“…Starting from the empirical model so optimized (from Equation (2)), i.e., once found , , , , for each output variable, a different fuzzy regression model can be written, as described by Equation (3): where is the fuzzy function determined through the Transformation Method [ 46 ], while , , , , , are fuzzy numbers. Such an approach is proved to be able to propagate both sources of uncertainty, i.e., the random one due to the process variability and the systematic one due to the simplification introduced by the model itself, to the output qualities [ 51 , 52 ]. This is carried out by implementing the fuzzy arithmetic as a series of interval computations, i.e., α-cut strategy, which are numerically solved by sampling the interval based on a defined schema.…”