Type-1 and type-2 radial basis function neural networks Mandami system to evaluate quality features

This paper presents a methodology that uses the central composite design and radial basis function neural networks in type-1 or interval type-2 model to generate network evaluates quality features an industrial image processing. The includes couple of functions as Huygen’s tractrix triangular membership complementary contributions have not been reported literature functions. advantage using this proposal is training required get accurate result, also generation IT2 RBFNN fuzzy rule base for evaluating characteristics simplified by method statistical indicators extracted from product specification data. Experimental results show error reduction 90% when Mandami Radial was compared against its counterpart Gaussian onto network. On other hand, implementation tractrix, found 50% comparison function.