forum.alglib.net

Hi,

I'm completely new to this forum so please excuse me if my questions are very basic.
My interest in this amazing libary is currently driven by the following:

At present I use Excel's Solver to fit X-ray diffraction patterns of pure phases to other patterns which are mixtures of phases.

The patterns consist of thousands of data points (x,y) and frequently a dozen or more individual pure phase patterns may be required to fit the pattern of a mixture.

The mixture patern is simulated as a weighted sum of pure patterns, the best fit being obtained by minimising some objective function.

I have read through quite a few posts on this forum to see if I can identify what method would be preferable for this type of problem, (I wondered if the 'lsfit subpackage' was the one I should try) but there appear to be so many variations, I don't know how to identify the best approach.

I also have no idea how to code it (vb.net is the language I have some experience with) so any advice there would be welcome, but first and foremost can someone point me to the best method and variant thereof that I should be looking at for this type of problem?

many thanks