Aero-Engine Health State Prediction Using EnsembleBRB-based SHapley Additive exPlanations Approach

doi:10.19678/j.issn.1000-3428.0070152

Abstract

Abstract:

As an important aspect of engine health management, predicting the health state of aero-engines can provide quantitative basis for improving aircraft reliability and reducing engine maintenance costs. However, traditional aviation engine health state prediction methods lack sufficient attention to interpretability, resulting in a decreased support for engine maintenance decision-making, specifically when condition-dependent. This study proposes an interpretable prediction method for the health state of aero-engines based on the EnsembleBRB-SHAP approach, considering the demand for interpretability in engine health state prediction. First, a data-driven approach is used to train multiple sub-aero-engine health state prediction models based on a Belief Rule Base (BRB). Subsequently, an EnsembleBRB model is constructed for predicting the health state of aero-engines such that it utilizes multiple sources of uncertain data while ensuring prediction accuracy. Based on the SHapley Additive exPlanations (SHAP) framework, the constructed EnsembleBRB model is analyzed and interpreted to identify key features and achieve an interpretable prediction of the aero-engine health state. Finally, the feasibility and effectiveness of the proposed method are verified by introducing experimental monitoring data of engine faults recorded using the Commercial Modular Aero-Propulsion System Simulation software. Experimental results show that the Mean Square Error (MSE) of the proposed method in predicting the health status of aero-engines is 0.012 2. By analyzing local and global interpretability, the Low-Pressure Turbine (LPT) coolant bleed and physical fan speed are identified as the key parameters determining engine health status, which in turn can better support decision-making for managing aero-engine health and other work.

Key words: ensemble learning algorithm, Belief Rule Base (BRB), SHapley Additive exPlanations (SHAP), interpretability, engine health state prediction

摘要：

航空发动机健康状态预测作为发动机健康管理的重要环节之一, 能够为提升飞机可靠性、降低发动机维护成本等工作提供定量化依据。然而, 传统的航空发动机健康状态预测对可解释性关注度较低, 导致对发动机视情维修等决策的支撑性不足。为此, 面向发动机健康状态预测的可解释需求, 提出基于EnsembleBRB-SHAP模型的航空发动机健康状态可解释预测方法。首先, 采用数据驱动法训练多个航空发动机健康状态预测子置信规则库(BRB)模型。在此基础上, 构建航空发动机健康状态预测集成置信规则库(EnsembleBRB)模型, 在有效利用多源不确定数据的同时, 保证模型的预测准确性。然后, 基于沙普利加性解释(SHAP), 对EnsembleBRB模型进行分析解释, 定位影响发动机健康状态的关键因素, 实现航空发动机健康状态的可解释性预测。最后, 引入商用模块化航空推进系统仿真软件记录的发动机故障实验监测数据, 验证所提方法的可行性与有效性。实验结果表明, 该方法在航空发动机健康状态预测中的均方误差(MSE)为0.012 2, 通过局部可解释性与全局可解释性分析, 归纳得出低压涡轮机冷却液泄漏量、风扇转速等是决定发动机健康状态的关键参数, 进而更好地支撑航空发动机健康管理等决策工作。

关键词: 集成学习算法, 置信规则库, 沙普利加性解释, 可解释性, 发动机健康状态预测

YOU Yaqian, YAN Hui, SU Yaofeng, WANG Xiaoshuang, YAN Ruicheng. Aero-Engine Health State Prediction Using EnsembleBRB-based SHapley Additive exPlanations Approach[J]. Computer Engineering, 2026, 52(4): 386-397.

游雅倩, 闫辉, 苏耀峰, 王晓双, 鄢睿丞. 基于EnsembleBRB-SHAP的航空发动机健康状态可解释预测方法[J]. 计算机工程, 2026, 52(4): 386-397.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0070152

https://www.ecice06.com/EN/Y2026/V52/I4/386

Figures/Tables 12

Fig.1 EnsembleBRB-SHAP-based prediction and its interpretable analysis process of engine health state

