基于性能数字孪生的航空发动机性能衰退实时监测与评估方法

王栋欢; 金海; 万东凯; 王军; 肖洪

doi:10.7527/S1000-6893.2025.32459

航空学报 >

0 1 - 0

DOI: https://doi.org/10.7527/S1000-6893.2025.32459

基于性能数字孪生的航空发动机性能衰退实时监测与评估方法

王栋欢 ,
金海 ,
万东凯 ,
王军 ,
肖洪

展开

1. 西北工业大学
2. 中国航发沈阳发动机研究所
3. 西北工业大学动力与能源学院

收稿日期: 2025-06-23

修回日期: 2025-09-15

网络出版日期: 2025-09-18

收起

Real-Time Monitoring and Evaluation Method for Aero-Engine Performance Degradation Based on Performance Digital Twin

WANG Dong-Huan ,
JIN Hai ,
WAN Dong-Kai ,
WANG Jun ,
XIAO Hong

Expand

Received date: 2025-06-23

Revised date: 2025-09-15

Online published: 2025-09-18

Fold

摘要

为实现航空发动机实时性能监测及衰退评估，提出了一种基于性能数字孪生的航空发动机性能衰退实时监测与评估方法。基于长短期记忆循环神经网络（LSTM）并结合发动机物理实体结构设计，搭建性能数字孪生模型架构，利用某发动机初始飞行架次飞参数据构建性能数字孪生基线模型。模型能够高精度模拟未衰退发动机在不同飞行工况下的性能。通过将发动机实时工况和飞行状态参数输入至基线模型，模拟未衰退发动机在当前运行工况下的实时性能。模拟结果与实际传感器数据对比，即可评估发动机当前性能衰退情况。在185架次飞行案例中，使用前3架次飞参数据构建基线模型并进行精度验证。结果显示模型对转速、压力、温度的预测平均绝对相对误差低于0.98%、0.94%、1.89%，单点预测时间不大于0.14ms，基线模型对发动机性能的实时孪生可靠。该方法的衰退评估结果与传统方法吻合良好，展现了显著的可行性和优势。

关键词： 航空发动机; 数字孪生; 性能监测; 衰退评估; LSTM; 架构驱动

本文引用格式

王栋欢 , 金海 , 万东凯 , 王军 , 肖洪 . 基于性能数字孪生的航空发动机性能衰退实时监测与评估方法[J]. 航空学报, 0 : 1 -0 . DOI: 10.7527/S1000-6893.2025.32459

Abstract

To enable real-time performance monitoring and degradation assessment of aircraft engines, a digital twin-based methodology for real-time evaluation of engine performance degradation is proposed. A performance digital twin architecture was designed and implemented by integrating Long Short-Term Memory (LSTM) recurrent neural networks with the engine’s physical structural configuration. Base-line models of the performance digital twin were established using flight parameter data from the initial operational flights of an engine. The model demonstrates high-fidelity simulation capabilities for replicating the engine’s performance across diverse flight conditions. By feeding real-time operational parameters and flight state data into the baseline model, the real-time performance metrics of a pristine (non-degraded) engine under current operating conditions are simulated. Comparative analysis between simulated outputs and actual sensor measurements enables quantitative assessment of the engine’s instantaneous performance degradation. A case study involving 185 flight cycles validated the framework: Baseline models constructed from the first three flights achieved mean absolute relative errors below 0.98%, 0.94%, and 1.89% for rotational speed, pressure, and temperature predictions, respectively, with single-point inference times under 0.14 milliseconds, confirming the reliability of real-time digital twinning. The degradation assessment results of this method align well with traditional methods, demonstrating significant feasibility and advantages.

