Study on the condition monitoring system for the sliding surface using machine learning
Machine equipment usually comprises many mechanical elements that can fail because of functional deterioration and friction. For tribo-elements like plane bearings, it is extremely important to diagnose the abnormal conditions and prevent such parts from breakdown caused by wear. However, diagnosing...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | Japanese |
| Published: |
The Japan Society of Mechanical Engineers
2018-11-01
|
| Series: | Nihon Kikai Gakkai ronbunshu |
| Subjects: | |
| Online Access: | https://www.jstage.jst.go.jp/article/transjsme/84/868/84_18-00275/_pdf/-char/en |
| _version_ | 1811220995709599744 |
|---|---|
| author | Yuka HASHIMOTO Tomomi HONDA Yusuke MOCHIDA Kazuhiko SUGIYAMA Yumiko NAKAMURA Chikako TAKATOH |
| author_facet | Yuka HASHIMOTO Tomomi HONDA Yusuke MOCHIDA Kazuhiko SUGIYAMA Yumiko NAKAMURA Chikako TAKATOH |
| author_sort | Yuka HASHIMOTO |
| collection | DOAJ |
| description | Machine equipment usually comprises many mechanical elements that can fail because of functional deterioration and friction. For tribo-elements like plane bearings, it is extremely important to diagnose the abnormal conditions and prevent such parts from breakdown caused by wear. However, diagnosing tribo-elements requires expensive diagnostic equipment and expertise. This study aims to propose a cost- and time- effective system that detect the signs of breakdown during equipment operation by using machine learning to identify abnormalities. We conducted wear tests in contaminated oil and used multiple sensors to collect data regarding the friction force, the electrical contact resistance, the acoustic emission (AE) signal, and vibration. An appropriate learning sample was selected using k-fold cross-validation. The electrical contact resistance was found to contribute relatively little to the detection of abnormalities, whereas the friction coefficient contributed greatly. Furthermore, the AE signal and the vibration detected local changes on the sliding surface. Consequently, we found that machine learning can judge whether monitoring data are normal or abnormal. |
| first_indexed | 2024-04-12T07:51:23Z |
| format | Article |
| id | doaj.art-86387449c7ff4a5bbc9530e2f9d0de90 |
| institution | Directory Open Access Journal |
| issn | 2187-9761 |
| language | Japanese |
| last_indexed | 2024-04-12T07:51:23Z |
| publishDate | 2018-11-01 |
| publisher | The Japan Society of Mechanical Engineers |
| record_format | Article |
| series | Nihon Kikai Gakkai ronbunshu |
| spelling | doaj.art-86387449c7ff4a5bbc9530e2f9d0de902022-12-22T03:41:35ZjpnThe Japan Society of Mechanical EngineersNihon Kikai Gakkai ronbunshu2187-97612018-11-018486818-0027518-0027510.1299/transjsme.18-00275transjsmeStudy on the condition monitoring system for the sliding surface using machine learningYuka HASHIMOTO0Tomomi HONDA1Yusuke MOCHIDA2Kazuhiko SUGIYAMA3Yumiko NAKAMURA4Chikako TAKATOH5School of Engineering, University of FukuiSchool of Engineering, University of FukuiSchool of Engineering, University of FukuiTechnologies, R&D Division, Ebara CorporationTechnologies, R&D Division, Ebara CorporationTechnologies, R&D Division, Ebara CorporationMachine equipment usually comprises many mechanical elements that can fail because of functional deterioration and friction. For tribo-elements like plane bearings, it is extremely important to diagnose the abnormal conditions and prevent such parts from breakdown caused by wear. However, diagnosing tribo-elements requires expensive diagnostic equipment and expertise. This study aims to propose a cost- and time- effective system that detect the signs of breakdown during equipment operation by using machine learning to identify abnormalities. We conducted wear tests in contaminated oil and used multiple sensors to collect data regarding the friction force, the electrical contact resistance, the acoustic emission (AE) signal, and vibration. An appropriate learning sample was selected using k-fold cross-validation. The electrical contact resistance was found to contribute relatively little to the detection of abnormalities, whereas the friction coefficient contributed greatly. Furthermore, the AE signal and the vibration detected local changes on the sliding surface. Consequently, we found that machine learning can judge whether monitoring data are normal or abnormal.https://www.jstage.jst.go.jp/article/transjsme/84/868/84_18-00275/_pdf/-char/entribologymachine learningcondition monitoringmaintenancek-fold cross-validation |
| spellingShingle | Yuka HASHIMOTO Tomomi HONDA Yusuke MOCHIDA Kazuhiko SUGIYAMA Yumiko NAKAMURA Chikako TAKATOH Study on the condition monitoring system for the sliding surface using machine learning Nihon Kikai Gakkai ronbunshu tribology machine learning condition monitoring maintenance k-fold cross-validation |
| title | Study on the condition monitoring system for the sliding surface using machine learning |
| title_full | Study on the condition monitoring system for the sliding surface using machine learning |
| title_fullStr | Study on the condition monitoring system for the sliding surface using machine learning |
| title_full_unstemmed | Study on the condition monitoring system for the sliding surface using machine learning |
| title_short | Study on the condition monitoring system for the sliding surface using machine learning |
| title_sort | study on the condition monitoring system for the sliding surface using machine learning |
| topic | tribology machine learning condition monitoring maintenance k-fold cross-validation |
| url | https://www.jstage.jst.go.jp/article/transjsme/84/868/84_18-00275/_pdf/-char/en |
| work_keys_str_mv | AT yukahashimoto studyontheconditionmonitoringsystemfortheslidingsurfaceusingmachinelearning AT tomomihonda studyontheconditionmonitoringsystemfortheslidingsurfaceusingmachinelearning AT yusukemochida studyontheconditionmonitoringsystemfortheslidingsurfaceusingmachinelearning AT kazuhikosugiyama studyontheconditionmonitoringsystemfortheslidingsurfaceusingmachinelearning AT yumikonakamura studyontheconditionmonitoringsystemfortheslidingsurfaceusingmachinelearning AT chikakotakatoh studyontheconditionmonitoringsystemfortheslidingsurfaceusingmachinelearning |