State-of-Health Prediction for Reaction Wheel of On-Orbit Satellite Based on Fourier Broad Learning System

The state-of-health (SoH) of the reaction wheel (RW) is a key indicator of the satellite’s ability to function properly and complete its mission successfully. Quick and accurate prediction of the RW’s SoH is an important guarantee of autonomous satellite mission execution and health management. In view of the pseudoperiodicity and strong noise characteristics of satellite on-orbit telemetry data, this paper aims to design a prediction framework meeting the satellite state on-orbit prediction requirements, which mainly includes data reconstruction, similar data screening, self-revised prediction and the fuzzy expression of results. First, a new method for RW health characterization is proposed for actual telemetry data from satellites, and a completely new set of historical samples is constructed. Second, a fusion deviation measure is proposed by selecting samples from the historical sample set that are similar to the sample to be predicted. Third, a Fourier Broad Learning System (FBLS) is proposed to improve the depiction accuracy of a standard Broad Learning System (BLS) in learning satellite telemetry data with less computational and time resources. Finally, a fuzzy expression is proposed to obtain the prediction results. The proposed method is validated with real satellite on-orbit telemetry data. The case study results show that the SoH of the RW can be predicted quickly and accurately, which demonstrates the promising performance of our method.