This is the first attempt at process modeling in terms of predictive control using a hierachical method based on regression analysis and Artificial Neural Networks (ANNs). This hierachical method leads to the reliability improvement of neural model of the process in predicting (extrapolation and interpolation) the process output. Such an outlook makes it possible to predict the proper input settings which can achieve a desired process output by designing various scenarios for process set up. This approach is applied to tile industry for spray drying process and in order to determine the amount of improvement, two models (i)Neural model of process taking general approach using Multilayer Perceptron based on Back Propagation algorithm and (ii)Mixed-regression neural model of process taking focus approach in architecture of neural model are designed to evaluate the reliability of prediction of spray drying process output via three criteria. These criteria include mean relative error, root mean squre error and coefficient of determination. The results indicate that the Mixed regression-neural model leads to the best results in prediction (extrapolation and interpolation) of spray drying process output.
Neshat, N., & Mahlooji, H. (2009). Predictive Process Control Using Artificial Neural Networks (ANNs) and A Combined Method of Regression Analysis and ANNs. Industrial Management Journal, 1(3), -.
MLA
Najmeh Neshat; Hashem Mahlooji. "Predictive Process Control Using Artificial Neural Networks (ANNs) and A Combined Method of Regression Analysis and ANNs". Industrial Management Journal, 1, 3, 2009, -.
HARVARD
Neshat, N., Mahlooji, H. (2009). 'Predictive Process Control Using Artificial Neural Networks (ANNs) and A Combined Method of Regression Analysis and ANNs', Industrial Management Journal, 1(3), pp. -.
VANCOUVER
Neshat, N., Mahlooji, H. Predictive Process Control Using Artificial Neural Networks (ANNs) and A Combined Method of Regression Analysis and ANNs. Industrial Management Journal, 2009; 1(3): -.
)