Key words： Aero-engine; Digital Twin; Performance Monitoring; Degradation Assessment; LSTM; Architecture-Driven

参考文献

[1] Abu Salem K, Palaia G, Bravo-Mosquera P D, et al.A review of novel and non-conventional propulsion integrations for next-generation aircraft[J]. Designs, 2024, 8(2): 20.
[2] Chen Q, Sheng H, Li J, et al. Model-based improved advanced adaptive performance recovery control method for a commercial turbofan engine[J]. IEEE Transactions on Aerospace and Electronic Systems, 2023, 59(6): 7440-7454.
[3] Kordestani M, Orchard M E, Khorasani K, et al. An overview of the state of the art in aircraft prognostic and health management strategies[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-15.
[4] 赵洪利, 张猛. 基于随机维纳过程的航空发动机性能衰退研究[J]. 推进技术, 2021, 42(3): 488.
ZHAO Hong-li，ZHANG Meng. Performance Degradation of Aeroengines Based on Stochastic Wiener Process[J]. Journal of Propulsion Technology，2021，42（3）：488-494.
[5] M. G. De Giorgi, N. Menga, A. Ficarella, Exploring prognostic and diagnostic techniques for jet engine health monitoring: A review of degradation mechanisms and advanced prediction strategies, Energies 16 (2023) 2711.
[6] Q. Chen, H. Sheng, T. Zhang, A novel direct performance adaptive control of aero-engine using subspace-based improved model predictive control, Aerospace Science and Technology 128 (2022) 107760
[7] 曹明，王鹏，左洪福，等．民用航空发动机故障诊断与健康管理现状、挑战与机遇Ⅱ：地面综合诊断、寿命管理和智能维护维修决策 [J]．航空学报，2022, 43(9): 625574.
CAO M, WANG P, ZUO H F, et all. Current status, challenges and opportunitites of civil aero-engine diagnostics & health management II: Comprehensive off-board diagnosis, life management and intelligent condition based MRO [J]. Acta Aeronautica et Astronautica Sinica,2022,43(9):625574(in Chinese). doi:10.7524/S1000-6893.2021.25574
[8] Fentaye A D, Zaccaria V, Kyprianidis K. Aircraft engine performance monitoring and diagnostics based on deep convolutional neural networks[J]. Machines, 2021, 9(12): 337.
[9] Rath N, Mishra R K, Kushari A. Aero engine health monitoring, diagnostics and prognostics for condition-based maintenance: An overview[J]. International journal of turbo & jet-engines, 2024, 40(s1): s279-s292.
[10] 陶飞, 孙清超, 孙惠斌, 等. 航空发动机数字孪生工程: 内涵与关键技术[J]. 航空学报, 2024, 45（21）: 630283．
TAO F, SUN Q C, SUN H B, et al. Aero-engine digital twin engineering: Connotation and key technologies [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45（21）: 630283（in Chinese）. doi: 10. 7527/S1000-6893. 2024. 30283.
[11] A. J. Volponi, R. Rajamani, Hybrid models for engine health management, Machine Learning and Knowledge Discovery for Engineering Systems Health Management (2012) 395–422.
[12] S. Kim, K. Kim, C. Son, Transient system simulation for an aircraft engine using a data-driven model, Energy 196 (2020) 117046.
[13] 董威，尹家录，郑培英，等. 航空发动机及燃气轮机整机性能仿真综述[J]. 航空发动机，2023，49（5）：8-21.
DONG Wei，YIN Jialu，ZHENG Peiying，et al. Review: engine-level performance simulation of aeroengine and gas turbines[J]. Aeroengine，2023，49（5）：8-21.
[14] S. Pang, Q. Li, H. Feng, A hybrid onboard adaptive model for aero-engine parameter prediction, Aerospace Science and Technology 105 (2020) 105951.
[15] A. González-Mu?iz, I. Diaz, A. A. Cuadrado, D. García-Pérez, Health indicator for machine condition monitoring built in the latent space of a deep autoencoder, Reliability Engineering & System Safety 224 (2022) 108482.
[16] Xinglong ZHANG;Zhonglin LIN;Runmin JI;Tianhong ZHANG. Deep reinforcement learning based active surge control for aeroengine compressors [J]. Chinese Journal of Aeronautics, 2024, 37(7): 418–438.
