DocumentCode :
389447
Title :
Accurate inference of variables using artificial neural networks
Author :
Ackermann, D.W. ; Bodenstein, C.P.
Author_Institution :
Sch. for Electr. & Electron. Eng., Potchefstroom Univ., South Africa
Volume :
6
fYear :
2002
fDate :
6-9 Oct. 2002
Abstract :
Accurate measurements are essential for feature extraction and accurate control of systems. Often, however, accurate measurements cannot be performed directly due to the inaccessibility in systems to place sensors or non-ideal sensor characteristics. Inference measurements (also called soft sensors) enables estimates of variables in a system from directly measurable variables. This paper shows which directly accessible variables should be used for accurate inference by exploring various systems. Neural networks have universal mapping capabilities, and are used to perform inference measurements on nonlinear dynamic systems. The results show which variables should be used in order to perform accurate inference of unknown variables.
Keywords :
feedforward neural nets; inference mechanisms; measurement systems; multilayer perceptrons; nonlinear dynamical systems; sensors; artificial neural networks; feature extraction; feedforward neural network; inference of variables; measurements; nonlinear dynamic systems; sensors; soft sensors; universal mapping; unknown variables; Artificial neural networks; Engines; Feature extraction; Frequency; Neural networks; Nonlinear dynamical systems; Nonlinear equations; Transducers; Transfer functions; Vectors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Systems, Man and Cybernetics, 2002 IEEE International Conference on
ISSN :
1062-922X
Print_ISBN :
0-7803-7437-1
Type :
conf
DOI :
10.1109/ICSMC.2002.1175644
Filename :
1175644
Link To Document :
بازگشت