← Use cases

Generative design verified by simulation

Based on an FEM / CFD model and the geometry, a generative network (GAN) or a reinforcement learning agent creates solution variants, and each of them is verified by our solvers.

Training
Diagram: the mathematical model, geometry and constraints go to a GAN generator or reinforcement learning agent, pre-trained with supervised learning on historical results. The generator creates geometry and action variants, which an FEM or CFD solver on the GPU evaluates, returning the score as a reward to the generator. The result is the best shapes and parameters for the engineer.
Operation
Operation diagram: a new design task with requirements and constraints goes to the trained GAN generator or RL agent, which creates solution proposals; the GPU solver performs the final verification and the verified variant goes to the engineer

We describe the computational environment and the geometric model and generate many variants of shapes and actions. The solver’s assessment is fed back to the network as a reward, so the proposals improve with each iteration. Earlier results from publications, projects and research are used for supervised learning and speed up the first, random attempts.

  • Generation of geometry and parameter variants
  • FEM / CFD solver validates every proposal
  • Historical results as the starting point for training

We can build a solution like this for your company.

Let’s talk to define your needs and prepare an offer.