AI-FORM optimizer can execute multi-criteria non-linear optimization based on DOE/GA/PSO as known in Artificial Intelligence.
- Multiple Criteria Targets: All physical problems could be optimized, including the thickness, thinning, displacement, stress and strain, contact stress and force, FLD, blank pattern, etc. For example: Single or multiple targets of the simulation, what the design engineer is trying to achieve like to maximize the yield, minimize springback or minimize material thinning and balance the final blank pattern during the forming process.
- Multiple Design or Process Variable: Design elements that are allowed to vary, could be the Parametric CAD Geometries like die face gape and dimensions, addendum dimension, drawbead dimension even original stamping part, or process parameters, like material properties, friction factor, or the holding force.
- Genetic Algorithm and PSO in AI-FORM Optimizer checks the results of each optimization iteration like blank thickness and intelligently sets the new value for the design variables like size and radius for the addendum. Such iterations are continued until the targets are achieved.
- Complex user formulas are supported.
DESIGN OF EXPERIMENTS
The DOE component enables engineers to quickly assess the impact of various design variables based on a set of objectives and identify significant interactions. The design data produced by DOE runs can also be used with approximation models for use with optimization methods.
The system supports full factors, Taguchi DOE method and user-defined formula for a condition.
AI-FORM provides a comprehensive selection of parallelized optimization techniques that can be applied to a variety of problems. It also includes techniques that can handle multi-objective optimization problems.
This process enables simulation models to be calibrated by minimizing any variety of different error measures using optimization techniques. Target data can be imported as experimental or simulation results.
AI-FORM offers powerful real-time tools to interpolate results of computationally intensive realistic simulations. Approximation models are automatically cross-validated to ensure accurate predictions.
AI-FORM Optimizer enables lower research expenditures and shorter implementation time. The primary purpose of the system is to relieve a designer or researcher of the sufficiently complex and very labor-intensive process of searching for optimal system design parameters which simultaneously meet a significant number of sometimes controversial requirements.
AI-FORM provides rich tools to monitor the optimization process and analyze optimization calculation results.
- Visualization: 2D, 3D, surface map, contour map, etc.
- Data could be directly inputted into Microsoft Excel for subsequent analysis.
- Statistics, regression, ANOVA.
- Parallel coordinator plot and Pareto graphic plot.