基于MAML-LSTM的服役涡轮叶片损伤状态评估方法

doi:10.7527/S1000-6893.2024.29547

Abstract

Abstract:

Accurately evaluating the damage state of turbine blades is of great significance for guiding their overhaul / replacement behavior. However， due to the complexity of turbine blade structure and service environment， it is difficult for existing technical means to simulate the blade damage under real service conditions， and the damage prediction based on the damage data of real service blades has the objective limitation of high data acquisition cost and few samples. Therefore， a damage parameter prediction method based on meta-learning is proposed to evaluate the damage state of turbine blades in service under small sample conditions. Based on the limited service data， the damage parameters of turbine blades are predicted. Firstly， the slice samples of different blade heights of turbine blades were prepared， and the microscopic images of typical parts of the slice samples were obtained by field emission scanning electron microscopy. The image processing technology was used to extract the damage data of different parts， and the damage data were divided into different training task data according to the different parts of the picture. Then， a prediction method of turbine blade damage parameters based on MAML-LSTM is proposed. Meta-learning is carried out on the basis of different training tasks， which enhances the correlation between service conditions and blade damage parameters， establishes an effective mapping between service parameters and damage parameters， and realizes the prediction of turbine blade damage parameters. Finally， the MAML-LSTM model proposed in this paper is used to predict the test set data. The average absolute percentage error of the prediction results is 7.55%. Compared with the prediction results of BP， RNN， LSTM， Bi-LSTM and other neural networks， the average absolute error of the model proposed in this paper on the test set is reduced by at least 52.37%， and the mean square error is reduced by at least 76.98%.

Key words: meta-learning, damage prediction, turbine blade, neural network, small sample, microstructure damage

CLC Number:

V232.4

Weiqing HUANG, Ning LI, Kailin LIU, Zhizhong FU, Pengfei JI, Shengliang ZHANG, Liwei DONG, Yantao SUN. Damage state evaluation method of service turbine blades based on MAML-LSTM[J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(18): 429547.

