Reaction wheel fault detection and health assessment system and method based on deep learning

Abstract

The invention discloses a reaction wheel fault detection and health assessment system and method based on deep learning, and can solve the problems that the difficulty of reaction wheel fault detection is high, and normal data cannot be fully utilized to assess the health state of a reaction wheel when the fault data of the reaction wheel is less. The reaction wheel fault detection and health evaluation system comprises an observer, a detector and an evaluator. The observer is used for tracking the dynamic state of the reaction wheel and generating a real-time residual error; the detector generates a self-adaptive threshold value of the current time in real time, compares the relation between the residual error and the threshold value, and detects whether the reaction wheel breaks down or not; the evaluator is used for periodically evaluating the health state of the reaction wheel; the evaluator obtains and records a residual error, and residual error data in a period of time form a residual error vector; extracting features of the residual vectors; and calculating a spatial topological structure of the feature vectors, calculating a spatial deviation degree, and finally converting the spatial deviation degree into a health degree (CV) so as to realize health assessment.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis, in particular to a deep learning-based reaction wheel fault detection and health assessment system and method. Background technique [0002] Attitude and Orbit Control System (AOCS) is an important part of a spacecraft. When the spacecraft is affected by external disturbance torque, AOCS is used to control the stability and orientation of the spacecraft to a predetermined direction during operation. The space environment in which spacecraft are located is harsh and is often disturbed by various torques. Many spacecraft fail before completing their missions. More than 30% of spacecraft failures are due to AOCS, and nearly 50% of AOCS failures are caused by actuators. 60% of actuator-induced failures are caused by reaction wheels and control torque gyros. Fault detection and health assessment of reaction wheels is one of the important means to improve the reliability and safety of spacec...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the present invention provides a reaction wheel fault detection and health assessment system and method based on deep learning, which can solve the problems of many interferences, false alarms, and difficulty in reaction wheel fault detection; The problem of failing to make full use of normal data to assess its health status

Images