چکیده مقاله
A neural network with feed forward topology and back propagation algorithm was used to predict the effects of chemical composition and tensile test parameters on hardness of Heat affected zone HAZ in X70 pipeline steels The weight percent of chemical compositions carbon equivalent, based upon the International Institute of Welding equation CEIIW , the carbon equivalent, based upon the chemical portion of the Ito Bessyo carbon equivalent equation CEPcm , the sum of the niobium,vanadium and titanium concentrations VTiNb , the sum of the niobium and vanadium concentrations NbV , The sum of the chromium, molybdenum, nickel and copper concentrations CrMoNiCu , yield strength at 0 005 offset YS , ultimate tensile strength UTS and percent elongation El were considered as input parameters to the network; while Vickers microhardness with 10 N load HV was considered as its output For purpose of constructing these models, 104 different data were gathered from the experimental results Scatter diagrams and two statistical criteria: absolute fraction of variance R2 and mean relative error MRE were used to evaluate the prediction performance of the developed model The developed model can be further used in practical applications of alloy and thermo mechanical schedule design in manufacturing process of pipeline steels
کلیدواژهها
نویسندگان
شیوه ارجاع
Khalaj, Gholamreza and Khalaj, Mohammad-Javad,1395,Artificial neural networks to prediction hardness of HAZ with chemical composition and tensile test of X70 pipeline steels,The second international conference on welding and non-destructive testing, the 17th national conference on welding and inspection, and the sixth national conference on non-destructive testing,Isfahan
ارائهشده در
مجموعه مقالات دومین کنفرانس بین المللی جوشکاری و آزمایش های غیرمخرب، هفدهمین کنفرانس ملی جوش و بازرسی و ششمین کنفرانس ملی آزمایش های غیرمخرب30 آذر 1395 · اصفهان