Orbit Classification for Prediction Based on Evidential Reasoning and Belief Rule Base

At present, most of the modeling methods in orbit classification for prediction (OCP) are data-driven methods, these reasoning processes are not interpretable, and the modeling effect is not good under small samples. In this paper, a new interpretable small sample OCP method is proposed based on evidence reasoning (ER) and belief rule base (BRB). First, multiple indicators were integrated by ER iteration to reduce the parameters. Then the BRB model was constructed based on expert knowledge and quantitative data. Finally, the projection covariance matrix adaptation evolutionary strategy (P-CMA-ES) is used to optimize model parameters. A case study is constructed to verify the effectiveness of the proposed method.