| Citation: | ZHANG Zhenliang, BI Junxi, HE Rongrong, et al. Health management method of helicopter turbine engine based on Caps-BiGRU-Attention[J]. Journal of Aerospace Power, 2026, 41（6）：20240775 doi: 10.13224/j.cnki.jasp.20240775
|
In response to the issues of difficulties in identifying faults and quantifying the health status of helicopter turbo engines, a Caps-BiGRU-Attention model based on the attention mechanism for fault mode recognition and torque margin prediction of turbo engines was proposed. The model consisted of three main components: capsule layer used to capture the intrinsic relationships of the input data, bidirectional gated recurrent unit (BiGRU) layer used to extract time series features and outputs results, and the squeeze-and-excitation attention mechanism (SE) used to weight the features to highlight important information. Experimental validation on a helicopter turbo engine dataset demonstrated that the model achieved an accuracy exceeding 99.7% in fault diagnosis and reduced the mean absolute error in torque margin prediction to 0.027. Additionally, feature analysis was conducted during the diagnosis and prediction processes to identify favorable ranges of feature values for the engine’s health status. Finally, probability distribution fitting was performed on the distribution of torque margin, determining that the optimal distributions for severe failure, minor failure, and healthy states of the engine were Beta distributions.
| [1] |
侯波, 徐冠峰, 闫慧娟, 等. 某型直升机主桨叶大梁断裂故障分析[J]. 航空动力学报, 2023, 38(6): 1489-1495. HOU Bo, XU Guanfeng, YAN Huijuan, et al. Fracture fault analysis of main blades girder on a helicopter[J]. Journal of Aerospace Power, 2023, 38(6): 1489-1495. (in Chinese doi: 10.13224/j.cnki.jasp.20220933
HOU Bo, XU Guanfeng, YAN Huijuan, et al. Fracture fault analysis of main blades girder on a helicopter[J]. Journal of Aerospace Power, 2023, 38(6): 1489-1495. (in Chinese) doi: 10.13224/j.cnki.jasp.20220933
|
| [2] |
LEONI J, TANELLI M, PALMAN A. A new comprehensive monitoring and diagnostic approach for early detection of mechanical degradation in helicopter transmission systems[J]. Expert Systems with Applications, 2022, 210: 118412. doi: 10.1016/j.eswa.2022.118412
|
| [3] |
MIRONOV A, DORONKIN P. The demonstrator of structural health monitoring system of helicopter composite blades[J]. Procedia Structural Integrity, 2022, 37: 241-249. doi: 10.1016/j.prostr.2022.01.080
|
| [4] |
万安平, 龚志鹏, 王景霖, 等. 多工况直升机附件齿轮箱振动故障诊断[J]. 振动、测试与诊断, 2024, 44(2): 246-252. WAN Anping, GONG Zhipeng, WANG Jinglin, et al. Vibration fault diagnosis of helicopter accessory gearbox under multi-operating conditions[J]. Journal of Vibration, Measurement & Diagnosis, 2024, 44(2): 246-252. (in Chinese
WAN Anping, GONG Zhipeng, WANG Jinglin, et al. Vibration fault diagnosis of helicopter accessory gearbox under multi-operating conditions[J]. Journal of Vibration, Measurement & Diagnosis, 2024, 44(2): 246-252. (in Chinese)
|
| [5] |
SUN Kuangchi, YIN Aijun, LU S. Domain distribution variation learning via adversarial adaption for helicopter transmission system fault diagnosis[J]. Mechanical Systems and Signal Processing, 2024, 215: 111419. doi: 10.1016/j.ymssp.2024.111419
|
| [6] |
MIRONOV A, DORONKIN P, PRIKLONSKY A, et al. The role of advanced technologies of vibration diagnostics to provide efficiency of helicopter life cycle[J]. Procedia Engineering, 2017, 178: 96-106. doi: 10.1016/j.proeng.2017.01.070
|
| [7] |
OUYANG Lei, JIN Ningde, BAI Landi, et al. Soft measurement of oil-water two-phase flow using a multi-task sequence-based CapsNet[J]. ISA Transactions, 2023, 137: 629-645. doi: 10.1016/j.isatra.2022.12.007
|
| [8] |
MOUDGIL A, SINGH S, RANI S, et al. Deep learning for ancient scripts recognition: a CapsNet-LSTM based approach[J]. Alexandria Engineering Journal, 2024, 103: 169-179. doi: 10.1016/j.aej.2024.06.007
|
| [9] |
LI Xingqiu, JIANG Hongkai, LIU Yuan, et al. An integrated deep multiscale feature fusion network for aeroengine remaining useful life prediction with multisensor data[J]. Knowledge-Based Systems, 2022, 235: 107652. doi: 10.1016/j.knosys.2021.107652
|
| [10] |
LYU Fen, LIU Junping, CHEN Li, et al. 3D in-situ stress prediction for shale reservoirs based on the CapsNet-BiLSTM hybrid model[J]. International Journal of Rock Mechanics and Mining Sciences, 2024, 183: 105937. doi: 10.1016/j.ijrmms.2024.105937
|
| [11] |
NIZARUDEEN S, SHANMUGHAVEL G R. Comparative analysis of ResNet, ResNet-SE, and attention-based RaNet for hemorrhage classification in CT images using deep learning[J]. Biomedical Signal Processing and Control, 2024, 88: 105672. doi: 10.1016/j.bspc.2023.105672
