Configuring the Adaptive DOE Optimization Technique

Adaptive DOE optimization runs a series of space-filling DOEs, where each iteration is centered around a projection of the improvement from the previous DOE.

See Also
Adaptive DOE Optimization
Configuring the Technique and the Execution Options
  1. From the Flow section of the action bar, click Optimization , and drop it on the process diagram.
  2. Double-click Optimization .
    The Optimization Editor appears.
  3. From the General tab's Optimization Technique list, select Adaptive DOE.
  4. In the Optimization Technique Options area, enter or select the following:
    OptionDescription
    Number of Adaptive Iterations The number of adaptive iterations to be performed by the optimizer. To find the more accurate optimum, for each adaptive iteration the design space is shrunk and expanded around the earlier iteration optimum point. Integers greater than zero are accepted. The default value is 10; however, problems with small nonlinear coupling between the parameters can be solved with as few as four iterations, while highly coupled parameter spaces may take up to 30.
    Number of Points per Iteration The number of simulations to be run for each adaptive iteration to find the optimum. The number of points per iteration must at least be twice the number of design variables. For more than two design variables, the number of points per iteration should be at least four times the number of design variables. For highly coupled problems, you should enter a low number of points per iteration with a high number of adaptive iterations. For uncoupled problems, you should enter a high number of points per iteration with a lower number of adaptive iterations.
    Initial Box The scaling factor applied to the box formed by each design variable's lower and upper bound, producing an interval for each variable centered on the midpoint of its range. The scaling factor is applied only during the first iteration. The default value of 1.0 indicates that the first iteration will choose design points scattered throughout the bounded range.
    Significant Step Size The Adaptive DOE technique optimizes the position of points in the space by maximizing the distance from any other point. Enter a small Significant Step Size (for example, 0.001) to find more subtle gradients. Enter a larger Significant Step Size (for example, 0.05) to filter noise.
    Max Failed Runs The maximum number of failed subflow evaluations that can be tolerated by the optimization technique. If the number of failed runs exceeds this value, the optimization component terminates execution. To disable this feature, specify any negative value (for example, -1). When you specify a negative value, the optimization continues execution despite any number of failed subflow runs.
    Failed Run Penalty Value The value of the Penalty parameter that is used for all failed subflow runs. The default value is 1⁢ ×⁢ 1030.
    Failed Run Objective Value The value of the Objective parameter that is used for all failed subflow runs. The default value is 1⁢ ×⁢ 1030.
    Use fixed random seed If this option is selected, the random number generator used by the optimization algorithm is seeded using the Random seed value.

    If this option is not selected, the random number generator is seeded by using the clock time at the moment of execution.

    Random seed value The random number generator used by the optimization algorithm is seeded using the value specified. All executions of the Optimization adapter will use the same sequence of random numbers and, therefore, will produce the same design points. This arrangement is useful for debugging the optimization process when you want to reproduce the same sequence of design points.
  5. Click Ok to save your changes and to close the Optimization Editor.