Use of fuzzy logic for modeling the growth of Fe2B boride layers during boronizing

In this study, the evaluation of the phase Fe2B growth in AISI 1045 steel during paste boronizing was carried out. Fuzzy logic Mamdani and Takagi–Sugeno methods were used as the technical model. The experimental procedure was performed in a solid paste medium, at temperatures range of 1193–1273 K; for 2, 4 and 6 h; and modifying the boron potential (paste thickness) at the metal surface. Membership functions were proposed for fuzzification and defuzzification of the input and output values. The system structure utilized was based on two membership functions for the input (time and paste thickness), and one for the output (layer growth). Comparing the results, given by the fuzzy logic system with experimental data, the medium error generated from the Mamdani method was 2.61%, and from the Takagi–Sugeno was 3.62%. It is concluded that the technique of fuzzy logic is an alternative for modeling the growth of borided phases.