Figures/Tables 15

Table 1

Fig.1

Fig.2

Table 2

Fig.3

Fig.4

Fig.5

Fig.6

Table 3

Fig.7

Fig.8

Table 4

Fig.9

Fig.10

Table 5

References 23

1	冯强，童锦艳，郑运荣，等. 燃气涡轮叶片的服役损伤与修复［J］. 中国材料进展， 2012， 31（12）： 21-34.
	FENG Q， TONG J Y， ZHENG Y R， et al. Service induced degradation and rejuvenation of gas turbine blades［J］. Materials China， 2012， 31（12）： 21-34 （in Chinese）.
2	LI D W， LIU J X， SUN Y T， et al. Microstructure and mechanical degradation of K403 Ni-based superalloy from ultra-long-term serviced turbine blade［J］. Journal of Alloys and Compounds， 2023， 957： 170378.
3	陈操，韩雷，张钰，等. 镍基合金涡轮叶片的服役损伤机理与性能衰减［J］. 航空材料学报， 2021， 41（4）： 96-108.
	CHEN C， HAN L， ZHANG Y， et al. Service damage mechanism and performance attenuation of nickel-based alloy turbine blades［J］. Journal of Aeronautical Materials， 2021， 41（4）： 96-108 （in Chinese）.
4	ACHARYA M V， FUCHS G E. The effect of long-term thermal exposures on the microstructure and properties of CMSX-10 single crystal Ni-base superalloys［J］. Materials Science and Engineering： A， 2004， 381（1-2）： 143-153.
5	HAN L， LI P， YU S， et al. Creep/fatigue accelerated failure of Ni-based superalloy turbine blade： Microscopic characteristics and void migration mechanism［J］. International Journal of Fatigue， 2022， 154： 106558.
6	范永升，杨晓光，石多奇，等. 服役涡轮叶片筏化判废：定量表征及阈值确定［J］. 航空学报， 2022， 43（9）： 625100.
	FAN Y S， YANG X G， SHI D Q， et al. Rafting-waste judgement od serviced turbine blades： quantitative characterization and threshold determination［J］. Acta Aeronautica et Astronautica Sinica， 2022， 43（9）： 625100 （in Chinese）.
7	ELLIS B， HEYNS P S， SCHMIDT S. A hybrid framework for remaining useful life estimation of turbomachine rotor blades［J］. Mechanical Systems and Signal Processing， 2022， 170： 108805.
8	雷世英，孙见忠，刘赫. 涡轮叶片累积损伤指数模型及服役可靠性评估［J］. 航空学报， 2022， 43（3）： 225064.
	LEI S Y， SUN J Z， LIU H. Cumulative damage index model and service reliability evaluation of turbine blade［J］. Acta Aeronautica et Astronautica Sinica， 2022， 43（3）： 225064 （in Chinese）.
9	WANG J， ZHANG J， ZHAO W， et al. Lifetime prediction of turbine blade of turbocharger for diesel engine based on fatigue and creep damage model［C］∥2021 Global Reliability and Prognostics and Health Management. 2021： 1-5.
10	车畅畅，王华伟，倪晓梅，等. 基于1D-CNN和Bi-LSTM的航空发动机剩余寿命预测［J］. 机械工程学报， 2021， 57（14）： 304-312.
	CHE C C， WANG H W， NI X M， et al. Residual life prediction of aeroengine based on 1D-CNN and Bi-LSTM［J］. Journal of Mechanical Engineering， 2021， 57（14）： 304-312 （in Chinese）.
11	QUINTANAR-GAGO D A， NELSON P F， DÍAZ-SÁNCHEZ Á， et al. Assessment of steam turbine blade failure and damage mechanisms using a Bayesian network［J］. Reliability Engineering & System Safety， 2021， 207： 107329.
12	QATTAN N A， AL-BAHI A M， KADA B. ANN-based failure modeling of T-56 engine turbine［C］∥2023 Annual Reliability and Maintainability Symposium. 2023： 23-26.
13	LIU H， SUN J， LEI S， et al. In-service aircraft engines turbine blades life prediction based on multi-modal operation and maintenance data［J］. Propulsion and Power Research， 2021， 10（4）： 360-373.
14	FINN C， ABBEEL P， LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks［DB/OL］. arXiv preprint： 1703.03400， 2017.
15	ANDRYCHOWICZ M， DENIL M， GOMEZ S， et al. Learning to learn by gradient descent by gradient descent［DB/OL］. arXiv preprent： 1606.04474， 2016.
16	HOUTHOOFT R， CHEN R Y， ISOLA P， et al. Evolved policy gradients［DB/OL］. arXiv preprint： 1802.04821， 2018.
17	SUNG F， YANG Y， ZHANG L， et al. Learning to compare： Relation network for few-shot learning［C］∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018： 18-23.
18	RUSU A， RAO D， SYGNOWSKI J， et al. Meta-learning with latent embedding optimization［DB/OL］. arXiv preprint： 1807.05960， 2019.
19	周登极，张会生，苏明. 一种燃气轮机涡轮叶片蠕变损伤评估模型及其应用［J］. 动力工程学报， 2015， 35（12）： 964-969.
	ZHOU D J， ZHANG H S， SU M. An evaluation model for the creep damage of gas turbine blades and its application［J］. Journal of Chinese Society of Power Engineering， 2015， 35（12）： 964-969 （in Chinese）.
20	CHOI J Y， LEE B. Combining LSTM network ensemble via adaptive weighting for improved time series forecasting［J］. Mathematical Problems in Engineering， 2018， 2018： 2470171.
21	黄炎，葛思源，翟慕赛，等. 环境温度影响下基于LSTM神经网络识别结构损伤［J］. 计算力学学报， 2024， 41（2）： 248-255.
	HUANG Y， GE S Y， ZHAI M S， et al. Structural damage identification based on LSTM neural networks under ambient temperature variations［J］. Chinese Journal of Computational Mechanics， 2024， 41（2）： 248-255 （in Chinese）.
22	CHOE D， KIM H， KIM M. Sequence-based modeling of deep learning with LSTM and GRU networks for structural damage detection of floating offshore wind turbine blades［J］. Renewable Energy， 2021，174： 218-235.
23	GREFF K， SRIVASTAVA R K， KOUTNIK J， et al. LSTM： A search space odyssey［J］. IEEE Transactions on Neural Networks and Learning Systems， 2017， 28（10）： 2222-2232.

