Multi-objective optimization of low-thrust propulsion systems for multi-target missions using ANNs

Multi-target missions are an attractive solution to visit multiple bodies, increasing the scientific return and reducing the cost, compared to multiple missions to individual targets. Examples of multi-target missions are multiple active debris removals (MADR) and multiple near-Earth asteroids rendezvous (MNR) missions. MADR missions allow for the disposal of inactive satellites, preventing the build-up of space junk, while MNR missions allow to reduce the expenses of each asteroid observation. Since those missions are long and highly demanding in terms of energy, it is paramount to select the most convenient propulsion system so that the propellant mass and the duration of the mission are minimized. To this end, this paper proposes the use of a multi-objective optimization and artificial neural networks. The methodology is assessed by optimizing trajectories for MADR and MNR sequences with off-the-shelf thrusters. Multiple Pareto-optimal solutions can be identified depending on the propulsion system characteristics, enabling mission designers to trade-off the different options quickly and reliably.