Fast solution to the free return orbit's reachable domain of the manned lunar mission by deep neural network

It is important to calculate the reachable domain(RD)of the manned lunar mission to evaluate whether a lunar landing site could be reached by the spacecraft. In this paper, the RD of free return orbits is quickly evaluated and calculated via the classification and regression neural networks. An efficient databasegeneration method is developed for obtaining eight types of free return orbits and then the RD is defined by the orbit’s inclination and right ascension of ascending node(RAAN) at the perilune. A classify neural network and a regression network are trained respectively. The former is built for classifying the type of the RD, and the latter is built for calculating the inclination and RAAN of the RD. The simulation results show that two neural networks are well trained. The classification model has an accuracy of more than 99% and the mean square error of the regression model is less than 0.01°on the test set. Moreover, a serial strategy is proposed to combine the two surrogate models and a recognition tool is built to evaluate whether a lunar site could be reached. The proposed deep learning method shows the superiority in computation efficiency compared with the traditional double two-body model.

Free return orbit design and characteristics analysis for manned lunar mission

A circumlunar free return orbit design model that satisfies manned lunar mission constraints is established. By combining analytical method with numerical method,a serial orbit design strategy from initial value design to precision solution is proposed. A simulation example is given,and the conclusion indicates that the method has excellent convergence performance and precision. According to a great deal of simulation results solved by the method,the free return orbit characters such as accessible moon orbit parameters,return orbit parameters,transfer delta velocity,etc. are analyzed,which can supply references to constitute manned lunar mission orbit scheme.

Point return orbit design and characteristics analysis for manned lunar mission

Point return orbit(PRO) of manned lunar mission is constrained by both lunar parking orbit and reentry corridor associated with reentry position.Besides,the fuel consumption and flight time should be economy.The patched conic equations which are adaptive to PRO are derived first,the PRO is modeled with fuel and time constraints based on the design variables of orbit parameters with clear physical meaning.After that,by combining analytical method with numerical method,a serial orbit design strategy from initial value design to precision solution is proposed.Simulation example indicates that the method has excellent convergence performance and precision.According to a great deal of simulation results by the method,the PRO characteristics such as Moon centered orbit parameters,Earth centered orbit parameters,transfer velocity change,etc.are analyzed,which can supply references to the manned lunar mission orbit scheme.

Characteristic analysis and design of near moon abort trajectory for manned lunar landing mission

The safety of astronauts would be severely threatened if the lunar-landing spacecraft were under an emergency during the near moon phase of flight, which was far from the Earth. For the problem of mission abort caused by the main engine (service propulsion system, SPS) failure during lunar orbit insertion, firstly, the family of trajectories resulted from SPS premature shutdown and corresponding abort trajectories were analyzed; then an algorithm that can be applied to the near moon abort trajectories was proposed using patched-conic technique. The characteristics of the abort trajectory, such as energy consumption and return time of flight, were analyzed and presented. Finally, simulation examples were given to demonstrate various cases of near moon SPS failure. The results of the simulation have validated the approach proposed.