Premium
Dynamic data rectification by recurrent neural networks vs. Traditional methods
Author(s) -
Karjala Thomas W.,
Himmelblau David M.
Publication year - 1994
Publication title -
aiche journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.958
H-Index - 167
eISSN - 1547-5905
pISSN - 0001-1541
DOI - 10.1002/aic.690401110
Subject(s) - rectification , computer science , artificial neural network , kalman filter , recurrent neural network , nonlinear system , dynamic programming , process (computing) , noise (video) , dynamic data , artificial intelligence , extended kalman filter , control theory (sociology) , algorithm , engineering , programming language , physics , quantum mechanics , voltage , electrical engineering , image (mathematics) , control (management)
Recurrent neural networks are used to demonstrate the dynamic data rectification of process measurements containing Gaussin noise. The performance of these networks is compared to the traditional extended Kalman filtering approach and to published results for model‐based nonlinear programming techniques for data reconciliation. The recurrent network architecture is shown to provide comparable, if not superior, results when compared to traditional methods. The networks used were trained using conventional nonlinear programming techniques in a batch fashion.