Hello everyone,
I am currently using Isight to solve an optimization problem, and my goal is to implement the Successive Response Surface Method. This approach seems similar to the Approximation Loop technique described within the Exploration Component. According to the documentation:
"A linear response surface model (RSM) approximation is created and initialized by executing a suitable DOE design matrix using an orthogonal array at the smallest suitable size, such that at least N + 1 design points are included. N is the number of inputs of the approximation (the design variables)."
However, after running the component with only one design variable, I noticed that the number of iterations is equal to the number of simulations performed. This doesn't seem correct to me, as I would expect that creating a response surface with one design variable should require at least 2 DOE points.
More specifically, I expected that in each iteration, a DOE matrix would be generated to fit the response surface, but this doesn't seem to be happening.
Does anyone have suggestions on how to address this issue? Is there a way to increase the number of DOE points for each iteration while keeping just one design variable?
Thank you in advance for your help!
