Title :
Modelling of crude oil blending via discrete-time neural networks
Author :
de Jesus Rubio, J. ; Wen Yu
Abstract :
Crude oil blending is an important unit operation in petroleum refining industry. A good model for the blending system is beneficial for supervision operation, prediction of the export petroleum quality and realizing model-based optimal control. Since the blending cannot follow the ideal mixing rule in practice, we propose a static neural network to approximate the blending properties. By input-to-state stability and dead-zone approaches, we propose a new robust learning algorithm and give theoretical analysis. Real data is applied to illustrate the neuro modeling approache.
Keywords :
Automatic control; Backpropagation algorithms; Mathematical model; Neural networks; Petroleum; Predictive models; Refining; Robust stability; Stability analysis; Uncertainty;
Conference_Titel :
Electrical and Electronics Engineering, 2004. (ICEEE). 1st International Conference on
Conference_Location :
Acapulco, Mexico
Print_ISBN :
0-7803-8531-4
DOI :
10.1109/ICEEE.2004.1433920