TY - GEN
T1 - Research on the future state evaluation of satellite functional components
AU - Changwen, Zhu
AU - Jun, Zhou
AU - Jianchen, Dang
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/10/16
Y1 - 2020/10/16
N2 - In this paper, a satellite health assessment model based on prediction data is proposed to research on the health assessm ent of the components of the satellite department in the future. Firstly select the temperature, voltage, and current telemetry para meters that can reflect the health of the component, use the CEE MDAN-PSO-ELM model to make single-step, three-step, and five -step predictions respectively, and then integrate the score which from the non-dimensional dimensionless model and the entropy weight method to get 'health', finally use the telemetry data fro m satellite to experiment. The experimental results show that single-step, three-step and five-step predictions can all accurately pr edict the change trend of the 'health' of the future state assessme nt of the component, and the mean square error (MSE) index of s ingle-step prediction is only 0.0049, which can evaluate the future status of the components.
AB - In this paper, a satellite health assessment model based on prediction data is proposed to research on the health assessm ent of the components of the satellite department in the future. Firstly select the temperature, voltage, and current telemetry para meters that can reflect the health of the component, use the CEE MDAN-PSO-ELM model to make single-step, three-step, and five -step predictions respectively, and then integrate the score which from the non-dimensional dimensionless model and the entropy weight method to get 'health', finally use the telemetry data fro m satellite to experiment. The experimental results show that single-step, three-step and five-step predictions can all accurately pr edict the change trend of the 'health' of the future state assessme nt of the component, and the mean square error (MSE) index of s ingle-step prediction is only 0.0049, which can evaluate the future status of the components.
KW - Complete Ensemble Empirical Mode Decomposition with Adaptive Noise
KW - Extreme Learning Machine
KW - mean square error
KW - Particle Swarm Optimization
KW - satellite
UR - http://www.scopus.com/inward/record.url?scp=85099681777&partnerID=8YFLogxK
U2 - 10.1109/PHM-Shanghai49105.2020.9280990
DO - 10.1109/PHM-Shanghai49105.2020.9280990
M3 - 会议稿件
AN - SCOPUS:85099681777
T3 - 2020 Global Reliability and Prognostics and Health Management, PHM-Shanghai 2020
BT - 2020 Global Reliability and Prognostics and Health Management, PHM-Shanghai 2020
A2 - Guo, Wei
A2 - Li, Steven
A2 - Miao, Qiang
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 Global Reliability and Prognostics and Health Management, PHM-Shanghai 2020
Y2 - 16 October 2020 through 18 October 2020
ER -