engleski

Modeling of chemical reactor dynamics by nonlinear principal components

The modelling of nonisothermal continuous stirred chemical reactor dynamics by lin-ear and nonlinear principal components methods is investigated. The derived models are analysed with respect of their ability to predict existence of the reactor multiple steady states and their use for adaptive on-line process control. Time evolution of the state variables is approximated by a single step finite difference prediction equation. Nonlinear principal components are determined by a feedforward neural network with a single hidden layer. Input and output patterns are jointly projected to a two dimen-sional surface yielding an implict process model. The ability of implicit models to predict controlled and manipulative variables without the need for separate model de-velopment for the direct and inverse models makes them ideally applicable in adap-tive internal model control loops. The model correctly predicts the existence of three steady states and provides an excellent fit to untrained samples of patterns under vari-ous dynamic conditions. The linear models based on a partial least squares algorithm provide fit to patterns under unsteady conditions, but they fail to predict multiple steady states in chemical reacting systems which makes them, under this condition, unsuitable for process control.

Neural networks; Principal components; Implicit model; Multiplicity of steady states; Internal model control

nije evidentirano