Title :
Separation of the Train Vibration Signal Based on Improved Fast ICA
Author :
Xing-yuan, Zhang ; Ji-liang, Tu ; De-cun, Dong
Author_Institution :
Coll. of Traffic & Transp. Eng., Tongji Univ., Shanghai, China
Abstract :
A separation method of the vibration signal based on improved fast ICA was proposed. It adopted the steepest descent method to improve the convergence rate. Improved fast ICA method is applied to separation of vibration signal from the train´s running gear. Separation results proved that the method is feasible and effective. The method is contributive and instructional to train´s running gear vibration fault-diagnose.
Keywords :
condition monitoring; fault diagnosis; gears; gradient methods; principal component analysis; railway rolling stock; vibrations; ICA; fault diagnosis; independent component analysis; steepest descent method; train running gear; vibration signal separation; Algorithm design and analysis; Blind source separation; Entropy; Gears; Independent component analysis; Signal processing algorithms; Vibrations; ICA; blind soure separation; vibration;
Conference_Titel :
Intelligent Computation Technology and Automation (ICICTA), 2011 International Conference on
Conference_Location :
Shenzhen, Guangdong
Print_ISBN :
978-1-61284-289-9
DOI :
10.1109/ICICTA.2011.229
