Satellite telemetry data feature selection method and device based on multi-objective optimization algorithm and medium

The embodiment of the invention discloses a satellite telemetry data feature selection method and device based on a multi-objective optimization algorithm and a medium. The method comprises the following steps: splicing original telemetering data of a satellite, screening and removing constant values in numerical data, and after time alignment, removing outliers and noise in the original telemetering data based on a Pauta criterion, a 53H algorithm and a median filtering algorithm to obtain preprocessed telemetering data; a traditional fast non-dominated sorting genetic algorithm NSGA-II is improved according to a non-uniform arithmetic crossover operator and a mutation operator based on fitness levels; determining a target function for feature selection according to the number of features, the root-mean-square error and the correlation function; and based on the objective function, selecting feature data for data completion, satellite state prediction and fault diagnosis from the preprocessed telemetry data