| Citation: | ZHANG Wei, SUN Jianzhong, YAN Zichen, et al. Data-driven engine performance digital twin modeling and interpretability analysis[J]. Journal of Aerospace Power, 2025, 40（11）：20240160 doi: 10.13224/j.cnki.jasp.20240160
|
A data-driven gas turbine performance digital twin (PDT) model and its application framework for performance monitoring and health assessment were proposed. In this framework, a data-driven performance digital twin was constructed using semi-supervised deep learning methods, which were used to calculate multidimensional features to characterize the performance status of gas pipelines, and to enhance the input feature space for gas path component fault diagnosis and performance monitoring. Based on this, a gas path fault monitoring and isolation model, a health state assessment model were developed utilizing the XGBoost method. The integrated framework’s performance was tested on quick access recorder (QAR) data from a civil aviation engine model, and NASA N-CMAPSS dataset and relevant indicators were introduced to evaluate the proposed method. The interpretability of the data-driven performance digital twin model was explored using the Shapley additive explanations (SHAP) method. The verification results showed that the proposed data-driven PDT modeling and application framework had a relative error of less than 0.6% in the prediction of key performance parameters of gas paths, and can successfully detect more than 95% faults based on NASA N-CMAPSS data, with the fault isolation accuracy reaching 86%.
| [1] |
TAHAN M, TSOUTSANIS E, MUHAMMAD M, et al. Performance-based health monitoring, diagnostics and prognostics for condition-based maintenance of gas turbines: a review[J]. Applied Energy, 2017, 198: 122-144. doi: 10.1016/j.apenergy.2017.04.048
|
| [2] |
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): 34-73. CAO Ming, WANG Peng, ZUO Hongfu, et al. Current status, challenges and opportunities 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): 34-73. (in Chinese doi: 10.7527/j.issn.1000-6893.2022.9.hkxb202209002
CAO Ming, WANG Peng, ZUO Hongfu, et al. Current status, challenges and opportunities 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): 34-73. (in Chinese) doi: 10.7527/j.issn.1000-6893.2022.9.hkxb202209002
|
| [3] |
曹增义, 单继东, 王昭阳, 等. 面向航空发动机制造的数字孪生应用架构探索与实践[J]. 航空制造技术, 2022, 65(19): 40-49. CAO Zengyi, SHAN Jidong, WANG Zhaoyang, et al. Exploration and practice of digital twin architecture for aero-engine manufacturing[J]. Aeronautical Manufacturing Technology, 2022, 65(19): 40-49. (in Chinese
CAO Zengyi, SHAN Jidong, WANG Zhaoyang, et al. Exploration and practice of digital twin architecture for aero-engine manufacturing[J]. Aeronautical Manufacturing Technology, 2022, 65(19): 40-49. (in Chinese)
|
| [4] |
ZACCARIA V, STENFELT M, ASLANIDOU I, et al. Fleet monitoring and diagnostics based on digital twin of aero-engines[R]. Oslo, Norway: ASME Turbo Expo: Power for Land, Sea, and Air, 2018.
|
| [5] |
LIU Zuming, KARIMI I A. Gas turbine performance prediction via machine learning[J]. Energy, 2020, 192: 116627. doi: 10.1016/j.energy.2019.116627
|
| [6] |
黄金泉, 王启航, 鲁峰. 航空发动机气路故障诊断研究现状与展望[J]. 南京航空航天大学学报, 2020, 52(4): 507-522. HUANG Jinquan, WANG Qihang, LU Feng. Research status and prospect of gas path fault diagnosis for aeroengine[J]. Journal of Nanjing University of Aeronautics & Astronautics, 2020, 52(4): 507-522. (in Chinese
HUANG Jinquan, WANG Qihang, LU Feng. Research status and prospect of gas path fault diagnosis for aeroengine[J]. Journal of Nanjing University of Aeronautics & Astronautics, 2020, 52(4): 507-522. (in Chinese)
|
| [7] |
PANOV V, CRUZ-MANZO S. Gas turbine performance digital twin for real-time embedded systems[R]. Virtual: ASME Turbo Expo: Power for Land, Sea, and Air, 2020.
|
| [8] |
HANACHI H, LIU Jie, BANERJEE A, et al. A physics-based performance indicator for gas turbine engines under variable operating conditions[R]. Düsseldorf, Germany: 2014: ASME Turbo Expo 2014: Turbine Technical Conference and Exposition.
|
| [9] |
HU Minghui, HE Ya, LIN Xinzhi, et al. Digital twin model of gas turbine and its application in warning of performance fault[J]. Chinese Journal of Aeronautics, 2023, 36(3): 449-470. doi: 10.1016/j.cja.2022.07.021
|
| [10] |
DALLA VEDOVA M D L, GERMANÀ A, BERRI P C, et al. Model-based fault detection and identification for prognostics of electromechanical actuators using genetic algorithms[J]. Aerospace, 2019, 6(9): 94. doi: 10.3390/aerospace6090094
|
| [11] |
CHAO M A, KULKARNI C, GOEBEL K, et al. Hybrid deep fault detection and isolation: combining deep neural networks and system performance models[EB/OL]. (2019-12-28)[2024-03-21]. https://arxiv.org/pdf/1908.01529v2.
