For access to this article, please select a purchase option:
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Your recommendation has been sent to your librarian.
The paper discusses several methods of modelling complex nonlinear dynamics using neural networks. Particular reference is made to the problem of modelling direction-dependent relationships. A typical example of this would be top product composition control in a distillation column, where it is easier (i.e. faster) to make the product less pure than it is to make it more pure by an equivalent amount. Recurrent neural networks are identified as a potential method of modelling this type of relationship. The particular architecture chosen for this example is referred to as ‘semirecurrent’, since only past values of the predictions of the network are fed back to the input layer. This architecture is successfully used to model direction-dependent relationships in both simulated and actual industrial process data.
Inspec keywords: modelling; large-scale systems; multilayer perceptrons; intelligent control; chemical variables control; recurrent neural nets; distillation; process control; neural net architecture; nonlinear control systems; feedforward neural nets
Other keywords:
Subjects: Neural nets (theory); Multivariable control systems; Control technology and theory (production); Chemical variables control; Industrial processes; Simulation, modelling and identification; Chemical industry; Neurocontrol; Nonlinear control systems; Control applications in chemical and oil refining industries