Abstract An intelligent computation approach to time and cost reduction in process planning of cold forging operations is illustrated. The problem taken into consideration is the generation of optimized working sequences in the fabrication of multi-diameter shafts through multiple-step cold forging. A supervised learning neural network paradigm was employed in order to identify the technologically feasible working sequences to be considered for process planning decision making. The process planner can then select the appropriate solution according to his experience or resort to further methods of detailed analysis (e.g. FEM analysis), with the advantage of applying time consuming numerical investigations only to a small number of cases suggested by the intelligent computing system. Neural network training and testing allowed to verify the system performance in classifying working sequence feasibility and its computational speed in providing technologically acceptable working sequences for process planner consideration.
[1]
R. Palmer,et al.
Introduction to the theory of neural computation
,
1994,
The advanced book program.
[2]
K. Sevenler,et al.
Forming-sequence design for multistage cold forging
,
1987
.
[3]
Timothy Masters,et al.
Practical neural network recipes in C
,
1993
.
[4]
K. Osakada,et al.
Neural Networks for Process Planning of Cold Forging
,
1991
.
[5]
Scott E. Fahlman,et al.
An empirical study of learning speed in back-propagation networks
,
1988
.
[6]
N. Alberti,et al.
Knowledge-Based Systems and F.E. Simulations in Metal-Forming Processes Design An integrated Approach
,
1991
.
[7]
Paolo Francesco Bariani,et al.
Computer-Aided Cold Forging Process Design: A Knowledge-Based System Approach to Forming Sequence Generation
,
1988
.