@inproceedings{ccd3b12edff04409bec88ecb3874963a,
title = "Research on Fault Diagnosis Method of Control Moment Gyroscope Based on Random Forest Algorithm",
abstract = "The control moment gyroscope (CMG) plays the role of the actuator of the attitude control system in the spacecraft. Accurate and timely diagnosis of CMG faults is very important to ensure the normal operation of the spacecraft. Aiming at the problem of CMG fault diagnosis, a CMG fault diagnosis method based on random forest is proposed. By analyzing the principle of CMG fault diagnosis based on random forest algorithm, a fault diagnosis model of random forest algorithm is established, and the optimal number of decision trees of the model is found by cross-validation method. The optimal parameter is used to establish the final prediction model for fault diagnosis of CMG, and it is compared with the support vector machine (SVM) method. The results show that the random forest-based diagnosis method can effectively diagnose 6 fault types under various working conditions of CMG, and has higher accuracy and faster diagnosis speed than the SVM-based diagnosis method.",
keywords = "SVM, control moment gyroscope, fault diagnosis, number of decision trees, random forest",
author = "Ruonan Jiang and Mengzhe Jiang and Ti Zhou and Zichen Huang and Jingyu Zhang and Haiping Dong",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 14th IEEE Global Reliability and Prognostics and Health Management Conference, PHM-Hangzhou 2023 ; Conference date: 12-10-2023 Through 15-10-2023",
year = "2023",
doi = "10.1109/PHM-HANGZHOU58797.2023.10482552",
language = "English",
series = "2023 Global Reliability and Prognostics and Health Management Conference, PHM-Hangzhou 2023",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
editor = "Wei Guo and Steven Li",
booktitle = "2023 Global Reliability and Prognostics and Health Management Conference, PHM-Hangzhou 2023",
address = "United States",
}