Prediction and Optimization of Heavy Clay Products Quality - Advanced Materials for Agriculture, Food and Environmental Safety - page 117

Figure 4.4 h e ef ects of most important parameters on optimization function.
4.4 Conclusions
h e ANN-based model was developed for prediction of CSB , CSC , WAT ,
WA B , WAC , FS , WLFT , WLFB , WLFC , and VMC for a wide range of
experimental conditions. h e model was able to predict experimental data
successfully, with ease of implementing it for design and control of the pro-
cesses and also the ef ective use for predictive modeling and optimization.
As compared to SOP models, ANN models yield a better i t of experimen-
tal data, according to r 2 and SOS of both models.
Taking into account that a considerable amount and wide variety of data
were used in the present work to obtain the ANN model, and considering
that the model turned out to yield a sui ciently good representation of