Spacecraft fault active detection method and device

Abstract

The embodiment of the invention provides a spacecraft fault active detection method and device. The method comprises the steps that: an abnormal score corresponding to normal mode expected data corresponding to each telemetry parameter of a spacecraft at the current time is obtained through employing a preset parameter normal trend model and the current actual telemetry data of the spacecraft, wherein the parameter normal trend model is obtained by training normal historical telemetry data of the spacecraft in a preset time period; and based on the abnormal score corresponding to each telemetry parameter and a preset abnormal threshold, whether the current actual telemetry data of the spacecraft contains a fault telemetry parameter is determined, and if yes, abnormal data corresponding to the fault telemetry parameter is output. According to the invention, under the condition of lack of spacecraft fault samples, downlink normal data can be utilized to the maximum extent, a correct change model of the data is learned, and active detection of spacecraft faults is realized.

Description

technical field [0001] The application relates to the technical field of spacecraft detection, in particular to a method and device for active detection of spacecraft faults. Background technique [0002] During the implementation of space missions, the multi-spacecraft cooperative flight control capability is required to be higher. In the operation stage, the operation and control center needs to complete the uplink control of multiple spacecraft at the same time, the control process is more complicated, and the timeliness requirements are higher. The center needs to organize on-orbit spacecraft platforms, crew equipment and extravehicular space suits, as well as the failure judgment and disposal of load platform equipment and main loads according to the failure plan. Some spacecraft have been in orbit for 10 to 15 years, and the functional components of the spacecraft platform have decayed over time, and the probability of emergency and failure has increased. [0003] At...

AI Technical Summary

Problems solved by technology

[0003] At present, fault detection software systems are usually based on rule-based and model-based fault diagnosis modes. However, in the case of no positive fault examples or lack of fault samples, it is difficult to obtain spacecraft fault models and this method is passive monitoring. As a result, the existing spacecraft fault diagnosis mode cannot proactively perform fault judgment and early warning on the state of the spacecraft. The automation level of the fault handling process is low, and the degree of personnel dependence is high, which cannot meet the needs of "intelligent operation and maintenance" for space mission fault diagnosis.

At the same time, fault diagnosis based on data analysis is still in the research stage, and a complete design framework has not been proposed

Images