Growth kinetics of borided layers: Artificial neural network and least square approaches

The present study evaluates the growth kinetics of the boride layer Fe₂B in AISI 1045 steel, by means of neural networks and the least square techniques. The Fe₂B phase was formed at the material surface using the paste boriding process. The surface boron potential was modified considering different boron paste thicknesses, with exposure times of 2, 4 and 6 h, and treatment temperatures of 1193, 1223 and 1273 K. The neural network and the least square models were set by the layer thickness of Fe₂B phase, and assuming that the growth of the boride layer follows a parabolic law. The reliability of the techniques used is compared with a set of experiments at a temperature of 1223 K with 5 h of treatment time and boron potentials of 2, 3, 4 and 5 mm. The results of the Fe₂B layer thicknesses show a mean error of 5.31% for the neural network and 3.42% for the least square method.