位置	前沿	尾沿	叶盆	叶背
叶根	Ⅰ	Ⅱ	Ⅲ	Ⅳ
60%叶高	Ⅴ	Ⅵ	Ⅶ	Ⅷ
叶尖	Ⅸ	Ⅹ	Ⅺ	Ⅻ

模型	MAE	MSE
BP	0.071 0	0.008 82
RNN	0.073 3	0.009 29
LSTM	0.071 9	0.008 08
Bi-LSTM	0.069 3	0.007 98
MAML-LSTM	0.036 3	0.001 84

[1]	Fei MA, Qiong ZHANG, Peijun LAI, Yidi YUE. BP neural network⁃based quantitative classification model for safety in experimental flight training [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(5): 529957-529957.
[2]	Yude NI, Miaoyu YAN, Ruihua LIU. Short-term prediction of ionospheric TEC based on DOA-BP neural network [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(4): 328707-328707.
[3]	Yonggang CHEN, Kangni LIU, Shuai WANG. Fault knowledge graph construction for aviation equipment based on BiGRU⁃Attention improvement [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(18): 229916-229916.
[4]	Hui LI, Yinchao CHEN, Shaoshan SUN, Zhaoxin LIANG, Gang MAO, Bin QIAO, Yongbo LI. Fault diagnosis method of rotor system based on federated graph network [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(17): 530611-530611.
[5]	Yuanhao HU, Yibo SONG, Jiahui LIU, Xiaoli ZHAO, Wenxiang DENG, Jian HU, Jianyong YAO. Fault diagnosis of electro-hydraulic proportional servo valves based on attention convolutional capsule networks [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(15): 630407-630407.
[6]	Jiajun LONG, Chenpiao LIU, Fei QIN, Jiale ZHANG, Shengguan XU, Yisheng GAO. Liutex based data-driven turbulence model correction [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(15): 129579-129579.
[7]	Yanfang LIU, Jiayu SHE, Qiufan YUAN, Rui ZHOU, Naiming QI. Real⁃time small target detection networks for UAV remote sensing [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(14): 630119-630119.
[8]	Wentao LI, Yunqin HE, Wenbo LI, Yiyi ZHANG, Guozhu LIANG. 3D grain reverse design and shape optimization for solid rocket motor [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(11): 529089-529089.
[9]	Zhongzhi LI, Jinyi MA, Jianliang AI, Yiqun DONG. Fault detection and classification of aerospace sensors using deep neural networks finetuned from VGG16 [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(S1): 727615-727615.
[10]	Wu LIU, Yunyan WU, Wei LIU, Mingming TIAN, Tianpeng HUANG. Re-entry robust fault tolerant attitude control for RLVs considering unknown disturbances [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(S1): 727787-727787.
[11]	Chenyang LIU, Dawei WU, Yize GUO, Xinsai LV, Jiani ZHOU, Shuyi SHAO. Robust adaptive attitude control of quadrotor with uncertain strong coupling [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(S1): 727645-727645.
[12]	Zhikai WANG, Sheng CHEN, Wei FAN. Effect of neural network width on combustor emission prediction [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(5): 126816-126816.
[13]	Lei HE, Weiqi QIAN, Kangsheng DONG, Xian YI, Congcong CHAI. Aerodynamic characteristics modeling of iced airfoil based on convolution neural networks [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(5): 126434-126434.
[14]	Honglun WANG, Yanxiang WANG, Yiheng LIU. Recovery trajectory optimization for UAV towed aerial recovery based on trajectory mapping [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(20): 628775-628775.
[15]	Xiangwei ZHU, Dan SHEN, Kai XIAO, Yuexin MA, Xiang LIAO, Fuqiang GU, Fangwen YU, Kefu GAO, Jingnan LIU. Mechanisms, algorithms, implementation and perspectives of brain⁃inspired navigation [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(19): 28569-028569.

Damage state evaluation method of service turbine blades based on MAML-LSTM

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 15

References 23

Related Articles 15

Recommended Articles 0

Metrics

Comments