R. Lanouette et al., IMPROVEMENT OF MODELING D-OPTIMAL DESIGN-DATA WITH NEURAL NETWORKS - RADIAL BASIS FUNCTION NEURAL NETWORKS ARE VERY ROBUST, Pulp & paper Canada, 99(9), 1998, pp. 34-38
D-Optimal design can be used to study the influence of numerous parame
ters in a process, with a limited number of experimental paints, Howev
er, the multiple regression techniques normally used to analyze the da
ta coming from this design. can lend to a false interpretation. In thi
s study, two different neural networks have been used to obtain a bett
er modeling of the process. Advantages and disadvantages of both metho
ds will be discussed.