AI-Powered Platform for Intelligent CAE Simulation

RD Motion is developing an AI-powered cloud simulation platform for mechanical engineers working on gear and powertrain design. The core challenge is that high-fidelity Finite Element Method (FEM) simulations are computationally intensive, often taking hours to complete and requiring specialist expertise, which limits their use during the early stages of product development.

The AIPICS project leverages the Vega EuroHPC supercomputer to generate 1,632 CalculiX FEM simulations covering a broad range of steel and polymer gear material families. Combined with RD Motion’s in-house gear testing data, these simulations create hybrid training datasets for Physics-Informed Neural Networks (PINNs), enabling faster and more accurate prediction of gear performance and lifetime. In addition, Large Language Models (LLMs) are being fine-tuned to support agentic design-space exploration and assist engineers in evaluating design alternatives. The validated AI models will be integrated into RD Motion’s cloud-based Computer-Aided Engineering (CAE) platform as a Software-as-a-Service (SaaS) solution, delivering FEM-quality lifetime predictions in seconds and at a fraction of the cost of traditional simulation workflows.

Organisations involved: 

End-User: RD Motion d.o.o.