High-Accuracy Guide Star Catalogue Generation with a Machine Learning Classification Algorithm

Abstract

In order to detect gravitational waves and characterise their sources, three laser links were constructed with three identical satellites, such that interferometric measurements for scientific experiments can be carried out. The attitude of the spacecraft in the initial phase of laser link docking is provided by a star sensor (SSR) onboard the satellite. If the attitude measurement capacity of the SSR is improved, the efficiency of establishing laser linking can be elevated. An important technology for satellite attitude determination using SSRs is star identification. At present, a guide star catalogue (GSC) is the only basis for realising this. Hence, a method for improving the GSC, in terms of storage, completeness, and uniformity, is studied in this paper. First, the relationship between star numbers in the field of view (FOV) of a staring SSR, together with the noise equivalent angle (NEA) of the SSR—which determines the accuracy of the SSR—is discussed. Then, according to the relationship between the number of stars (NOS) in the FOV, the brightness of the stars, and the size of the FOV, two constraints are used to select stars in the SAO GSC. Finally, the performance of the GSCs generated by Decision Trees (DC), K-Nearest Neighbours (KNN), Support Vector Machine (SVM), the Magnitude Filter Method (MFM), Gradient Boosting (GB), a Neural Network (NN), Random Forest (RF), and Stochastic Gradient Descent (SGD) is assessed. The results show that the GSC generated by the KNN method is better than those of other methods, in terms of storage, uniformity, and completeness. The KNN-generated GSC is suitable for high-accuracy spacecraft applications, such as gravitational detection satellites.

Monitoramento de modelos de simulação usados como Gêmeos Digitais de processos: uma abordagem baseada em Machine Learning e Carta de Controle

“…O K-NN é uma técnica de Machine Learning que se baseia nos rótulos das amostras de dados de 'K' vizinhos próximos (dados de treinamento) para classificar dados de teste . Embora o K-NN seja um dos algoritmos de classificação mais simples (Lee et al, 2020), este foi escolhido para a abordagem proposta devido à sua robustez e adequação para problemas com múltiplas classes Zhang et al, 2021). O K-NN utiliza a distância euclidiana, calculada pela Equação 1, para definir os dados vizinhos mais próximos e, então, prever a classificação dos dados de teste de acordo com os rótulos desses seus vizinhos próximos (Gong et al, 2020).…”

Construction of the Guide Star Catalog for Double Fine Guidance Sensors Based on SSBK Clustering

“…Somayehee et al [26] proposed a weighted k-means clustering based on the geodesic criterion. According to the algorithm, for a 12 • FOV, the probability of observing more than 20 stars in the non-uniform star catalog is about 11.47%, and the probability of observing more than 20 stars in the uniform star catalog is about 0.02%; Zhang et al [27] proposed a method for generating a high-precision guide star catalog based on a machine learning classification algorithm. The average number of guide stars in the FOV generated by the KNN method is 44.73, and the minimum number of guide stars is 15, which is superior to other classification methods in storage, uniformity, and integrity.…”