'Soft-sensor' for real-time monitoring of melt viscosity in polymer extrusion process

Laboratory capillary rheometer and side-stream rheometer for melt viscosity measurement in polymer extrusion have shown to be unsuitable for real-time monitoring and control, due to their measurement delay. Existing in-line rheometer designs disturb the melt flow or restrict throughput, limiting their industrial application. In this paper, a novel soft-sensor approach is proposed, aiming to tackle this problem. The soft-sensor involves a non-linear finite impulse response model with adaptable linear parameters for real-time prediction of the melt viscosity based on the process inputs; the model output is then used as an input of a model with a simple fixed structure to predict the barrel pressure which can be measured online. Finally, the predicted pressure is compared to the measured value and the corresponding error is used as a feedback signal to correct the viscosity estimate. This novel feedback structure enables the online adaptability of the viscosity model in response to modeling errors and disturbances, hence producing a reliable viscosity estimate. The experimental results confirm the effectiveness of the proposed 'soft-sensor' method for real-time monitoring and control of polymer extrusion processes.