Intelligent Fault Diagnosis of Liquid Rocket Engine via Interpretable LSTM with Multisensory Data
Fault diagnosis is essential for high energy systems such as liquid rocket engines (LREs) due to harsh thermal and mechanical working environment. In this study, a novel method based on one-dimension Convolutional Neural Network (1D-CNN) and interpretable bidirectional Long Short-term Memory (LSTM)...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/12/5636 |
| _version_ | 1797592615903821824 |
|---|---|
| author | Xiaoguang Zhang Xuanhao Hua Junjie Zhu Meng Ma |
| author_facet | Xiaoguang Zhang Xuanhao Hua Junjie Zhu Meng Ma |
| author_sort | Xiaoguang Zhang |
| collection | DOAJ |
| description | Fault diagnosis is essential for high energy systems such as liquid rocket engines (LREs) due to harsh thermal and mechanical working environment. In this study, a novel method based on one-dimension Convolutional Neural Network (1D-CNN) and interpretable bidirectional Long Short-term Memory (LSTM) is proposed for intelligent fault diagnosis of LREs. 1D-CNN is responsible for extracting sequential signals collected from multi sensors. Then the interpretable LSTM is developed to model the extracted features, which contributes to modeling the temporal information. The proposed method was executed for fault diagnosis using the simulated measurement data of the LRE mathematical model. The results demonstrate the proposed algorithm outperforms other methods in terms of accuracy of fault diagnosis. Through experimental verification, the method proposed in this paper was compared with CNN, 1DCNN-SVM and CNN-LSTM in terms of LRE startup transient fault recognition performance. The model proposed in this paper had the highest fault recognition accuracy (97.39%). |
| first_indexed | 2024-03-11T01:56:39Z |
| format | Article |
| id | doaj.art-0d89b1feab9d4b408a1427ed83fa568f |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T01:56:39Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0d89b1feab9d4b408a1427ed83fa568f2023-11-18T12:33:56ZengMDPI AGSensors1424-82202023-06-012312563610.3390/s23125636Intelligent Fault Diagnosis of Liquid Rocket Engine via Interpretable LSTM with Multisensory DataXiaoguang Zhang0Xuanhao Hua1Junjie Zhu2Meng Ma3Xi’an Aerospace Propulsion Institute, Xi’an 710100, ChinaSchool of Future Technology, Xi’an Jiaotong University, Xi’an 710049, ChinaSchool of Mechanical Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaSchool of Mechanical Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaFault diagnosis is essential for high energy systems such as liquid rocket engines (LREs) due to harsh thermal and mechanical working environment. In this study, a novel method based on one-dimension Convolutional Neural Network (1D-CNN) and interpretable bidirectional Long Short-term Memory (LSTM) is proposed for intelligent fault diagnosis of LREs. 1D-CNN is responsible for extracting sequential signals collected from multi sensors. Then the interpretable LSTM is developed to model the extracted features, which contributes to modeling the temporal information. The proposed method was executed for fault diagnosis using the simulated measurement data of the LRE mathematical model. The results demonstrate the proposed algorithm outperforms other methods in terms of accuracy of fault diagnosis. Through experimental verification, the method proposed in this paper was compared with CNN, 1DCNN-SVM and CNN-LSTM in terms of LRE startup transient fault recognition performance. The model proposed in this paper had the highest fault recognition accuracy (97.39%).https://www.mdpi.com/1424-8220/23/12/5636interpretablebidirectional LSTMdata fusionfault simulation |
| spellingShingle | Xiaoguang Zhang Xuanhao Hua Junjie Zhu Meng Ma Intelligent Fault Diagnosis of Liquid Rocket Engine via Interpretable LSTM with Multisensory Data Sensors interpretable bidirectional LSTM data fusion fault simulation |
| title | Intelligent Fault Diagnosis of Liquid Rocket Engine via Interpretable LSTM with Multisensory Data |
| title_full | Intelligent Fault Diagnosis of Liquid Rocket Engine via Interpretable LSTM with Multisensory Data |
| title_fullStr | Intelligent Fault Diagnosis of Liquid Rocket Engine via Interpretable LSTM with Multisensory Data |
| title_full_unstemmed | Intelligent Fault Diagnosis of Liquid Rocket Engine via Interpretable LSTM with Multisensory Data |
| title_short | Intelligent Fault Diagnosis of Liquid Rocket Engine via Interpretable LSTM with Multisensory Data |
| title_sort | intelligent fault diagnosis of liquid rocket engine via interpretable lstm with multisensory data |
| topic | interpretable bidirectional LSTM data fusion fault simulation |
| url | https://www.mdpi.com/1424-8220/23/12/5636 |
| work_keys_str_mv | AT xiaoguangzhang intelligentfaultdiagnosisofliquidrocketengineviainterpretablelstmwithmultisensorydata AT xuanhaohua intelligentfaultdiagnosisofliquidrocketengineviainterpretablelstmwithmultisensorydata AT junjiezhu intelligentfaultdiagnosisofliquidrocketengineviainterpretablelstmwithmultisensorydata AT mengma intelligentfaultdiagnosisofliquidrocketengineviainterpretablelstmwithmultisensorydata |