Static compensation on the basis of nnbm predictor under foundationtm fieldbus

This paper deals with the problem of disturbance compensation by mans of a novel feedforward control procedure. It consists in the additive association of a conventional feedback control action with the prediction of the steady state control effort necessary to keep the controlled plant under setpoint requirements. Such steady state control effort is achieved by means of inverse neural network based modelling prediction. Predictors are based in an inverse neural network steady state plant model. Implementation procedure is carried out with the facilities supplied by a FOUNDATIONT^TM fieldbus compliant tool which manage databases, neural network structures and training algorithms.