I have great hope that the CAD & FEM field will benefit greatly from LLM use. To my understanding we currently don't have a free CAD kernel and broadly applicable FEM solver because these are just too hard to make because geometry and physics are hard unforgiving problems. But all pieces of information are available and many implementations covering some details exist. So, the task is a lot of literature research and putting everything together and that's where LLM based agents should shine.
Of course we won't 1-shot a new CAD kernel but the human work will likely shift more towards identifying failure modes, specifying test cases and sometimes solving really hard details. Sometimes even working out details that have no precedent in literature or free code.
There are really good free and open source research FEA & CFD codes available, like FEniCS, Moose, Nek5000, OpenFOAM, SU2 and more. However, being research codes they can be difficult to learn and sometimes even compile and get running, that is why FEATool Multiphysics has been developed [1] - an integrated physics simulation platform with the aim of allowing users to run "any" CAE simulation solver from an easy to use GUI and unified scripting environment.
I have great hope that the CAD & FEM field will benefit greatly from LLM use. To my understanding we currently don't have a free CAD kernel and broadly applicable FEM solver because these are just too hard to make because geometry and physics are hard unforgiving problems. But all pieces of information are available and many implementations covering some details exist. So, the task is a lot of literature research and putting everything together and that's where LLM based agents should shine.
Of course we won't 1-shot a new CAD kernel but the human work will likely shift more towards identifying failure modes, specifying test cases and sometimes solving really hard details. Sometimes even working out details that have no precedent in literature or free code.
There are really good free and open source research FEA & CFD codes available, like FEniCS, Moose, Nek5000, OpenFOAM, SU2 and more. However, being research codes they can be difficult to learn and sometimes even compile and get running, that is why FEATool Multiphysics has been developed [1] - an integrated physics simulation platform with the aim of allowing users to run "any" CAE simulation solver from an easy to use GUI and unified scripting environment.
[1] https://www.featool.com
> broadly applicable FEM solver
gmsh/Calculix is great. Sure it doesn't reach quite as far as Ansys, but you can solve real meaningful problems with it.
> we currently don't have a free CAD kernel
BRLCAD is OK and OCCT is pretty good. The hard part isn't the CAD kernel; it's the user interface and interconnects.
I only got to know calculix because that's one of the FEM solver FreeCAD use