of pneumatic systems with a minimal number of low-cost sensors. In this study, a typical pneumatic circuit with two parallel-installed cylinders is taken as an example. The pressure, flow rate, and exergy data collected from upstream sensors are used for diagnosing the leakage faults in two downstream cylinders with the help of different machine learning methods. The features of data are extracted with stacked auto-encoders. Gaussian process classifier, support vector machine, and k-nearest neighbor are used for classifying faults. The results show that it is feasible to detect and diagnose downstream multi-faults with one or two upstream sensors. In terms of the working conditions presented in this study, the average accuracy of diagnosis with exergy data is the highest, followed by flow-rate data and pressure data. The support vector machine performs the best among the three machine learning methods. |
first_indexed | 2024-03-11T00:29:22Z |
format | Article |
id | doaj.art-5d9f804b6af54e7ca186cff29a6c7787 |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-11T00:29:22Z |
publishDate | 2023-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-5d9f804b6af54e7ca186cff29a6c77872023-11-18T22:48:39ZengMDPI AGElectronics2079-92922023-07-011215326110.3390/electronics12153261Leakage Fault Diagnosis of Two Parallel Cylinders in Pneumatic System with a Minimal Number of SensorsHongwei Zhu0Zhiwen Wang1Hu Wang2Zecheng Zhao3Wei Xiong4Department of Mechanical Engineering, Dalian Maritime University, Dalian 116026, ChinaDepartment of Mechanical Engineering, Dalian Maritime University, Dalian 116026, ChinaDepartment of Mechanical Engineering, Dalian Maritime University, Dalian 116026, ChinaDepartment of Mechanical Engineering, Dalian Maritime University, Dalian 116026, ChinaDepartment of Mechanical Engineering, Dalian Maritime University, Dalian 116026, ChinaThe low investment cost is one of the core competitiveness advantages of pneumatic power systems. With increasingly pressing intelligent manufacturing, it is meaningful to investigate the feasibility of implementing fault diagnoses of pneumatic systems with a minimal number of low-cost sensors. In this study, a typical pneumatic circuit with two parallel-installed cylinders is taken as an example. The pressure, flow rate, and exergy data collected from upstream sensors are used for diagnosing the leakage faults in two downstream cylinders with the help of different machine learning methods. The features of data are extracted with stacked auto-encoders. Gaussian process classifier, support vector machine, and k-nearest neighbor are used for classifying faults. The results show that it is feasible to detect and diagnose downstream multi-faults with one or two upstream sensors. In terms of the working conditions presented in this study, the average accuracy of diagnosis with exergy data is the highest, followed by flow-rate data and pressure data. The support vector machine performs the best among the three machine learning methods.https://www.mdpi.com/2079-9292/12/15/3261pneumaticsfault diagnosisexergymachine learningcompressed airsupport vector machine |
spellingShingle | Hongwei Zhu Zhiwen Wang Hu Wang Zecheng Zhao Wei Xiong Leakage Fault Diagnosis of Two Parallel Cylinders in Pneumatic System with a Minimal Number of Sensors Electronics pneumatics fault diagnosis exergy machine learning compressed air support vector machine |
title | Leakage Fault Diagnosis of Two Parallel Cylinders in Pneumatic System with a Minimal Number of Sensors |
title_full | Leakage Fault Diagnosis of Two Parallel Cylinders in Pneumatic System with a Minimal Number of Sensors |
title_fullStr | Leakage Fault Diagnosis of Two Parallel Cylinders in Pneumatic System with a Minimal Number of Sensors |
title_full_unstemmed | Leakage Fault Diagnosis of Two Parallel Cylinders in Pneumatic System with a Minimal Number of Sensors |
title_short | Leakage Fault Diagnosis of Two Parallel Cylinders in Pneumatic System with a Minimal Number of Sensors |
title_sort | leakage fault diagnosis of two parallel cylinders in pneumatic system with a minimal number of sensors |
topic | pneumatics fault diagnosis exergy machine learning compressed air support vector machine |
url | https://www.mdpi.com/2079-9292/12/15/3261 |
work_keys_str_mv | AT hongweizhu leakagefaultdiagnosisoftwoparallelcylindersinpneumaticsystemwithaminimalnumberofsensors AT zhiwenwang leakagefaultdiagnosisoftwoparallelcylindersinpneumaticsystemwithaminimalnumberofsensors AT huwang leakagefaultdiagnosisoftwoparallelcylindersinpneumaticsystemwithaminimalnumberofsensors AT zechengzhao leakagefaultdiagnosisoftwoparallelcylindersinpneumaticsystemwithaminimalnumberofsensors AT weixiong leakagefaultdiagnosisoftwoparallelcylindersinpneumaticsystemwithaminimalnumberofsensors |