Guiding Lunar Landers: Harnessing Neural Networks for Dynamic Flight Control with Adaptive Inertia and Mass Characteristics

Abstract

The autonomous control of landing procedures can provide the efficiency and precision thatare vital for the successful, safe completion of space operations missions. Controlling a lander withthis precision is challenging because the propellants, which will be expended during the operations,represent a significant fraction of the lander’s mass. The mass variation of each tank profoundlyinfluences the inertia and mass characteristics as thrust is generated and complicates the precisecontrol of the lander state. This factor is a crucial consideration in our research and methodology. Thedynamics model for our lander was developed where the mass, inertia, and center of mass (COM)vary with time. A feed-forward neural network (NN) is incorporated into the dynamics to capturethe time-varying inertia tensor and COM. Moreover, the propellant takes time to travel through thefeed lines from the storage tanks to the engine; also, the solenoid valves require time to open andclose. Therefore, there are time delays between the actuator and the engine response. To take intoaccount these sources of variations, a combined time delay is also included in the control loop toevaluate the effect of delays by fluid and mechanisms on the performance of the controller. Thetime delay is estimated numerically by a Computational Fluid Dynamics (CFD) model. As part ofthe lander’s control mechanism, a thrust vector control (TVC) with two rotational gimbals and areaction control system (RCS) are incorporated into the dynamics. Simple proportional, integral, andderivative (PID) controllers are designed to control the thrust, the gimbal angles of the TVC, and thetorque required by the RCS to manipulate the lander’s rotation and altitude. A complex mission withseveral numerical examples is presented to verify the hover and rotational motion control.