Search

The Korea Pathfinder Lunar Orbiter (KPLO), officially named as Danuri, is the Republic of Korea's first spacecraft to orbit the Moon. The goal of KPLO is to secure core deep space technology for future space exploration in Korea and contribute to lunar science by gathering data from the lunar orbit for one year. This paper presents the results of KPLO's Lunar Orbit Acquisition (LOA) phase in detail, with a particular focus on the operational results of Flight Dynamics (FD). During the LOA phase, the KPLO FD team experienced many expected and unexpected issues. These issues were mitigated by making real-time updates to the LOA phase Design Reference Mission (DRM). The paper also presents the results of the Orbit Determination (OD) and performance of each Lunar Orbit Insertion (LOI) maneuver conducted during the actual flight operation. The importance of considering operational constraints when designing the DRM is emphasized by presenting lessons learned based on actual flight experiences. Unlike the original KPLO LOA phase DRM, KPLO successfully achieved the final mission orbit using only three LOI burns, instead of the planned five LOI burns and an Orbit Trim Maneuver (OTM). Despite the extensive revisions made to the DRM, all mission requirements were still fulfilled during the final lunar orbit insertion, taking into account the significant operational constraints. • Real flight operation results of the Korea Pathfinder Lunar Orbiter's lunar orbit acquisition phase are presented. • Orbit determination and lunar orbit insertion maneuver performance are analyzed based on actual flight data. • Unexpected issues during the actual flight operation were mitigated through real-time updates on the design reference mission. • Considering real-world operational constraints while designing the design reference mission is very critical. [ABSTRACT FROM AUTHOR]

This study presents data-driven reduced-order models (ROMs) of a lunar orbiter based on principal component analysis (PCA) and artificial neural networks (ANNs) for a ground thermal vacuum test to simulate space thermal environments. We employed a radial basis function network (RBFN) and deep neural network (DNN) from among the various types of ANNs. PCA extracts features from high-dimensional data, such as thermal analysis data. It is utilized in machine learning algorithms as a preprocessing step before inputting the data into neural networks. This process improves the convergence speed and training performances compared to using neural networks alone. The coefficients of the extracted principal component modes were regressed using the RBFN and DNN. Twenty thermal design parameters comprising infrared emissivity, effective thermal conductivity, thermal contact conductance coefficients, and thermal conductance were used to train the ROMs. We conducted training and test of the proposed models during the cold and hot balance phases of the ground test. Consequently, the temperature map can be estimated in seconds for the new design parameters, and the model results are consistent with thermal analysis and measurement data. [ABSTRACT FROM AUTHOR]