A comparative study of neural network and Box-Jenkins ARIMA modeling in time series prediction

被引:231
作者
Ho, SL
Xie, M
Goh, TN
机构
[1] Ngee Ann Polytech, Ctr Qual, Singapore 599489, Singapore
[2] Natl Univ Singapore, Singapore 119260, Singapore
关键词
Box-Jenkins autoregressive integrated moving average model; multi-layer feed-forward neural network; recurrent neural network;
D O I
10.1016/S0360-8352(02)00036-0
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
This paper aims to investigate suitable time series models for repairable system failure analysis. A comparative study of the Box-Jenkins autoregressive integrated moving average (ARIMA) models and the artificial neural network models in predicting failures are carried out. The neural network architectures evaluated are the multi-layer feed-forward network and the recurrent network. Simulation results on a set of compressor failures showed that in modeling the stochastic nature of reliability data, both the ARIMA and the recurrent neural network (RNN) models outperform the feed-forward model; in terms of lower predictive errors and higher percentage of correct reversal detection. However, both models perform better with short term forecasting. The effect of varying the damped feedback weights in the recurrent net is also investigated and it was found that RNN at the optimal weighting factor gives satisfactory performances compared to the ARIMA model. (C) 2002 Published by Elsevier Science Ltd.
引用
收藏
页码:371 / 375
页数:5
相关论文
共 11 条
[1]  
ALMAN JL, 1990, COGNITIVE SCI, V14, P179
[2]  
Azoff E.M., 1994, NEURAL NETWORK TIME
[3]   The use of ARIMA models for reliability forecasting and analysis [J].
Ho, SL ;
Xie, M .
COMPUTERS & INDUSTRIAL ENGINEERING, 1998, 35 (1-2) :213-216
[4]  
Hoyland A., 1994, System reliability theory
[5]   A neural network approach to identifying cyclic behaviour on control charts: A comparative study [J].
Hwarng, HB .
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE, 1997, 28 (01) :99-112
[6]   A comparison of artificial neural network and time series models for forecasting commodity prices [J].
Kohzadi, N ;
Boyd, MS ;
Kermanshahi, B ;
Kaastra, I .
NEUROCOMPUTING, 1996, 10 (02) :169-181
[7]   AN EXPLORATORY-STUDY OF A NEURAL-NETWORK APPROACH FOR RELIABILITY DATA-ANALYSIS [J].
LIU, MC ;
KUO, W ;
SASTRI, T .
QUALITY AND RELIABILITY ENGINEERING INTERNATIONAL, 1995, 11 (02) :107-112
[8]  
Pham D. T., 1992, Journal of Systems Engineering, V2, P90
[9]  
Rumelhart DE, 1986, PARALLEL DISTRIBUTED, V1, DOI DOI 10.7551/MITPRESS/5236.001.0001
[10]   TIME-SERIES METHODS IN RELIABILITY [J].
WALLS, LA ;
BENDELL, A .
RELIABILITY ENGINEERING & SYSTEM SAFETY, 1987, 18 (04) :239-265