This study deals with a finite-element method application for die-casting dies with freeform surfaces, in order to find an accurate and fast determination of the material injection gate location. To avoid many of the influencing factors, first the part-line of the parameter equation is created using an abductive neural network to limit the range of the gate locations. From the various gate locations in the part-line of the shell, the location producing the minimum warp is found.A prediction of the warp is then found using an abductive neural network. A simulated annealing (SA) optimisation algorithm with a performance index is then applied to the neural network for searching for the optimal position of the gate on the freeform surface, and to obtain a satisfactory result. The method can be applied in die-casting die design, in order to reduce the high cost of trial dies.
[1]
C. D. Gelatt,et al.
Optimization by Simulated Annealing
,
1983,
Science.
[2]
N. Metropolis,et al.
Equation of State Calculations by Fast Computing Machines
,
1953,
Resonance.
[3]
G. A. Miller.
THE PSYCHOLOGICAL REVIEW THE MAGICAL NUMBER SEVEN, PLUS OR MINUS TWO: SOME LIMITS ON OUR CAPACITY FOR PROCESSING INFORMATION 1
,
1956
.
[4]
Manabu Gotoh,et al.
Elastic-plastic FEM analysis of the heading process and the die-forging process of a gear blank
,
1991
.
[5]
Yong-Taek Im,et al.
Finite elements simulation of solidification with momentum, heat and species transport
,
1995
.