Transient gas path fault diagnosis of aero-engine based on domain adaptive offline reinforcement learning

被引:3
作者
Xu, Jinghui [1 ]
Wang, Ye [1 ]
Wang, Zepeng [1 ]
Wang, Xizhen [1 ]
Zhao, Yongjun [1 ]
机构
[1] Fudan Univ, Dept Aeronaut & Astronaut, 220 Handan Rd, Shanghai 200433, Peoples R China
关键词
Aero-engine; Gas path diagnosis; Transient performance; Offline reinforcement learning; Domain adaptation; TURBINE PERFORMANCE;
D O I
10.1016/j.ast.2024.109701
中图分类号
V [航空、航天];
学科分类号
08 ; 0825 ;
摘要
Real-time measurement parameters are crucial for diagnosing faults in aero-engine gas path performance, ensuring engine reliability, and mitigating potential economic losses. Traditional aero-engines performance diagnosis was mainly based on the measurements of steady-state condition and lacked the utilization of data under transient conditions. Gas path diagnosis of aero-engines under transient conditions is crucial for early fault detection and safety of flight within the envelope. The challenge lies in the inconsistent distribution of performance deviations caused by variable operating conditions, especially with complex fault types, which can undermine diagnostic credibility. To improve reliability of gas path diagnosis under transient conditions, an offline reinforcement learning fault diagnosis framework based on a transient aero-engine performance model is proposed. To address the issue of variable operating conditions during transient states, a domain adaptive approach is utilized to reconstruct the measurement baseline and facilitate the transfer of different performance deviation distributions. Additionally, by adding spool acceleration as a measurement parameter, the multi-component fault coupling is solved. Finally, validation with actual operating data simulates fault cases, demonstrating the proposed method's efficacy in quantitatively detecting gradual, sudden, and multiple component faults under transient conditions with high accuracy and efficiency. The method proposed in this study achieves a computational speed improvement by 64% compared to the conventional method, achieving a time of 0.13 seconds, with an average error of less than 0.00389%. Additionally, it demonstrates strong robustness in the presence of noise, with an average error of less than 0.03125%. This proposed method improves real-time fault detection under transient conditions for its higher accuracy and efficiency, and therefore significantly enhance gas path health monitoring and diagnosis capability.
引用
收藏
页数:18
相关论文
共 56 条
[1]  
[Anonymous], Component Degradation Modeling in An Advanced Three-Shaft Turbofan Engine, DOI [10.1007/978-981-19-2635-887, DOI 10.1007/978-981-19-2635-887]
[2]  
[Anonymous], A study of aero-engine control method based on deep reinforcement learning | IEEE Journals & Magazine | IEEE Xplore
[3]   Deep Reinforcement Learning A brief survey [J].
Arulkumaran, Kai ;
Deisenroth, Marc Peter ;
Brundage, Miles ;
Bharath, Anil Anthony .
IEEE SIGNAL PROCESSING MAGAZINE, 2017, 34 (06) :26-38
[4]   Thermodynamic responses of bleed air on separated flow high by-pass turbofan engine under constant speed and constant thrust cases [J].
Aygun, Hakan .
ENERGY, 2024, 291
[5]   Thermodynamics, Environmental and Sustainability Impacts of a Turbofan Engine Under Different Design Conditions Considering Variable Needs in the Aviation Industry [J].
Aygun, Hakan ;
Sheikhi, Mohammad Rauf ;
Caliskan, Hakan .
GLOBAL CHALLENGES, 2024, 8 (02)
[6]  
Badnava B, 2019, Arxiv, DOI arXiv:1902.06239
[7]   A time-series turbofan engine successive fault diagnosis under both steady-state and dynamic conditions [J].
Chen, Yu-Zhi ;
Tsoutsanis, Elias ;
Wang, Chen ;
Gou, Lin-Feng .
ENERGY, 2023, 263
[8]   A dynamic performance diagnostic method applied to hydrogen powered aero engines operating under transient conditions [J].
Chen, Yu-Zhi ;
Tsoutsanis, Elias ;
Xiang, Heng-Chao ;
Li, Yi-Guang ;
Zhao, Jun-Jie .
APPLIED ENERGY, 2022, 317
[9]   A sequential model-based approach for gas turbine performance diagnostics [J].
Chen, Yu-Zhi ;
Zhao, Xu-Dong ;
Xiang, Heng-Chao ;
Tsoutsanis, Elias .
ENERGY, 2021, 220
[10]   Surrogate model-based real-time gas path fault diagnosis for gas turbines under transient conditions [J].
Cheng, Xianda ;
Zheng, Haoran ;
Yang, Qian ;
Zheng, Peiying ;
Dong, Wei .
ENERGY, 2023, 278