|
| [12] |
管智峰. 基于特征优选和ESPBO-HKELM的变压器故障诊断研究[D]. 阜新: 辽宁工程技术大学, 2023. GUAN Zhifeng. Research on transformer fault diagnosis based on feature selection and ESPBO-HKELM[D]. Fuxin: Liaoning Technical University, 2023. (in Chinese
GUAN Zhifeng. Research on transformer fault diagnosis based on feature selection and ESPBO-HKELM[D]. Fuxin: Liaoning Technical University, 2023. (in Chinese)
|
| [13] |
WEN Haijia, LIU Bo, DI Mingrui, et al. A SHAP-enhanced XGBoost model for interpretable prediction of coseismic landslides[J]. Advances in Space Research, 2024, 74(8): 3826-3854. doi: 10.1016/j.asr.2024.07.013
|
| [14] |
LU Yonghui, TANG Liqun, LIU Zejia, et al. Unsupervised quantitative structural damage identification method based on BiLSTM networks and probability distribution model[J]. Journal of Sound and Vibration, 2024, 590: 118597. doi: 10.1016/j.jsv.2024.118597
|
| [15] |
张雄, 张逸轩, 张明, 等. 基于小波包散布熵与Meanshift概率密度估计的轴承故障识别方法研究[J]. 湖南大学学报(自然科学版), 2021, 48(8): 133-140. ZHANG Xiong, ZHANG Yixuan, ZHANG Ming, et al. Research on bearing fault identification method based on wavelet packet dispersion entropy and meanshift probability density estimation[J]. Journal of Hunan University (Natural Sciences), 2021, 48(8): 133-140. (in Chinese doi: 10.16339/j.cnki.hdxbzkb.2021.08.017
ZHANG Xiong, ZHANG Yixuan, ZHANG Ming, et al. Research on bearing fault identification method based on wavelet packet dispersion entropy and meanshift probability density estimation[J]. Journal of Hunan University (Natural Sciences), 2021, 48(8): 133-140. (in Chinese) doi: 10.16339/j.cnki.hdxbzkb.2021.08.017
|
| [16] |
ZHANG Guangyao, WANG Yi, LI Xiaomeng, et al. Health indicator based on signal probability distribution measures for machinery condition monitoring[J]. Mechanical Systems and Signal Processing, 2023, 198: 110460. doi: 10.1016/j.ymssp.2023.110460
|
| [17] |
ZHANG Senhao, LIANG Weihe, ZHAO Wanzhong, et al. Electro-hydraulic SBW fault diagnosis method based on novel 1DCNN-LSTM with attention mechanisms and transfer learning[J]. Mechanical Systems and Signal Processing, 2024, 220: 111644. doi: 10.1016/j.ymssp.2024.111644
|
| [18] |
CHEN Ran, SHEN Hao, ZHAO Zhongqiu, et al. Global routing between capsules[J]. Pattern Recognition, 2024, 148: 110142. doi: 10.1016/j.patcog.2023.110142
|
| [19] |
ZHANG Tingting, JIA Jihua, CHEN Cheng, et al. BiGRUD-SA: Protein S-sulfenylation sites prediction based on BiGRU and self-attention[J]. Computers in Biology and Medicine, 2023, 163: 107145. doi: 10.1016/j.compbiomed.2023.107145
|
| [20] |
SAAD SHAKEEL M. CAAM: a calibrated augmented attention module for masked face recognition[J]. Journal of Visual Communication and Image Representation, 2024, 104: 104315. doi: 10.1016/j.jvcir.2024.104315
|
| [21] |
ZHOU Gaoyu, HU Guofeng, ZHANG Daxing, et al. A novel algorithm system for wind power prediction based on RANSAC data screening and Seq2Seq-Attention-BiGRU model[J]. Energy, 2023, 283: 128986. doi: 10.1016/j.energy.2023.128986
|
| [22] |
YE Meng, LI Lifeng, YOO D Y, et al. Prediction of shear strength in UHPC beams using machine learning-based models and SHAP interpretation[J]. Construction and Building Materials, 2023, 408: 133752. doi: 10.1016/j.conbuildmat.2023.133752
|
| [23] |
KASHIFI M T. Investigating two-wheelers risk factors for severe crashes using an interpretable machine learning approach and SHAP analysis[J]. IATSS Research, 2023, 47(3): 357-371. doi: 10.1016/j.iatssr.2023.07.005
|
| [24] |
SERAFINI J, BERNARDINI G, PORCELLI R, et al. In-flight health monitoring of helicopter blades via differential analysis[J]. Aerospace Science and Technology, 2019, 88: 436-443. doi: 10.1016/j.ast.2019.03.039
|
| [25] |
LIN Zhicheng, CAI Yongxiang, LIU Wei, et al. Estimating the state of health of lithium-ion batteries based on a probability density function[J]. International Journal of Electrochemical Science, 2023, 18(6): 100137. doi: 10.1016/j.ijoes.2023.100137
|
| [26] |
吴涵, 袁越, 侯语涵, 等. 配电网理论线损概率分布函数的计算与分析[J]. 中国电机工程学报, 2024, 44(16): 6444-6454. WU Han, YUAN Yue, HOU Yuhan, et al. Computation and analysis of theoretic line loss probability distribution function of distribution network[J]. Proceedings of the CSEE, 2024, 44(16): 6444-6454. (in Chinese doi: 10.13334/j.0258-8013.pcsee.230061
WU Han, YUAN Yue, HOU Yuhan, et al. Computation and analysis of theoretic line loss probability distribution function of distribution network[J]. Proceedings of the CSEE, 2024, 44(16): 6444-6454. (in Chinese) doi: 10.13334/j.0258-8013.pcsee.230061
|
DownLoad:
