Quality-related fault diagnosis based on -nearest neighbor rule for non-linear industrial processes
The fault diagnosis approaches based on k -nearest neighbor rule have been widely researched for industrial processes and achieve excellent performance. However, for quality-related fault diagnosis, the approaches using k -nearest neighbor rule have been still not sufficiently studied. To tackle thi...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-11-01
|
| Series: | International Journal of Distributed Sensor Networks |
| Online Access: | https://doi.org/10.1177/15501477211055931 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849306407164182528 |
|---|---|
| author | Zelin Ren Yongqiang Tang Wensheng Zhang |
| author_facet | Zelin Ren Yongqiang Tang Wensheng Zhang |
| author_sort | Zelin Ren |
| collection | DOAJ |
| description | The fault diagnosis approaches based on k -nearest neighbor rule have been widely researched for industrial processes and achieve excellent performance. However, for quality-related fault diagnosis, the approaches using k -nearest neighbor rule have been still not sufficiently studied. To tackle this problem, in this article, we propose a novel quality-related fault diagnosis framework, which is made up of two parts: fault detection and fault isolation. In the fault detection stage, we innovatively propose a novel non-linear quality-related fault detection method called kernel partial least squares- k -nearest neighbor rule, which organically incorporates k -nearest neighbor rule with kernel partial least squares. Specifically, we first employ kernel partial least squares to establish a non-linear regression model between quality variables and process variables. After that, the statistics and thresholds corresponding to process space and predicted quality space are appropriately designed by adopting k -nearest neighbor rule. In the fault isolation stage, in order to match our proposed non-linear quality-related fault detection method kernel partial least squares- k -nearest neighbor seamlessly, we propose a modified variable contributions by k -nearest neighbor (VCkNN) fault isolation method called modified variable contributions by k -nearest neighbor (MVCkNN), which elaborately introduces the idea of the accumulative relative contribution rate into VC k -nearest neighbor, such that the smearing effect caused by the normal distribution hypothesis of VC k -nearest neighbor can be mitigated effectively. Finally, a widely used numerical example and the Tennessee Eastman process are employed to verify the effectiveness of our proposed approach. |
| format | Article |
| id | doaj-art-34a73138941e459fa6b95d14c2002e13 |
| institution | Kabale University |
| issn | 1550-1477 |
| language | English |
| publishDate | 2021-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Distributed Sensor Networks |
| spelling | doaj-art-34a73138941e459fa6b95d14c2002e132025-08-20T03:55:06ZengWileyInternational Journal of Distributed Sensor Networks1550-14772021-11-011710.1177/15501477211055931Quality-related fault diagnosis based on -nearest neighbor rule for non-linear industrial processesZelin Ren0Yongqiang Tang1Wensheng Zhang2University of Chinese Academy of Sciences, Beijing, ChinaResearch Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences, Beijing, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaThe fault diagnosis approaches based on k -nearest neighbor rule have been widely researched for industrial processes and achieve excellent performance. However, for quality-related fault diagnosis, the approaches using k -nearest neighbor rule have been still not sufficiently studied. To tackle this problem, in this article, we propose a novel quality-related fault diagnosis framework, which is made up of two parts: fault detection and fault isolation. In the fault detection stage, we innovatively propose a novel non-linear quality-related fault detection method called kernel partial least squares- k -nearest neighbor rule, which organically incorporates k -nearest neighbor rule with kernel partial least squares. Specifically, we first employ kernel partial least squares to establish a non-linear regression model between quality variables and process variables. After that, the statistics and thresholds corresponding to process space and predicted quality space are appropriately designed by adopting k -nearest neighbor rule. In the fault isolation stage, in order to match our proposed non-linear quality-related fault detection method kernel partial least squares- k -nearest neighbor seamlessly, we propose a modified variable contributions by k -nearest neighbor (VCkNN) fault isolation method called modified variable contributions by k -nearest neighbor (MVCkNN), which elaborately introduces the idea of the accumulative relative contribution rate into VC k -nearest neighbor, such that the smearing effect caused by the normal distribution hypothesis of VC k -nearest neighbor can be mitigated effectively. Finally, a widely used numerical example and the Tennessee Eastman process are employed to verify the effectiveness of our proposed approach.https://doi.org/10.1177/15501477211055931 |
| spellingShingle | Zelin Ren Yongqiang Tang Wensheng Zhang Quality-related fault diagnosis based on -nearest neighbor rule for non-linear industrial processes International Journal of Distributed Sensor Networks |
| title | Quality-related fault diagnosis based on -nearest neighbor rule for non-linear industrial processes |
| title_full | Quality-related fault diagnosis based on -nearest neighbor rule for non-linear industrial processes |
| title_fullStr | Quality-related fault diagnosis based on -nearest neighbor rule for non-linear industrial processes |
| title_full_unstemmed | Quality-related fault diagnosis based on -nearest neighbor rule for non-linear industrial processes |
| title_short | Quality-related fault diagnosis based on -nearest neighbor rule for non-linear industrial processes |
| title_sort | quality related fault diagnosis based on nearest neighbor rule for non linear industrial processes |
| url | https://doi.org/10.1177/15501477211055931 |
| work_keys_str_mv | AT zelinren qualityrelatedfaultdiagnosisbasedonnearestneighborrulefornonlinearindustrialprocesses AT yongqiangtang qualityrelatedfaultdiagnosisbasedonnearestneighborrulefornonlinearindustrialprocesses AT wenshengzhang qualityrelatedfaultdiagnosisbasedonnearestneighborrulefornonlinearindustrialprocesses |