Knock Detection Based on Recursive Variational Mode Decomposition and Multilevel Semi-Supervised Local Fisher Discriminant Analysis
Knock is an abnormal combustion phenomenon in gasoline engines. Strong knocks will reduce the efficiency and durability of engine, while with slight knocks engines can run on a high-efficiency state. It is necessary to detect knock and control the state of knock in order to improve the thermal effic...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8813039/ |
| _version_ | 1818613257755164672 |
|---|---|
| author | Fengrong Bi Xin Li Jiewei Lin Xiaobo Bi Teng Ma Xiao Yang Daijie Tang Pengfei Shen |
| author_facet | Fengrong Bi Xin Li Jiewei Lin Xiaobo Bi Teng Ma Xiao Yang Daijie Tang Pengfei Shen |
| author_sort | Fengrong Bi |
| collection | DOAJ |
| description | Knock is an abnormal combustion phenomenon in gasoline engines. Strong knocks will reduce the efficiency and durability of engine, while with slight knocks engines can run on a high-efficiency state. It is necessary to detect knock and control the state of knock in order to improve the thermal efficiency of engine. This paper proposes a novel approach for detecting engine knocks in various intensities based on vibration signal of engine block using variational mode decomposition (VMD) and semi-supervised local fisher discriminant analysis (SELF). Since the quadratic penalty of recursive VMD has a great influence on decomposition results, the approach establishes the connection between the quadratic penalty and the stop condition by analyzing a large amount of data and quantifies the relationship by polynomial fitting, which reduces the complexity and subjectivity of recursive VMD. A multilevel SELF is developed for solving the problem that SELFs sometimes may not find ideal embedding space under large scale dimensionality reduction. This method adopts multi embedding spaces, with gradually decreasing dimension, to reduce the dimensionality of original data by a series of small steps. Verifications show the proposed approach can achieve high classification accuracy in knock detection and is able to identify the intensity of knock. This research contributes to the field of engine abnormality detection and can be implemented on vibration-based faults diagnosis area. |
| first_indexed | 2024-12-16T15:59:15Z |
| format | Article |
| id | doaj.art-9591ae38a9cb454da2c7a3c040a83536 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T15:59:15Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-9591ae38a9cb454da2c7a3c040a835362022-12-21T22:25:30ZengIEEEIEEE Access2169-35362019-01-01712202812204010.1109/ACCESS.2019.29375718813039Knock Detection Based on Recursive Variational Mode Decomposition and Multilevel Semi-Supervised Local Fisher Discriminant AnalysisFengrong Bi0Xin Li1https://orcid.org/0000-0002-9244-6485Jiewei Lin2Xiaobo Bi3https://orcid.org/0000-0003-0183-7729Teng Ma4Xiao Yang5Daijie Tang6https://orcid.org/0000-0001-9913-9093Pengfei Shen7State Key Laboratory of Engines, Tianjin University, Tianjin, ChinaState Key Laboratory of Engines, Tianjin University, Tianjin, ChinaState Key Laboratory of Engines, Tianjin University, Tianjin, ChinaState Key Laboratory of Engines, Tianjin University, Tianjin, ChinaState Key Laboratory of Engines, Tianjin University, Tianjin, ChinaState Key Laboratory of Engines, Tianjin University, Tianjin, ChinaState Key Laboratory of Engines, Tianjin University, Tianjin, ChinaState Key Laboratory of Engines, Tianjin University, Tianjin, ChinaKnock is an abnormal combustion phenomenon in gasoline engines. Strong knocks will reduce the efficiency and durability of engine, while with slight knocks engines can run on a high-efficiency state. It is necessary to detect knock and control the state of knock in order to improve the thermal efficiency of engine. This paper proposes a novel approach for detecting engine knocks in various intensities based on vibration signal of engine block using variational mode decomposition (VMD) and semi-supervised local fisher discriminant analysis (SELF). Since the quadratic penalty of recursive VMD has a great influence on decomposition results, the approach establishes the connection between the quadratic penalty and the stop condition by analyzing a large amount of data and quantifies the relationship by polynomial fitting, which reduces the complexity and subjectivity of recursive VMD. A multilevel SELF is developed for solving the problem that SELFs sometimes may not find ideal embedding space under large scale dimensionality reduction. This method adopts multi embedding spaces, with gradually decreasing dimension, to reduce the dimensionality of original data by a series of small steps. Verifications show the proposed approach can achieve high classification accuracy in knock detection and is able to identify the intensity of knock. This research contributes to the field of engine abnormality detection and can be implemented on vibration-based faults diagnosis area.https://ieeexplore.ieee.org/document/8813039/Engineknock detectionsemi-supervised local fisher discriminant analysis (SELF)variational mode decomposition (VMD)vibration |
| spellingShingle | Fengrong Bi Xin Li Jiewei Lin Xiaobo Bi Teng Ma Xiao Yang Daijie Tang Pengfei Shen Knock Detection Based on Recursive Variational Mode Decomposition and Multilevel Semi-Supervised Local Fisher Discriminant Analysis IEEE Access Engine knock detection semi-supervised local fisher discriminant analysis (SELF) variational mode decomposition (VMD) vibration |
| title | Knock Detection Based on Recursive Variational Mode Decomposition and Multilevel Semi-Supervised Local Fisher Discriminant Analysis |
| title_full | Knock Detection Based on Recursive Variational Mode Decomposition and Multilevel Semi-Supervised Local Fisher Discriminant Analysis |
| title_fullStr | Knock Detection Based on Recursive Variational Mode Decomposition and Multilevel Semi-Supervised Local Fisher Discriminant Analysis |
| title_full_unstemmed | Knock Detection Based on Recursive Variational Mode Decomposition and Multilevel Semi-Supervised Local Fisher Discriminant Analysis |
| title_short | Knock Detection Based on Recursive Variational Mode Decomposition and Multilevel Semi-Supervised Local Fisher Discriminant Analysis |
| title_sort | knock detection based on recursive variational mode decomposition and multilevel semi supervised local fisher discriminant analysis |
| topic | Engine knock detection semi-supervised local fisher discriminant analysis (SELF) variational mode decomposition (VMD) vibration |
| url | https://ieeexplore.ieee.org/document/8813039/ |
| work_keys_str_mv | AT fengrongbi knockdetectionbasedonrecursivevariationalmodedecompositionandmultilevelsemisupervisedlocalfisherdiscriminantanalysis AT xinli knockdetectionbasedonrecursivevariationalmodedecompositionandmultilevelsemisupervisedlocalfisherdiscriminantanalysis AT jieweilin knockdetectionbasedonrecursivevariationalmodedecompositionandmultilevelsemisupervisedlocalfisherdiscriminantanalysis AT xiaobobi knockdetectionbasedonrecursivevariationalmodedecompositionandmultilevelsemisupervisedlocalfisherdiscriminantanalysis AT tengma knockdetectionbasedonrecursivevariationalmodedecompositionandmultilevelsemisupervisedlocalfisherdiscriminantanalysis AT xiaoyang knockdetectionbasedonrecursivevariationalmodedecompositionandmultilevelsemisupervisedlocalfisherdiscriminantanalysis AT daijietang knockdetectionbasedonrecursivevariationalmodedecompositionandmultilevelsemisupervisedlocalfisherdiscriminantanalysis AT pengfeishen knockdetectionbasedonrecursivevariationalmodedecompositionandmultilevelsemisupervisedlocalfisherdiscriminantanalysis |