Table of Contents Author Guidelines Submit a Manuscript
Science and Technology of Nuclear Installations
Volume 2017 (2017), Article ID 1839871, 11 pages
https://doi.org/10.1155/2017/1839871
Research Article

Dynamic Behavior Analysis of Touchdown Process in Active Magnetic Bearing System Based on a Machine Learning Method

Zhe Sun,1,2,3 Xunshi Yan,1,2,3 Jingjing Zhao,1,2,3 Xiao Kang,4 Guojun Yang,1,2,3 and Zhengang Shi1,2,3

1Institute of Nuclear and New Energy Technology, Tsinghua University, Beijing 100084, China
2Collaborative Innovation Center of Advanced Nuclear Energy Technology, Beijing 100084, China
3The Key Laboratory of Advanced Reactor Engineering and Safety, Ministry of Education, Beijing 100084, China
4Mechanical Engineering, Texas A&M University, College Station, TX 77843, USA

Correspondence should be addressed to Zhe Sun; nc.ude.auhgnist@ehz_nus

Received 30 December 2016; Revised 28 August 2017; Accepted 14 September 2017; Published 18 October 2017

Academic Editor: Eugenijus Ušpuras

Copyright © 2017 Zhe Sun et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

Magnetic bearings are widely applied in High Temperature Gas-cooled Reactor (HTGR) and auxiliary bearings are important backup and safety components in AMB systems. The performance of auxiliary bearings significantly affects the reliability, safety, and serviceability of the AMB system, the rotating equipment, and the whole reactor. Research on the dynamic behavior during the touchdown process is crucial for analyzing the severity of the touchdown. In this paper, a data-based dynamic analysis method of the touchdown process is proposed. The dynamic model of the touchdown process is firstly established. In this model, some specific mechanical parameters are regarded as functions of deformation of auxiliary bearing and velocity of rotor firstly; furthermore, a machine learning method is utilized to model these function relationships. Based on the dynamic model and the Kalman filtering technique, the proposed method can offer estimation of the rotor motion state from noisy observations. In addition, the estimation precision is significantly improved compared with the method without learning. The proposed method is validated by the experimental data from touchdown experiments.