关键词: 几何可调燃烧室, 超声速燃烧, 硬件在环仿真, 深度强化学习, 多点压力分布控制

Abstract:

Generally， the variable geometry combustor can ensure suitable performance of scramjets. However， its multivariate and strong coupling characteristics make it difficult to develop high-performance control algorithms， and also become an intractable problem hindering the development of the scramjet field. To solve the contradiction between control design and mechanical coupling， this paper firstly proposes a multipoint fuel injection structure for the conventional variable geometry combustor. The newly proposed structure can provide more operable inputs， thereby ensuring a theoretical ability to improve the system performance. On the basis of the multipoint fuel injection structure， a new LSTM/DDPG-based control scheme is proposed to solve the problem of distributed pressure control in the case of supersonic combustion. This scheme can effectively improve the potential performance of the scramjet at wide range velocities and in long flight time. The effectiveness of the proposed scheme is then verified with the simulation results， i.e.， the LSTM/DDPG-based control scheme can significantly optimize the combustion performance of variable geometry combustor under different operating conditions. Finally， the applicability of the proposed scheme is validated on the Hardware-In-the-Loop （HIL） simulation platform， and the pressure distribution can be effectively controlled at different expansion ratios. The high-accuracy control of multipoint pressure distribution at wide range velocities for the variable geometry combustor is shown to be realized.

Key words: variable geometry combustor, supersonic combustion, hardware-in-the-loop, deep reinforcement learning, multipoint pressure distribution control