Modelling of gasoline blending via discrete-time neural networks

Gasoline blending is an important operation in chemical industry. A good model for the blending process is beneficial for supervision operation, prediction of gasoline qualities and realizing model-based optimal control. Gasoline blending process includes static and dynamic properties which are corresponded to thermodynamic and the storage tank respectively. Since the blending does not follow the ideal mixing rule in practice, we propose static and dynamic neural networks to approximate the blending process. Input-to-state stability approach is applied to access new robust learning algorithms of the neural networks. Numerical simulations are provided to illustrate the neuro modelling approaches.

[1]  A. Michel,et al.  Robustness analysis of a class of discrete-time systems with applications to neural networks , 1999, Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251).

[2]  Liang Jin,et al.  Stable dynamic backpropagation learning in recurrent neural networks , 1999, IEEE Trans. Neural Networks.

[3]  Johan A. K. Suykens,et al.  NLq theory: checking and imposing stability of recurrent neural networks for nonlinear modeling , 1997, IEEE Trans. Signal Process..

[4]  Jose Alvarez-Ramirez,et al.  Robustness of a Class of Bias Update Controllers for Blending Systems , 2002 .

[5]  Q. Song,et al.  Robust training algorithm of multi-layered neural networks for identification of nonlinear dynamic systems , 1997 .

[6]  Marios M. Polycarpou,et al.  Learning and convergence analysis of neural-type structured networks , 1992, IEEE Trans. Neural Networks.

[7]  Cheng-Ching Yu,et al.  Coordinated control of blending systems , 1998, IEEE Trans. Control. Syst. Technol..

[8]  A. Muller.  New method produces accurate octane blending values , 1992 .

[9]  M. D. Bashir,et al.  Predict octane number for gasoline blends , 1993 .

[10]  Dale E. Seborg,et al.  Constrained parameter estimation with applications to blending operations , 2000 .

[11]  V. G. Rau,et al.  Robust training algorithm of multilayered neural networks for identification of nonlinear dynamic systems , 1998 .

[12]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[13]  Zhong-Ping Jiang,et al.  Input-to-state stability for discrete-time nonlinear systems , 1999 .

[14]  Marios M. Polycarpou,et al.  High-order neural network structures for identification of dynamical systems , 1995, IEEE Trans. Neural Networks.

[15]  Johan A. K. Suykens,et al.  Lur'e systems with multilayer perceptron and recurrent neural networks: absolute stability and dissipativity , 1999, IEEE Trans. Autom. Control..

[16]  Frank L. Lewis,et al.  Identification of nonlinear dynamical systems using multilayered neural networks , 1996, Autom..

[17]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[18]  Alexander S. Poznyak,et al.  Multilayer dynamic neural networks for non-linear system on-line identification , 2001 .

[19]  John F. Forbes,et al.  Model-based real-time optimization of automotive gasoline blending operations , 2000 .

[20]  J. Fraser Forbes,et al.  Real-time optimization under parametric uncertainty: a probability constrained approach , 2002 .