Fig.2 Comparison of real and predicted values of #1 engine health state

Fig.3 SHAP force guidance diagram of some samples of engine #1

Fig.4 SHAP waterfall diagram of partial sample of engine #1

Fig.5 SHAP beeswarm summary diagram

Fig.6 SHAP dependence diagram for single monitoring parameter

Fig.7 SHAP dependence diagram for dual monitoring parameters

Fig.8 SHAP heatmap diagram

Fig.9 SHAP queue bar diagram

Fig.10 SHAP feature cluster diagram

References 29

1	ZHANG Y , XIN Y Q , LIU Z W , et al. Health status assessment and remaining useful life prediction of aero-engine based on BiGRU and MMoE. Reliability Engineering & System Safety, 2022, 220, 108263.
2	CUBILLO A , PERINPANAYAGAM S , ESPERON-MIGUEZ M . A review of physics-based models in prognostics: application to gears and bearings of rotating machinery. Advances in Mechanical Engineering, 2016, 8 (8): 168781.
3	VICHARE N M , PECHT M G . Prognostics and health management of electronics. IEEE Transactions on Components and Packaging Technologies, 2006, 29 (1): 222- 229. doi: 10.1109/TCAPT.2006.870387
4	YOU Y Q , SUN J B , CHEN Y W , et al. Ensemble belief rule-based model for complex system classification and prediction. Expert Systems with Applications, 2021, 164, 113952. doi: 10.1016/j.eswa.2020.113952
5	LUNDBERG S M, LEE S I. A unified approach to interpreting model predictions[C]//Proceedings of the Advances in Neural Information Processing Systems. Cambridge, USA: MIT Press, 2017: 4765-4774.
6	YANG J B , LIU J , WANG J , et al. Belief rule-base inference methodology using the evidential reasoning Approach-RIMER. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, 2006, 36 (2): 266- 285. doi: 10.1109/TSMCA.2005.851270
7	韩文策, 康潇, 李红宇, 等. 基于人在回路策略的在线置信规则库疾病诊断方法. 计算机工程, 2025, 51 (1): 321- 331. doi: 10.19678/j.issn.1000-3428.0068838
	HAN W C , KANG X , LI H Y , et al. A novel online belief rule base method with human-in-the-loop strategy for disease diagnosis. Computer Engineering, 2025, 51 (1): 321- 331. doi: 10.19678/j.issn.1000-3428.0068838
8	SHAPLEY L . A value for n-person games, contributions to the theory of games Ⅱ. New York, USA: Cambridge University Press, 1953.
9	MANGALATHU S , HWANG S H , JEON J S . Failure mode and effects analysis of RC members based on machine-learning-based Shapley additive explanations approach. Engineering Structures, 2020, 219, 110927. doi: 10.1016/j.engstruct.2020.110927
10	武宇翔, 韩肖清, 牛哲文, 等. 基于变权重随机森林的暂态稳定评估方法及其可解释性分析. 电力系统自动化, 2023, 47 (14): 93- 104.
	WU Y X , HAN X Q , NIU Z W , et al. Transient stability assessment method based on variable weight random forest and its interpretability analysis. Automation of Electric Power Systems, 2023, 47 (14): 93- 104.
11	SAXENA A, GOEBEL K, SIMON D, et al. Damage propagation modeling for aircraft engine Run-to-failure simulation[C]//Proceedings of the International Conference on Prognostics and Health Management. Denver, USA: IEEE Press, 2008: 1-9.
12	HANACHI H , LIU J , BANERJEE A , et al. A physics-based modeling approach for performance monitoring in gas turbine engines. IEEE Transactions on Reliability, 2014, 64 (1): 197- 205.
13	KIM S , IM J H , KIM M , et al. Diagnostics using a physics-based engine model in aero gas turbine engine verification tests. Aerospace Science and Technology, 2023, 133, 108102. doi: 10.1016/j.ast.2022.108102
14	于拓舟, 王宇, 张建锐, 等. 基于AMESim发动机物理模型的预测性研究[C]//2016 Siemens PLM Software仿真与试验技术大会论文集. 大连: [s. n. ], 2016: 1-5.
	YU T Z, WANG Y, ZHANG J R, et al. Predictive research of engine physical model based on AMESim[C]//Proceedings of the 2016 Siemens PLM Software Conference on Simulation and Testing Technology. Dalian: [s. n. ], 2016: 1-5. (in Chinese)
15	SUN X B , TAN J W , WEN Y , et al. Rolling bearing fault diagnosis method based on data-driven random fuzzy evidence acquisition and dempster-shafer evidence theory. Advances in Mechanical Engineering, 2016, 8, 168781.
16	LI Z X , GOEBEL K , WU D Z . Degradation modeling and remaining useful life prediction of aircraft engines using ensemble learning. Journal of Engineering for Gas Turbines and Power, 2019, 141 (4): 041008. doi: 10.1115/1.4041674
17	CHENG Y J , ZENG J Y , WANG Z L , et al. A health state-related ensemble deep learning method for aircraft engine remaining useful life prediction. Applied Soft Computing, 2023, 135, 110041. doi: 10.1016/j.asoc.2023.110041
18	SKORDILIS E , MOGHADDASS R . A deep reinforcement learning approach for real-time sensor-driven decision making and predictive analytics. Computers & Industrial Engineering, 2020, 147, 106600.
19	VISHNU T, GUGULOTHU N, MALHOTRA P, et al. Bayesian networks for interpretable health monitoring of complex systems[C]//Proceedings of the IJCAI'05. Washington D. C., USA: IEEE Press, 2005: 223-235.
20	GAO J H , WANG Y R , SUN Z J . An interpretable RUL prediction method of aircraft engines under complex operating conditions using spatio-temporal features. Measurement Science and Technology, 2024, 35 (7): 076003. doi: 10.1088/1361-6501/ad3b2c
21	ZHOU Z J , CAO Y , HU G Y , et al. New health-state assessment model based on belief rule base with interpretability. Science China Information Sciences, 2021, 64 (7): 172214. doi: 10.1007/s11432-020-3001-7
22	SACHAN S, YANG J B, XU D L. Global and local interpretability of belief rule base[C]//Proceedings of the Developments of Artificial Intelligence Technologies in Computation and Robotics. Berlin, Germany: Springer, 2020: 68-75.
23	CAO Y , ZHOU Z J , HU C H , et al. On the interpretability of belief rule-based expert systems. IEEE Transactions on Fuzzy Systems, 29 (11): 3489- 3503. doi: 10.1109/TFUZZ.2020.3024024
24	RIBEIRO M T, SINGH S, GUESTRIN C. Why should I trust you? Explaining the predictions of any classifier[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM Press, 2016: 1135-1144.
25	SHRIKUMAR A, GREENSIDE P, KUNDAJE A. Learning important features through propagating activation differences[C]//Proceedings of the International Conference on Machine Learning. Washington D. C., USA: IEEE Press, 2017: 3145-3153.
26	BACH S , BINDER A , MONTAVON G , et al. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS One, 2015, 10 (7): e0130140. doi: 10.1371/journal.pone.0130140
27	LIPOVETSKY S , CONKLIN M . Analysis of regression in game theory approach. Applied Stochastic Models in Business and Industry, 2001, 17 (4): 319- 330. doi: 10.1002/asmb.446
28	ŠTRUMBELJ E , KONONENKO I . Explaining prediction models and individual predictions with feature contributions. Knowledge and Information Systems, 2014, 41 (3): 647- 665. doi: 10.1007/s10115-013-0679-x
29	DATTA A, SEN S, ZICK Y. Algorithmic transparency via quantitative input influence: theory and experiments with learning systems[C]//Proceedings of the IEEE Symposium on Security and Privacy. San Jose, USA: IEEE Press, 2016: 598-617.

