Jt. Liu et al., Prediction of the flow stress of high-speed steel during hot deformation using a BP artificial neural network, J MATER PR, 103(2), 2000, pp. 200-205
The hot deformation behavior of T1 (W18Cr4V) high-speed steel was investiga
ted by means of continuous compression tests performed on a Gleeble 1500 Th
ermomechanical simulator over a wide range of temperatures (950-1150 degree
s C) with strain rates of 0.001-10 s(-1) and true strains of 0-0.7. The flo
w stress under the above-mentioned hot deformation conditions is predicted
using a BP artificial neural network. The architecture of the network inclu
des three input parameters: strain rate epsilon, temperature T and true str
ain epsilon; and just one output parameter: the flow stress sigma. Two hidd
en layers are adopted, the first hidden layer including nine neurons and th
e second 10 neurons. It has been verified that a BP artificial neural netwo
rk with 3-9-10-1 architecture can predict the flow stress of high-speed ste
el during hot deformation very well. Compared with the prediction method of
flow stress using the Zener-Holloman parameter and hyperbolic sine stress
function, the prediction method using the BP artificial neural network has
higher efficiency and accuracy. (C) 2000 Elsevier Science S.A. All rights r
eserved.