DocumentCode :
1761120
Title :
A Novel Long-Term Prediction Model for Hemispherical Resonator Gyroscope´s Drift Data
Author :
Chenglong Dai ; Dechang Pi ; Zhen Fang ; Hui Peng
Author_Institution :
Coll. of Comput. Sci. & Technol., Nanjing Univ. of Aeronaut. & Astronaut., Nanjing, China
Volume :
14
Issue :
6
fYear :
2014
fDate :
41791
Firstpage :
1886
Lastpage :
1897
Abstract :
The hemispherical resonator gyroscope (HRG) is a new vibration gyro, which has features of high accuracy, long lifespan, no wear-out, and great reliability. However, the excellent performances make it impractical to get the HRG´s lifespan within whole life test, and its lifespan has not even been explored. To predict the HRG´s lifespan without whole life test, one residual modified autoregressive gray model, ARGM(1,1), is proposed. It combines autoregressive process inherited from artificial neural network and support vector machine with gray model to train, model, and forecast. In this paper, this model is applied to predict multiperiod sequences with one HRG´s drift data, and gray correlation analysis is used to evaluate the HRG´s failure stage and get the lifespan. The experimental results show the model has good characteristics of self-adaption and low demands for modeling data. Compared with the conventional GM(1,1), back propagation neural network and support vector regression, residual modified ARGM(1,1) outperforms them in long-term prediction for the HRG´s drift data. Meanwhile, the predictive result shows the HRG can work about 15.74 years. Based on the 10 global oldest spacecraft, the predictive result with the method is reliable.
Keywords :
autoregressive processes; computerised instrumentation; correlation theory; grey systems; gyroscopes; neural nets; prediction theory; resonators; sequences; support vector machines; vibration measurement; ARGM(1,1); HRG drift data; HRG failure stage evaluation; HRG lifespan; artificial neural network; autoregressive process; gray correlation analysis; hemispherical resonator gyroscope; long term prediction model; multiperiod sequence prediction; residual modified autoregressive gray model; support vector machine; vibration gyro; Artificial neural networks; Correlation; Data models; Materials requirements planning; Predictive models; Support vector machines; Training data; ARGM(1,1); Hemispherical resonator gyroscope (HRG); drift data; grey correlation; long-term prediction; residual modified model;
fLanguage :
English
Journal_Title :
Sensors Journal, IEEE
Publisher :
ieee
ISSN :
1530-437X
Type :
jour
DOI :
10.1109/JSEN.2014.2305438
Filename :
6736078
Link To Document :
بازگشت