Determining Dynamic Thresholds for Gas Turbine Engine Condition Monitoring
Thresholds are commonly used in condition monitoring and fault diagnosis of gas turbine engines as they are the criteria for health status discrimination. We discover that most thresholds should be varying according to gas turbine working condition, but many traditional fixed threshold designs didn&...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9857846/ |
| _version_ | 1811281433131483136 |
|---|---|
| author | Zhouzheng Li Dongyan Miao Kun Feng |
| author_facet | Zhouzheng Li Dongyan Miao Kun Feng |
| author_sort | Zhouzheng Li |
| collection | DOAJ |
| description | Thresholds are commonly used in condition monitoring and fault diagnosis of gas turbine engines as they are the criteria for health status discrimination. We discover that most thresholds should be varying according to gas turbine working condition, but many traditional fixed threshold designs didn’t consider this and therefore can potentially be replaced with dynamic ones for higher monitoring precision. In this paper, we propose an objective function that can be applied in any neural network model to learn to output a set of parameters for a distribution based on the maximum likelihood theory, and a matching dynamic threshold determination method for health state discrimination in example of a residual-based monitoring approach. The proposed methods are examined progressively with simulated data and finally an industrial gas turbine failure case. Results show that 1) the proposed objective function can learn the parameters of the distribution well; 2) the dynamic thresholds can effectively reduce the false-positive and false-negative rates when there is a varying noise comparing to fixed thresholds. |
| first_indexed | 2024-04-13T01:33:34Z |
| format | Article |
| id | doaj.art-cdbb5cbc945b46f895df04651b8cead6 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-13T01:33:34Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-cdbb5cbc945b46f895df04651b8cead62022-12-22T03:08:27ZengIEEEIEEE Access2169-35362022-01-0110874048741410.1109/ACCESS.2022.31989839857846Determining Dynamic Thresholds for Gas Turbine Engine Condition MonitoringZhouzheng Li0https://orcid.org/0000-0001-9451-1861Dongyan Miao1Kun Feng2Key Laboratory of Engine Health Monitoring-Control and Networking, Ministry of Education, Beijing University of Chemical Technology, Beijing, ChinaKey Laboratory of Engine Health Monitoring-Control and Networking, Ministry of Education, Beijing University of Chemical Technology, Beijing, ChinaKey Laboratory of Engine Health Monitoring-Control and Networking, Ministry of Education, Beijing University of Chemical Technology, Beijing, ChinaThresholds are commonly used in condition monitoring and fault diagnosis of gas turbine engines as they are the criteria for health status discrimination. We discover that most thresholds should be varying according to gas turbine working condition, but many traditional fixed threshold designs didn’t consider this and therefore can potentially be replaced with dynamic ones for higher monitoring precision. In this paper, we propose an objective function that can be applied in any neural network model to learn to output a set of parameters for a distribution based on the maximum likelihood theory, and a matching dynamic threshold determination method for health state discrimination in example of a residual-based monitoring approach. The proposed methods are examined progressively with simulated data and finally an industrial gas turbine failure case. Results show that 1) the proposed objective function can learn the parameters of the distribution well; 2) the dynamic thresholds can effectively reduce the false-positive and false-negative rates when there is a varying noise comparing to fixed thresholds.https://ieeexplore.ieee.org/document/9857846/Thresholdscondition monitoringgas turbine enginemachine learning |
| spellingShingle | Zhouzheng Li Dongyan Miao Kun Feng Determining Dynamic Thresholds for Gas Turbine Engine Condition Monitoring IEEE Access Thresholds condition monitoring gas turbine engine machine learning |
| title | Determining Dynamic Thresholds for Gas Turbine Engine Condition Monitoring |
| title_full | Determining Dynamic Thresholds for Gas Turbine Engine Condition Monitoring |
| title_fullStr | Determining Dynamic Thresholds for Gas Turbine Engine Condition Monitoring |
| title_full_unstemmed | Determining Dynamic Thresholds for Gas Turbine Engine Condition Monitoring |
| title_short | Determining Dynamic Thresholds for Gas Turbine Engine Condition Monitoring |
| title_sort | determining dynamic thresholds for gas turbine engine condition monitoring |
| topic | Thresholds condition monitoring gas turbine engine machine learning |
| url | https://ieeexplore.ieee.org/document/9857846/ |
| work_keys_str_mv | AT zhouzhengli determiningdynamicthresholdsforgasturbineengineconditionmonitoring AT dongyanmiao determiningdynamicthresholdsforgasturbineengineconditionmonitoring AT kunfeng determiningdynamicthresholdsforgasturbineengineconditionmonitoring |