A novel aero-engine control method based on deep reinforcement learning (DRL) is proposed to improve the engine response ability. The Q-learning that is model free and can be performed online is adopted. For improving the learning capacity of DRL, the online sliding window deep neural network (OL-SW-DNN) is proposed and adopted to estimate the action value function. The OL-SW-DNN selects the nearest point data with certain length as training data and is insensitivity to the noise. Finally, the comparison simulations of the proposed method with the proportion-integration-differentiation (PID) that is the most commonly used as an engine controller algorithm in industry are conducted to verify the validity of the proposed method. The results show that, compared with the PID, the acceleration time of the proposed method decreased by 1.525 s under the premise of satisfying all engine limits. INDEX TERMS Aero-engine control method, response ability, deep reinforcement learning, on line, deep neural network.

The modern advanced aero-engine control methods are onboard dynamic model–based algorithms. In this article, a novel aero-engine dynamic modeling method based on improved compact propulsion system dynamic model is proposed. The aero-engine model is divided into inlet, core engine, surge margin and nozzle models for establishing sub-model in the compact propulsion system dynamic model. The model of core engine is state variable model. The models of inlet, surge margin and nozzle are nonlinear models which are similar to the component level model. A new scheduling scheme for basepoint control vector, basepoint state vector and basepoint output vector which considers the change of engine total inlet temperature is proposed to improve engine model accuracy especially the steady. The online feedback correction of measurable parameters is adopted to improve the steady and dynamic accuracy of model. The modeling errors of improved compact propulsion system dynamic model remain unchanged when engine total inlet temperature of different conditions are the same or changes small. The model accuracy of compact propulsion system dynamic model, especially the measurable parameters, is improved by online feedback correction. Moreover, the real-time performance of compact propulsion system dynamic model and improved compact propulsion system dynamic model are much better than component level model.

According to the structural characteristics and working principle of the electric actuator system of the aircraft thrust reverser, the mathematical control model of the thrust reverser actuator is proposed for a certain type of electric thrust reverser actuator system. The model is established and simulated by the modular modeling method based on Simulink software. The actuator’s load force, transmission, displacement, and velocity relationship are analyzed. The simulation results show that the model can simulate the deployment and stow of the actuator under different conditions and provide a platform for the control logic design, force analysis, and fault diagnosis of the electric thrust reverse actuator system.

Aero-engine on-board steady state model is an important part of many advanced engine control algorithms. In order to build a high accuracy and real-time steady-state onboard model in a large envelope, an ICPSM (improved compact propulsion system model) based on batch normalize neural network is proposed in this paper. Compared with piecewise linearization model and support vector machine model, conventional CPSM which is mainly composed of baseline model and nonlinear sub model has the advantages of high real-time performance and small data storage. However, as the similarity conversion error increases with the distance from the design point, the cumulative error of the conventional baseline model also increases, which makes the model unable to maintain high accuracy in the full envelope. Thus, a high accuracy baseline model in full envelope based on batch normalize neural network is proposed in this paper. The simulation result shows that compared with the conventional compact propulsion system model, the percentage error of parameters of the improved compact propulsion system model based on the batch neural network is reduced by two times, the single step operation time is reduced by 18%, and the data storage of the onboard model is reduced as well.

No abstract