|
| [12] |
李天梅, 司小胜, 张建勋. 多源传感监测线性退化设备数模联动的剩余寿命预测方法[J]. 航空学报, 2023, 44(8): 227190. LI Tianmei, SI Xiaosheng, ZHANG Jianxun. Data-model interactive remaining useful life prediction method for multi-sensor monitored linear stochastic degrading devices[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(8): 227190. (in Chinese
LI Tianmei, SI Xiaosheng, ZHANG Jianxun. Data-model interactive remaining useful life prediction method for multi-sensor monitored linear stochastic degrading devices[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(8): 227190. (in Chinese)
|
| [13] |
GUO Xiaojie, CHEN Liang, SHEN Changqing. Hierarchical adaptive deep convolution neural network and its application to bearing fault diagnosis[J]. Measurement, 2016, 93: 490-502. doi: 10.1016/j.measurement.2016.07.054
|
| [14] |
FU Song, ZHONG Shisheng, LIN Lin, et al. A re-optimized deep auto-encoder for gas turbine unsupervised anomaly detection[J]. Engineering Applications of Artificial Intelligence, 2021, 101: 104199. doi: 10.1016/j.engappai.2021.104199
|
| [15] |
SONG Tao, LIU Chao, WU Rui, et al. A hierarchical scheme for remaining useful life prediction with long short-term memory networks[J]. Neurocomputing, 2022, 487: 22-33. doi: 10.1016/j.neucom.2022.02.032
|
| [16] |
CUI Langfu, ZHANG Chaoqi, ZHANG Qingzhen, et al. A method for aero-engine gas path anomaly detection based on Markov transition field and multi-LSTM[J]. Aerospace, 2021, 8(12): 374. doi: 10.3390/aerospace8120374
|
| [17] |
PARK D, HOSHI Y, KEMP C C. A multimodal anomaly detector for robot-assisted feeding using an LSTM-based variational autoencoder[J]. IEEE Robotics and Automation Letters, 2018, 3(3): 1544-1551. doi: 10.1109/LRA.2018.2801475
|
| [18] |
GULATI A, GHORAI J. Prognostic health management for turbofan engines[EB/OL]. [2024-03-21]. https://cs230.stanford.edu/projects_spring_2021/reports/15.pdf.
|
| [19] |
ARIAS CHAO M, KULKARNI C, GOEBEL K, et al. Aircraft engine Run-to-failure dataset under real flight conditions for prognostics and diagnostics[J]. Data, 2021, 6(1): 5. doi: 10.3390/data6010005
|
| [20] |
DONG Yuanbo, MAO Dajun, ZHANG Mingming. Research on optimization and adjustment of gas turbine combustion based on XGBoost and NSGA-Ⅱ[R]. Shanghai, China: 6th International Conference on Power and Renewable Energy, 2021.
|
| [21] |
COBLE J B. Merging data sources to predict remaining useful life: an automated method to identify prognostic parameters[R]. Knoxville, US: University of Tennessee, 2010.
|
| [22] |
CHRIST M, BRAUN N, NEUFFER J, et al. Time series feature extraction on basis of scalable hypothesis tests (tsfresh: a Python package)[J]. Neurocomputing, 2018, 307: 72-77. doi: 10.1016/j.neucom.2018.03.067
|
| [23] |
ROADMAP E A I. EASA concept paper: first usable guidance for Level 1 machine learning applications[R]. Cologne, Germany: European Union Aviation Safety Agency, 2021.
|
| [24] |
DOSHI-VELEZ F, KIM B. Towards a rigorous science of interpretable machine learning[EB/OL]. (2017-03-02)[2024-03-21]. https://arxiv.org/pdf/1702.08608.
|
| [25] |
陈曦泽, 贾俊峰, 白玉磊, 等. 基于XGBoost-SHAP的钢管混凝土柱轴向承载力预测模型[J]. 浙江大学学报(工学版), 2023, 57(6): 1061-1070. CHEN Xize, JIA Junfeng, BAI Yulei, et al. Prediction model of axial bearing capacity of concrete-filled steel tube columns based on XGBoost-SHAP[J]. Journal of Zhejiang University (Engineering Science), 2023, 57(6): 1061-1070. (in Chinese
CHEN Xize, JIA Junfeng, BAI Yulei, et al. Prediction model of axial bearing capacity of concrete-filled steel tube columns based on XGBoost-SHAP[J]. Journal of Zhejiang University (Engineering Science), 2023, 57(6): 1061-1070. (in Chinese)
|
| [26] |
RIBEIRO M, SINGH S, GUESTRIN C. “Why should I trust you”: explaining the predictions of any classifier[R]. San Francisco, US: 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016.
|
DownLoad:
