Hybrid onboard model of high-flow dual variable cycle engine based on deep reinforcement learning

In a recent article featured in the Chinese Journal of Aeronautics, considering the strong information extraction ability of deep reinforcement learning and the characteristics of interaction with the environment, an aero-engine hybrid onboard model based on deep reinforcement learning is proposed by Prof. Wenxiang Zhou and Doctoral student. Ying Chen from Nanjing University of Aeronautics and Astronautics.

This study focus on the high-flow dual variable cycle engine, firstly delves into the engine's thermodynamic principles comprehensively, then establishing and validating the component level model (CLM), which serve as the inner loop of hybrid model. Subsequently, integrated twin delayed deep deterministic (TD3) policy gradient algorithm to establish the outer loop of hybrid model within full flight envelope and all operational states. The simulation results demonstrate that the hybrid model can converge quickly within the full flight envelope, the error of key parameters is less than 1.5%, and the average single-step simulation time on the P2020 development board is no more than 3ms, meeting the requirements of fast convergence, high accuracy, and good real-time performance for onboard model. Further, the inner-outer loop design enables hybrid onboard model approaching the domain of solution quickly, significantly reducing the calculation time of simulation initialization and ensuring model convergence throughout transition processes.

It is worth mentioning that the proposed hybrid model is suitable for all aero-engine component-level modeling. The hybrid onboard model has the characteristics of high accuracy and good real-time performance, providing a foundation for control and fault diagnosis in the field of aircraft engines.

Looking to the future, the team will further develop the onboard models and control schedules design methods for aircraft engines. The final template is to develop a universal onboard simulation test platform for general aero-engines with high precision and good real-time performance, providing a foundation for the testing of next generation aero-engines onboard models.

Original Source

Chen Y, Lu S, Chen Z, et al. Hybrid onboard model of high-flow dual variable cycle engine based on deep reinforcement learning[J]. Chinese Journal of Aeronautics, 2025, https://doi.org/10.1016/j.cja.2025.103792.

About Chinese Journal of Aeronautics 

Chinese Journal of Aeronautics (CJA) is an open access, peer-reviewed international journal covering all aspects of aerospace engineering, monthly published by Elsevier. The Journal reports the scientific and technological achievements and frontiers in aeronautic engineering and astronautic engineering, in both theory and practice. CJA is indexed in SCI (IF = 5.7, Q1), EI, IAA, AJ, CSA, Scopus.