Neural modelling of Mooney viscosity of polybutadiene rubber

Mooney viscosity is one of the important quality properties of polybutadiene rubber (PBR). It is important to implement appropriate measures to maintain and guarantee a uniform product quality required by the rubber processing industries. One major step towards quality assurance is the on line quality prediction of the product from the process parameters. This can be accomplished by developing a reliable model that predicts product quality as a function of process parameters. Artificial neural networks (ANN), which are capable of mapping highly complex and non-linear dependencies, have been adapted to develop models to predict Mooney and solution viscosity of PBR from process variables. Of the different networks trained with input-output data collected from plant history to predict Mooney and fluid viscosity (FV) from process variables, generalized regression neural networks (GRNN) mapped the input-output well compared to that of other networks. The predicted Mooney viscosity of PBR from the reactor outlet by GRNN was deviated by mean square error of 0.0252 when tested with new data.