Authors : R. Ferreiro Garcia, J. Luis Calvo Rolle, M. Romero Gomez and A. DeMiguel Catoira
Abstract: In-line mixing problems affected by controlled variables, such as conductivity, pH, viscosity which strongly depends on complementary physical variables disturbances, such as temperature and pressure variations are appropriate candidates to be solved using neural network model-based functional approximation techniques. The aim for this type of non-linear control problems is to compute the proportions of input product flow rates yielding a final product, thus satisfying as much physical properties as manipulated input flow rates exists in a considered plant. The core of the contribution is a functional approximation approach implemented on the basis of back propagation neural networks associated to the proposed control design strategies (CVFFC and CVFBC).
R. Ferreiro Garcia, J. Luis Calvo Rolle, M. Romero Gomez and A. DeMiguel Catoira, 2014. In-Line Mixing on Concentration Control Using Computed Multi-Variable Neural Networks Based Techniques. International Journal of Signal System Control and Engineering Application, 7: 1-10.