Share Email Print

Proceedings Paper

Application of forcasting algorithms in the optical fiber coal dust burner monitoring system
Author(s): Waldemar Wojcik; T. Bieganski; Andrzej Kotyra; Andrzej Smolarz
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this article we discuss the properties of autoregression (AR) and moving average (MA) processes, as well as non- parametrical and parametrical identification of their models describing real time-series. We have shown the principles of calculating one-step forecasts with the smallest average square error for real time series, which describe flame blinking in a coal burner working in a boiler of the 200 MW energetic block. We have calculated ARMA (p,q) and ARIMA (p,d,q) mixed models, which, in turn, helped us to calculate one-step forecasts. The results, in the form of a measured time series, with marked one-step forecasts, are shown in enclosed figures.

Paper Details

Date Published: 5 August 1997
PDF: 10 pages
Proc. SPIE 3189, Technology and Applications of Light Guides, (5 August 1997); doi: 10.1117/12.285618
Show Author Affiliations
Waldemar Wojcik, Technical Univ. of Lublin (Poland)
T. Bieganski, Technical Univ. of Lublin (Poland)
Andrzej Kotyra, Technical Univ. of Lublin (Poland)
Andrzej Smolarz, Technical Univ. of Lublin (Poland)

Published in SPIE Proceedings Vol. 3189:
Technology and Applications of Light Guides
Jan Wojcik; Waldemar Wojcik, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?