TY - JOUR
T1 - Growth kinetics of borided layers
T2 - Artificial neural network and least square approaches
AU - Campos, I.
AU - Islas, M.
AU - Ramírez, G.
AU - VillaVelázquez, C.
AU - Mota, C.
N1 - Funding Information:
This work has been supported by the research grant 20070130 of Instituto Politécnico Nacional at Mexico. The authors wish to thank Mr. Carlos Flores and Luis Hernández Simón for their valuable cooperation.
PY - 2007/5/15
Y1 - 2007/5/15
N2 - The present study evaluates the growth kinetics of the boride layer Fe 2 B in AISI 1045 steel, by means of neural networks and the least square techniques. The Fe 2 B 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 Fe 2 B 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 Fe 2 B layer thicknesses show a mean error of 5.31% for the neural network and 3.42% for the least square method.
AB - The present study evaluates the growth kinetics of the boride layer Fe 2 B in AISI 1045 steel, by means of neural networks and the least square techniques. The Fe 2 B 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 Fe 2 B 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 Fe 2 B layer thicknesses show a mean error of 5.31% for the neural network and 3.42% for the least square method.
KW - Boride layers
KW - Boriding process
KW - Boron paste
KW - Growth kinetics
KW - Least square method
KW - Neural networks
UR - http://www.scopus.com/inward/record.url?scp=34247188013&partnerID=8YFLogxK
U2 - 10.1016/j.apsusc.2007.01.070
DO - 10.1016/j.apsusc.2007.01.070
M3 - Artículo
SN - 0169-4332
VL - 253
SP - 6226
EP - 6231
JO - Applied Surface Science
JF - Applied Surface Science
IS - 14
ER -