Title :
Bayesian neural networks on the inference of distillation product quality
Author :
Barbosa, C.Hall ; Melo, B. ; Vellasco, M. ; Pacheco, M. ; Vasconcellos, L.P.
Abstract :
The control of the distillation process in oil refineries requires the evaluation of product quality throughout the operation of the plant. This paper uses Bayesian neural networks, combined to several pre-processing and variable selection techniques, to develop systems for inferencing the quality of distillation products, for REPAR refinery (Refinaria do Parana), operated by PETROBRAS.
Keywords :
distillation; inference mechanisms; neural nets; oil refining; process control; quality control; Bayesian neural networks; REPAR refinery; diesel; distillation; inference; oil refinery; process control; quality control; Backpropagation; Bayesian methods; Control theory; Input variables; Neural networks; Neurons; Pattern recognition; Principal component analysis; Rivers; Testing;
Conference_Titel :
Neural Networks, 2002. SBRN 2002. Proceedings. VII Brazilian Symposium on
Print_ISBN :
0-7695-1709-9
DOI :
10.1109/SBRN.2002.1181447
