Fault Diagnosis Method of Check Valve Based on Multikernel Cost-Sensitive Extreme Learning Machine
Check valve is one of the most important components and most easily damaged parts in high pressure diaphragm pump, which is a typical representative of reciprocating machinery. In order to ensure the normal operation of the pump, it is necessary to monitor its running state and diagnose fault. Howev...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2017-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2017/8395252 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832558727639597056 |
|---|---|
| author | Jun Ma Jiande Wu Xiaodong Wang |
| author_facet | Jun Ma Jiande Wu Xiaodong Wang |
| author_sort | Jun Ma |
| collection | DOAJ |
| description | Check valve is one of the most important components and most easily damaged parts in high pressure diaphragm pump, which is a typical representative of reciprocating machinery. In order to ensure the normal operation of the pump, it is necessary to monitor its running state and diagnose fault. However, in the fault diagnosis of check valve, the classification models with single kernel function can not fully interpret the classification decision function, and meanwhile unreasonable assumption of diagnostic cost equalization has a significant impact on classification results. Therefore, the multikernel function and cost-sensitive mechanism are introduced to construct the fault diagnosis model of check valve based on the multikernel cost-sensitive extreme learning machine (MKL-CS-ELM) in this paper. The comparative test results of check valve for high pressure diaphragm pump show that MKL-CS-ELM can obtain fairly or slightly better performance than ELM, CS-ELM, MKL-ELM, and multikernel cost-sensitive support vector learning machine (MKL-CS-SVM). At the same time, the presented method can obtain very high accuracy under imbalance datasets condition and effectively overcome the weakness of diagnostic cost equalization and improve the interpretability and reliability of the decision function of classification model. It, therefore, is more suitable for the practical application. |
| format | Article |
| id | doaj-art-642af12c500e403f961ba5fb9933d73a |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2017-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-642af12c500e403f961ba5fb9933d73a2025-02-03T01:31:46ZengWileyComplexity1076-27871099-05262017-01-01201710.1155/2017/83952528395252Fault Diagnosis Method of Check Valve Based on Multikernel Cost-Sensitive Extreme Learning MachineJun Ma0Jiande Wu1Xiaodong Wang2Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming 650500, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaFaculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, ChinaCheck valve is one of the most important components and most easily damaged parts in high pressure diaphragm pump, which is a typical representative of reciprocating machinery. In order to ensure the normal operation of the pump, it is necessary to monitor its running state and diagnose fault. However, in the fault diagnosis of check valve, the classification models with single kernel function can not fully interpret the classification decision function, and meanwhile unreasonable assumption of diagnostic cost equalization has a significant impact on classification results. Therefore, the multikernel function and cost-sensitive mechanism are introduced to construct the fault diagnosis model of check valve based on the multikernel cost-sensitive extreme learning machine (MKL-CS-ELM) in this paper. The comparative test results of check valve for high pressure diaphragm pump show that MKL-CS-ELM can obtain fairly or slightly better performance than ELM, CS-ELM, MKL-ELM, and multikernel cost-sensitive support vector learning machine (MKL-CS-SVM). At the same time, the presented method can obtain very high accuracy under imbalance datasets condition and effectively overcome the weakness of diagnostic cost equalization and improve the interpretability and reliability of the decision function of classification model. It, therefore, is more suitable for the practical application.http://dx.doi.org/10.1155/2017/8395252 |
| spellingShingle | Jun Ma Jiande Wu Xiaodong Wang Fault Diagnosis Method of Check Valve Based on Multikernel Cost-Sensitive Extreme Learning Machine Complexity |
| title | Fault Diagnosis Method of Check Valve Based on Multikernel Cost-Sensitive Extreme Learning Machine |
| title_full | Fault Diagnosis Method of Check Valve Based on Multikernel Cost-Sensitive Extreme Learning Machine |
| title_fullStr | Fault Diagnosis Method of Check Valve Based on Multikernel Cost-Sensitive Extreme Learning Machine |
| title_full_unstemmed | Fault Diagnosis Method of Check Valve Based on Multikernel Cost-Sensitive Extreme Learning Machine |
| title_short | Fault Diagnosis Method of Check Valve Based on Multikernel Cost-Sensitive Extreme Learning Machine |
| title_sort | fault diagnosis method of check valve based on multikernel cost sensitive extreme learning machine |
| url | http://dx.doi.org/10.1155/2017/8395252 |
| work_keys_str_mv | AT junma faultdiagnosismethodofcheckvalvebasedonmultikernelcostsensitiveextremelearningmachine AT jiandewu faultdiagnosismethodofcheckvalvebasedonmultikernelcostsensitiveextremelearningmachine AT xiaodongwang faultdiagnosismethodofcheckvalvebasedonmultikernelcostsensitiveextremelearningmachine |