Prediction of the remaining useful life of middle-low speed maglev train braking system based on COA-LSSVR

The prediction of remaining useful life has always been the research hotspot in the field of reliability engineering. The structure of the system is too complex to model by the method of physical model and it is also difficult to accurately predict the remaining useful life. During the actual operat...

Full description

Saved in:
Bibliographic Details
Published in2017 13th IEEE International Conference on Electronic Measurement & Instruments (ICEMI) pp. 86 - 91
Main Authors Wang Ping, Long Zhiqiang, Dou Fengshan
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2017
Subjects
braking system
COA-LSSVR
Data models
Kernel
Mathematical model
Prediction algorithms
Predictive models
remaining useful life prediction
Support vector machines
Training
Online AccessGet full text

Cover

More Information
Summary:The prediction of remaining useful life has always been the research hotspot in the field of reliability engineering. The structure of the system is too complex to model by the method of physical model and it is also difficult to accurately predict the remaining useful life. During the actual operation process, the equipment maintenance would inevitably lead to the change of the curve, and sometimes the variation of curve is comparatively large. In view of the equipment maintenance situation, the error control advantage of least square support vector regression(LSSVR) could be taken. In this paper, two parameters of LSSVR were optimized by using the cuckoo optimization algorithm (COA), and the COA-LSSVR model was established. Then the model was used to predict the remaining useful life. Based on the experimental data of medium-low speed maglev train braking system, LSSVR was used to compare with COA-LSSVR finally. The results show that the proposed algorithm of COA-LSSVR model could gain more accurate data of the remaining useful life.
DOI:10.1109/ICEMI.2017.8265722