Data-driven spacecraft state prediction method

Abstract

The invention provides a data-driven spacecraft state prediction method, first a prediction sample is input, predictive factors are determined, a projection value is calculated, then a projection pursuit auto-regressive model is established, a projection indicator function is built, an acceleration genetic algorithm is used to optimize a projection direction, the projection pursuit regressive model is finally determined, and parameter prediction is performed. The data-driven spacecraft state prediction method provided by the invention can find the structure or characteristic from telemetry data themselves which do not conform to normal distribution or have little prior information, and can solves the problem of a nonlinear structure in linear projection. The data-driven spacecraft state prediction method has a good prediction effect, and has positive significance to spacecraft fault prediction and diagnosis.

Description

technical field [0001] The invention belongs to the field of aerospace measurement and control, and relates to a spacecraft state prediction method based on accelerated genetics and projection pursuit regression models. Background technique [0002] For a long time, the theoretical exploration, method research and application development of data-driven trend analysis, mutation detection and fault location technology have been widely valued by the theoretical and engineering circles of the world, and has now developed into a field based on reliability theory, control theory, information theory, statistics, and decision theory as the theoretical basis, with system modeling, process identification, process automation, statistical signal processing, intelligent computing, and machine reasoning technology as the main processing means, and with the system and its operation process equipment component defects, System functional faults and process abnormal changes are emerging fring...

AI Technical Summary

Problems solved by technology

However, in the application of spacecraft on-orbit operation management, its key technology still stays at the level of "status monitoring + threshold alarm". Most of what the rule-based fault diagnosis expert system for satellite downlink data can accomplish is essentially sensor / Sensor sampling data similar outlier discovery work, satellite telemetry parameter prediction has shortcomings such as poor real-time performance, slow optimization speed, strong dependence of prediction model on theoretical data of telemetry parameters, and many model assumptions

Images