Deep reinforcement learning based active surge control for aeroengine compressors

作     者：Xinglong ZHANG Zhonglin LIN Runmin JI Tianhong ZHANG Xinglong ZHANG;Zhonglin LIN;Runmin JI;Tianhong ZHANG

作者机构：College of Energy and Power EngineeringNanjing University of Aeronautics and AstronauticsNanjing 210016China School of Mechanical Engineering and AutomationFuzhou UniversityFuzhou 350108China 

出 版 物：《Chinese Journal of Aeronautics》 (中国航空学报（英文版）)

年 卷 期：2024年第37卷第7期

页      面：418-438页

核心收录：

学科分类：082502[工学-航空宇航推进理论与工程] 08[工学] 0825[工学-航空宇航科学与技术] 

基　　金：co-supported by the National Natural Science Foundation of China(No.51976089) the Science Center for Gas Turbine Project,China(No.P2023-B-V-001-001) the China Scholarship Council(No.202306830092) 

主　　题：Aeroengine surge Active surge control Moore-Greitzer model Deep reinforcement learning Soft actor-critic Nonlinear observer 

摘      要：This study proposes an active surge control method based on deep reinforcement learning to ensure the stability of compressors when adhering to the pressure rise command across the wide operating range of an ***,the study establishes the compressor dynamic model with uncertainties,disturbances,and Close-Coupled Valve(CCV)actuator *** upon this foundation,a Partially Observable Markov Decision Process(POMDP)is defined to facilitate active surge *** address the issue of unobservability,a nonlinear state observer is designed using a finite-time high-order sliding ***,an Improved Soft Actor-Critic(ISAC)algorithm is developed,incorporating prioritized experience replay and adaptive temperature parameter techniques,to strike a balance between exploration and convergence during *** addition,reasonable observation variables,error-segmented reward functions,and random initialization of model parameters are employed to enhance the robustness and generalization ***,to assess the effectiveness of the proposed method,numerical simulations are conducted,and it is compared with the fuzzy adaptive backstepping method and Second-Order Sliding Mode Control(SOSMC)*** simulation results demonstrate that the deep reinforcement learning based controller outperforms other methods in both tracking accuracy and ***,the proposed active surge controller can effectively ensure stable operation of compressors in the high-pressure-ratio and high-efficiency region.