A State-Supervised Model and Novel Anomaly Index for Gas Turbines Blade Fault Detection Under Multi-Operating Conditions
To meet industrial demands, gas turbines typically operate under multiple conditions, presenting unique challenges for fault diagnosis. This paper proposes a novel blade fault detection framework designed for such environments. First, a State-Supervised Variational Autoencoder (SS-VAE) model is intr...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10843193/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832586891138957312 |
|---|---|
| author | Yuan Xiao Kun Feng Dongyan Miao Peng Zhang Jiaxin Yang |
| author_facet | Yuan Xiao Kun Feng Dongyan Miao Peng Zhang Jiaxin Yang |
| author_sort | Yuan Xiao |
| collection | DOAJ |
| description | To meet industrial demands, gas turbines typically operate under multiple conditions, presenting unique challenges for fault diagnosis. This paper proposes a novel blade fault detection framework designed for such environments. First, a State-Supervised Variational Autoencoder (SS-VAE) model is introduced, which integrates the learning process of turbine operational states into the VAE bypass, enabling it to capture variations in vibration signal data across different operating conditions. Through the fusion decoding of operating states and vibration signals, the foundation of the SS-VAE model and its loss function is established. Secondly, a new State Mapping Error (SME) index is introduced to further address the issue of reconstruction error variability across multiple conditions. The proposed method is validated through a blade fault test rig and applied in an industrial gas turbine blade fault case. Results demonstrate that the SS-VAE model and SME index effectively capture vibration signal changes due to blade faults across multi-operating conditions, achieving accurate monitoring and diagnosis. Compared to traditional methods, the proposed approach shows higher effectiveness and robustness. |
| format | Article |
| id | doaj-art-d4924ef351e8418cba901bbe4bb1ead1 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-d4924ef351e8418cba901bbe4bb1ead12025-01-25T00:01:37ZengIEEEIEEE Access2169-35362025-01-0113142251423810.1109/ACCESS.2025.352989910843193A State-Supervised Model and Novel Anomaly Index for Gas Turbines Blade Fault Detection Under Multi-Operating ConditionsYuan Xiao0https://orcid.org/0000-0003-1376-5881Kun Feng1Dongyan Miao2Peng Zhang3Jiaxin Yang4State Key Laboratory of High-End Compressor and System Technology, Beijing University of Chemical Technology, Beijing, ChinaState Key Laboratory of High-End Compressor and System Technology, Beijing University of Chemical Technology, Beijing, ChinaState Key Laboratory of High-End Compressor and System Technology, Beijing University of Chemical Technology, Beijing, ChinaState Key Laboratory of High-End Compressor and System Technology, Beijing University of Chemical Technology, Beijing, ChinaState Key Laboratory of High-End Compressor and System Technology, Beijing University of Chemical Technology, Beijing, ChinaTo meet industrial demands, gas turbines typically operate under multiple conditions, presenting unique challenges for fault diagnosis. This paper proposes a novel blade fault detection framework designed for such environments. First, a State-Supervised Variational Autoencoder (SS-VAE) model is introduced, which integrates the learning process of turbine operational states into the VAE bypass, enabling it to capture variations in vibration signal data across different operating conditions. Through the fusion decoding of operating states and vibration signals, the foundation of the SS-VAE model and its loss function is established. Secondly, a new State Mapping Error (SME) index is introduced to further address the issue of reconstruction error variability across multiple conditions. The proposed method is validated through a blade fault test rig and applied in an industrial gas turbine blade fault case. Results demonstrate that the SS-VAE model and SME index effectively capture vibration signal changes due to blade faults across multi-operating conditions, achieving accurate monitoring and diagnosis. Compared to traditional methods, the proposed approach shows higher effectiveness and robustness.https://ieeexplore.ieee.org/document/10843193/Gas turbinebladeanomaly detectionautoencodermulti-operating conditions |
| spellingShingle | Yuan Xiao Kun Feng Dongyan Miao Peng Zhang Jiaxin Yang A State-Supervised Model and Novel Anomaly Index for Gas Turbines Blade Fault Detection Under Multi-Operating Conditions IEEE Access Gas turbine blade anomaly detection autoencoder multi-operating conditions |
| title | A State-Supervised Model and Novel Anomaly Index for Gas Turbines Blade Fault Detection Under Multi-Operating Conditions |
| title_full | A State-Supervised Model and Novel Anomaly Index for Gas Turbines Blade Fault Detection Under Multi-Operating Conditions |
| title_fullStr | A State-Supervised Model and Novel Anomaly Index for Gas Turbines Blade Fault Detection Under Multi-Operating Conditions |
| title_full_unstemmed | A State-Supervised Model and Novel Anomaly Index for Gas Turbines Blade Fault Detection Under Multi-Operating Conditions |
| title_short | A State-Supervised Model and Novel Anomaly Index for Gas Turbines Blade Fault Detection Under Multi-Operating Conditions |
| title_sort | state supervised model and novel anomaly index for gas turbines blade fault detection under multi operating conditions |
| topic | Gas turbine blade anomaly detection autoencoder multi-operating conditions |
| url | https://ieeexplore.ieee.org/document/10843193/ |
| work_keys_str_mv | AT yuanxiao astatesupervisedmodelandnovelanomalyindexforgasturbinesbladefaultdetectionundermultioperatingconditions AT kunfeng astatesupervisedmodelandnovelanomalyindexforgasturbinesbladefaultdetectionundermultioperatingconditions AT dongyanmiao astatesupervisedmodelandnovelanomalyindexforgasturbinesbladefaultdetectionundermultioperatingconditions AT pengzhang astatesupervisedmodelandnovelanomalyindexforgasturbinesbladefaultdetectionundermultioperatingconditions AT jiaxinyang astatesupervisedmodelandnovelanomalyindexforgasturbinesbladefaultdetectionundermultioperatingconditions AT yuanxiao statesupervisedmodelandnovelanomalyindexforgasturbinesbladefaultdetectionundermultioperatingconditions AT kunfeng statesupervisedmodelandnovelanomalyindexforgasturbinesbladefaultdetectionundermultioperatingconditions AT dongyanmiao statesupervisedmodelandnovelanomalyindexforgasturbinesbladefaultdetectionundermultioperatingconditions AT pengzhang statesupervisedmodelandnovelanomalyindexforgasturbinesbladefaultdetectionundermultioperatingconditions AT jiaxinyang statesupervisedmodelandnovelanomalyindexforgasturbinesbladefaultdetectionundermultioperatingconditions |