Abstract
Food extrusion processes are becoming critical in the production of novel nutritional food products, whereas the design of advanced process control, monitoring and diagnostics systems has not been actively pursued in the food processing industry. The above realization results from the inherent properties of extrusion processes that lead to highly complex dynamic behavior, nonlinear characteristics, as well as the considerable variability of raw material and sensitivity to seasonal variation and market conditions. In order to develop reliable and well-performing advanced process monitoring and diagnostic systems for achieving improved product quality and cost-effective operation, the neural network-based modeling technique for the extrusion cooking process was studied, that can be digitally implemented using a computer. The comparison of the model testing results using real process data showed that the neural network-based modeling technique not only is superior to the statistical RSM modeling technique, but also has the ability to deal with complex and high-dimensional systems and capture their steady state behavior. Results and findings of this research provided the appropriate systematic framework for the development of a steady state computer-based modeling framework of extrusion cooking processes. It is anticipated, that the proposed framework could remarkably reduce the time and cost required for the development of a new and accurate process model, in order to describe the process behavior over a wide operating regime.
Jang, Won-Hyouk (2001). Digital neural network-based modeling technique for extrusion processes. Master's thesis, Texas A&M University. Available electronically from
https : / /hdl .handle .net /1969 .1 /ETD -TAMU -2001 -THESIS -J35.