[17] 马博文, 巫骁雄, 于洋. 基于机器学习方法的压气机落后角与总压损失预测代理模型[J]. 航空动力学报, 2023, 38（7）：1675-1690 doi: 10.13224/j.cnki.jasp.20220749
MA Bowen, WU Xiaoxiong, YU Yang. Surrogate model for deviation angle and total pressure loss prediction of compressor based on machine learning methods[J]. Journal of Aerospace Power, 2023, 38（7）：1675-1690 doi: 10.13224/j.cnki.jasp.20220749
[18] 蔡舒妤,殷航,史涛,等.基于ResNet-LSTM的航空发动机性能异常检测方法[J]. 航空发动机, 2024, 50（1）:135-142.
CAI Shuyu,YIN Hang,SHI Tao,et al.Aero-engine performance anomaly detection method based on ResNet-LSTM[J]. Aeroengine, 2024, 50（1）:135-142.
[19] K. Zhao, Z. Jia, F. Jia, H. Shao, Multi-scale integrated deep self-attention network for predicting remaining useful life of aero-engine, Engineering Applications of Artificial Intelligence 120 (2023) 105860.
[20] L. Zhou, H. Wang, S. Xu, Aero-engine prognosis strategy based on multi-scale feature fusion and multi-task parallel learning, Reliability Engineering & System Safety 234 (2023) 109182.
[21] I. de Pater, A. Reijns, M. Mitici, Alarm-based predictive maintenance scheduling for aircraft engines with imperfect remaining useful life prognostics, Reliability Engineering & System Safety 221 (2022) 108341.
[22] I. de Pater, M. Mitici, Developing health indicators and rul prognostics for systems with few failure instances and varying operating conditions using a lstm autoencoder, Engineering Applications of Artificial Intelligence 117 (2023) 105582.
[23] Y. Huang, J. Tao, G. Sun, H. Zhang, Y. Hu, A prognostic and health management framework for aero-engines based on a dynamic probability model and lstm network, Aerospace 9 (2022) 316.
[24] Y. Zhang, Y. Xin, Z.-w. Liu, M. Chi, G. Ma, Health status assessment and remaining useful life prediction of aero-engine based on bigru and mmoe, Reliability Engineering & System Safety 220 (2022) 108263.
[25] M. G. De Giorgi, L. Strafella, N. Menga, A. Ficarella, Intelligent combined neural network and kernel principal component analysis tool for engine health monitoring purposes, Aerospace 9 (2022) 118.
[26] F. Lu, J. Wu, J. Huang, X. Qiu, Aircraft engine degradation prognostics based on logistic regression and novel os-elm algorithm, Aerospace Science and Technology 84 (2019) 661–671.
[27] Z. Li, D. Wu, C. Hu, J. Terpenny, An ensemble learning-based prognostic approach with degradation-dependent weights for remaining useful life prediction, Reliability Engineering & System Safety 184 (2019) 110–122.
[28] G. Protopapadakis, A. Apostolidis, A. I. Kalfas, Explainable and interpretable ai-assisted remaining useful life estimation for aeroengines, in: Turbo Expo: Power for Land, Sea, and Air, volume 85987, American Society of Mechanical Engineers, 2022, p. V002T05A002.
[29] Y. Huang, J. Tao, J. Zhao, G. Sun, K. Yin, J. Zhai, Graph structure embedded with physical constraints-based information fusion network for interpretable fault diagnosis of aero-engine, Energy (2023) 129120.
[30] H. Li, L. Gou, H. Li, Z. Liu, Physics-guided neural network model for aeroengine control system sensor fault diagnosis under dynamic conditions, Aerospace 10 (2023) 644.
[31] Xiao D, Lin Z, Yu A, et al. Data-driven method embedded physical knowledge for entire lifecycle degradation monitoring in aircraft engines[J]. Reliability Engineering & System Safety, 2024, 247: 110100.
[32] M. A. Chao, C. Kulkarni, K. Goebel, O. Fink, Fusing physics-based and deep learning models for prognostics, Reliability Engineering & System Safety 217 (2022) 107961.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献