[1]	WEN Wen, ZHONG Yanhong, HAO Zhifeng. Repurchase Behavior and Time Interval Prediction Fused with Temporal Attenuation Characteristics [J]. Computer Engineering, 2026, 52(4): 111-121.
[2]	LIAO Yong, HAN Xiaojin, LIU Jinlin, WANG Hao. Research Progress of Interpretable Artificial Intelligence [J]. Computer Engineering, 2026, 52(3): 41-61.
[3]	GUO Peilin, ZHANG De, WANG Huaixiu. Exploring the Impact of Skip Connection Structures on the Deep Neural Networks Feature Extraction Based on Feature Visualization [J]. Computer Engineering, 2025, 51(4): 149-157.
[4]	Xueqiang LÜ, Xingqiang ZHAO, Zhibin JIA, Jing HAN. Visual Semantic Interpretation Model for Classification Network [J]. Computer Engineering, 2023, 49(11): 220-230.
[5]	PU Ruili, WANG Yuanlong, LI Ru. Judgement of Causality Options in Reading Comprehension Incorporating Representation of Causality [J]. Computer Engineering, 2022, 48(7): 89-96.
[6]	LUO Yong,GUO Yamo,LIU Chong. Design of Fuzzy Classification System Based on Pareto Firework Algorithm [J]. Computer Engineering, 2017, 43(2): 304-307,316.
[7]	ZHANG Yong, HUANG Cheng, XU Zhi-Liang, TUN Xiao-Bei. Design of Fuzzy Model Based on Differential Evolution Algorithm [J]. Computer Engineering, 2011, 37(21): 165-166,169.
[8]	ZHANG Yong; XING Zongyi; XIANG Zhengrong; HU Weili. Design of Interpretable Fuzzy Model Based on Clustering and Genetic Algorithm [J]. Computer Engineering, 2007, 33(08): 160-162.

Please choose a citation manager

Content to export