Abstract: This study deals with the problem of disturbance compensation by means of a novel feedforward control procedure. It is based in the association of a conventional feedback control action with the feedforward action consisting in 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 a neural network based inverse model which actuates as a control effort predictor. Predictors are based in an inverse neural network steady state plant model. Implementation procedure is carried out with the facilities supplied by a FOUNDATION™ Fieldbus compliant tool which manage databases, neural network structures and back-propagation training algorithms.