Aero-engine fault diagnosis based on time series anomaly detection
The fault diagnosis of aero-engines is confronted with a data skew issue，where the number of fault sam ples is significantly fewer than normal samples，and the fault samples can't adequately represent the entire operating conditions，resulting in poor generalization ability of conventional classi...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Advances in Aeronautical Science and Engineering
2025-04-01
|
| Series: | Hangkong gongcheng jinzhan |
| Subjects: | |
| Online Access: | http://hkgcjz.cnjournals.com/hkgcjz/article/abstract/2024055 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849316033055162368 |
|---|---|
| author | WANG Yinru |
| author_facet | WANG Yinru |
| author_sort | WANG Yinru |
| collection | DOAJ |
| description | The fault diagnosis of aero-engines is confronted with a data skew issue，where the number of fault sam ples is significantly fewer than normal samples，and the fault samples can't adequately represent the entire operating conditions，resulting in poor generalization ability of conventional classification models. To overcome this issue，an improved deep support vector data description-based time series anomaly detection model is proposed. The long short-term memory（LSTM）network is employed to map the inputs and outputs of samples，forming temporal anomaly vectors with actual collected outputs. The deep support vector data description（SVDD）incorporating variational auto-encoder（VAE）is utilized to achieve anomaly detection for aero-engine time series data. The experimental verification is performed with a certain type of aero-engine ground test platform，and the model is com pared to with isolation forest（IF），transformer-based anomaly detection（TranAD）model，and GANomaly. The results show that the curve value calculated with the proposed model can reach to 0.987 8，has superior anomaly detection performance. The proposed model can effectively be applied to various anomaly detection and fault diagnosis tasks in aero-engine systems. |
| format | Article |
| id | doaj-art-04b07fdabba9464fa62dfdb65a71456e |
| institution | Kabale University |
| issn | 1674-8190 |
| language | zho |
| publishDate | 2025-04-01 |
| publisher | Editorial Department of Advances in Aeronautical Science and Engineering |
| record_format | Article |
| series | Hangkong gongcheng jinzhan |
| spelling | doaj-art-04b07fdabba9464fa62dfdb65a71456e2025-08-20T03:51:59ZzhoEditorial Department of Advances in Aeronautical Science and EngineeringHangkong gongcheng jinzhan1674-81902025-04-0116212113310.16615/j.cnki.1674-8190.2025.02.1420250214Aero-engine fault diagnosis based on time series anomaly detectionWANG Yinru0AECC Aero Engine Control System Institute, Wuxi 214063, ChinaThe fault diagnosis of aero-engines is confronted with a data skew issue，where the number of fault sam ples is significantly fewer than normal samples，and the fault samples can't adequately represent the entire operating conditions，resulting in poor generalization ability of conventional classification models. To overcome this issue，an improved deep support vector data description-based time series anomaly detection model is proposed. The long short-term memory（LSTM）network is employed to map the inputs and outputs of samples，forming temporal anomaly vectors with actual collected outputs. The deep support vector data description（SVDD）incorporating variational auto-encoder（VAE）is utilized to achieve anomaly detection for aero-engine time series data. The experimental verification is performed with a certain type of aero-engine ground test platform，and the model is com pared to with isolation forest（IF），transformer-based anomaly detection（TranAD）model，and GANomaly. The results show that the curve value calculated with the proposed model can reach to 0.987 8，has superior anomaly detection performance. The proposed model can effectively be applied to various anomaly detection and fault diagnosis tasks in aero-engine systems.http://hkgcjz.cnjournals.com/hkgcjz/article/abstract/2024055anomaly detectionfault diagnosissupport vector data descriptiontime seriesaero-engine |
| spellingShingle | WANG Yinru Aero-engine fault diagnosis based on time series anomaly detection Hangkong gongcheng jinzhan anomaly detection fault diagnosis support vector data description time series aero-engine |
| title | Aero-engine fault diagnosis based on time series anomaly detection |
| title_full | Aero-engine fault diagnosis based on time series anomaly detection |
| title_fullStr | Aero-engine fault diagnosis based on time series anomaly detection |
| title_full_unstemmed | Aero-engine fault diagnosis based on time series anomaly detection |
| title_short | Aero-engine fault diagnosis based on time series anomaly detection |
| title_sort | aero engine fault diagnosis based on time series anomaly detection |
| topic | anomaly detection fault diagnosis support vector data description time series aero-engine |
| url | http://hkgcjz.cnjournals.com/hkgcjz/article/abstract/2024055 |
| work_keys_str_mv | AT wangyinru aeroenginefaultdiagnosisbasedontimeseriesanomalydetection |