Dakota Reference Manual
Version 6.2
LargeScale Engineering Optimization and Uncertainty Analysis

A model whose responses are computed through the use of a subiterator
Alias: none
Argument(s): none
Required/Optional  Description of Group  Dakota Keyword  Dakota Keyword Description  

Optional  optional_interface_pointer  Pointer to interface that provides nonnested responses  
Required  sub_method_pointer  The sub_method_pointer specifies the method block for the subiterator 
Instead of appealing directly to a primary interface, a nested model maps variables to responses by executing a secondary iterator, or a "subiterator". In other words, a function evaluation of the primary study consists of a solution of an entire secondary study  potentially many secondary function evaluations.
The subiterator in turn operates on a submodel. The subiterator responses may be combined with nonnested contributions from an optional interface specification.
A sub_method_pointer
must be provided in order to specify the method block describing the subiterator. The remainder of the model is specified under that keyword.
A optional_interface_pointer
points to the interface specification and optional_interface_responses_pointer
points to a responses specification describing the data to be returned by this interface). This interface is used to provide nonnested data, which is then combined with data from the nested iterator using the primary_response_mapping
and secondary_response_mapping
inputs (see mapping discussion below).
An example of variable and response mappings is provided below:
primary_variable_mapping = '' '' 'X' 'Y' secondary_variable_mapping = '' '' 'mean' 'mean' primary_response_mapping = 1. 0. 0. 0. 0. 0. 0. 0. 0. secondary_response_mapping = 0. 0. 0. 1. 3. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 1. 3. 0.
The variable mappings correspond to 4 toplevel variables, the first two of which employ the default mappings from active toplevel variables to submodel variables of the same type (option 3 above) and the latter two of which are inserted into the mean distribution parameters of submodel variables 'X'
and 'Y'
(option 1 above). The response mappings define a 3 by 9 matrix corresponding to 9 inner loop response attributes and 3 outer loop response functions (one primary response function and 2 secondary functions, such as one objective and two constraints). Each row of the response mapping is a vector which is multiplied (i.e, with a dotproduct) against the 9 subiterator values to determine the outer loop function. Consider a UQ example with 3 response functions, each providing a mean, a standard deviation, and one level mapping (if no level mappings are specified, the responses would only have a mean and standard deviation). The primary response mapping can be seen to extract the first value from the inner loop, which would correspond to the mean of the first response function. This mapped subiterator response becomes a single objective function, least squares term, or generic response function at the outer level, as dictated by the toplevel response specification. The secondary response mapping maps the fourth subiterator response function plus 3 times the fifth subiterator response function (mean plus 3 standard deviations) into one toplevel nonlinear constraint and the seventh subiterator response function plus 3 times the eighth subiterator response function (mean plus 3 standard deviations) into another toplevel nonlinear constraint, where these toplevel nonlinear constraints may be inequality or equality, as dictated by the toplevel response specification. Note that a common case is for each subiterator response to be mapped to a unique outer loop response (for example, in the nested UQ case where one wants to determine an interval on each inner loop statistic). In these simple cases, the response mapping would define an identity matrix.
These keywords may also be of interest: