Title :
Application of a multivariable self-tuning predictor
Author :
Kanjilal, P.P. ; Rose, E.
Author_Institution :
University of Oxford, Oxford, England
Abstract :
A multivariable predictor algorithm is presented which can produce multistep prediction of a stochastic time series. The algorithm is used to predict product quality in an iron-ore sintering process. The application uses a modified low-pass filtering technique involving less time lag than conventional filters.
Keywords :
Ellipsoids; Filtering; Linear programming; Pattern recognition; Polynomials; Prediction algorithms; Random number generation; Stochastic processes; Testing; Vectors;
Journal_Title :
Proceedings of the IEEE
DOI :
10.1109/PROC.1986.13472
