Innovative simulation and test solutions for trustworthy data-centric AI

Trustworthy AI begins with trustworthy data. Discover how Siemens and KU Leuven are performing research along this line, aiming to enable trustworthy data-centric AI for engineering applications. We consider the rich variety of engineering data, from modeling and simulation to test data acquisition, throughout product design and validation up to real-world operation. Check our blog to learn about our research towards trustworthy data-centric AI, together with KU Leuven in the frame of our research project SATISFY.AI, with support from the Flanders Innovation & Entrepreneurship Agency (VLAIO).

An abstract digital visualization displaying data flow and network connectivity. Glowing lines in blue, red, orange, and yellow stream across a dark blue background filled with binary code, circuit patterns, and data analytics charts. Illuminated dots and nodes cluster on the right side, representing data points or network nodes. The left side shows various digital interface elements including graphs, percentages, and monitoring icons, creating a representation of big data processing, artificial intelligence, or network analysis.

Leveraging know-how with AI into efficient product design

Is your engineering data a hidden goldmine? Overcome the ‘cold start’ problem in AI by using geometric similarity and transfer learning to transform existing models and simulations into powerful assets, speeding up product design and innovation

Your next colleague is an agent: The dawn of agentic AI-aided engineering

What if every engineer had instant access to simulation expertise? Agentic AI-Aided Engineering could transform engineering by putting intelligent AI agents alongside designers, automating complex CAE workflows, and breaking long-standing expertise bottlenecks. Discover how this emerging approach could democratize simulation and accelerate innovation across the engineering lifecycle

Fine-Tuning VLM

When off-the-shelf is not enough: fine-tuning for industrial part classification

Part identification in complex CAD assemblies is a bottleneck in simulation workflows, which can cost engineering teams days before the real work even begins. In this post, we explore how fine-tuning a Vision-Language Model on industrial components can improve the pre-processing phase.

Transfer Learning accelerating the shift to new battery materials and chemistries

Unlock faster battery innovation with transfer learning! This blog reveals how AI accelerates the discovery and optimization of new battery materials, rapidly advancing sustainable energy solutions for a brighter future

Agentic AI for simulation post-processing

Ask, don’t click: Agentic AI takes the pain out of simulation post-processing

Picture this. You have just finished a hydraulic drive-cycle simulation in Simcenter Amesim. The solver finished in four minutes. Excellent….

ML for Industrial CAE – “Just scale it”

By scaling up ML, engineers can more quickly iterate and optimize their product design, thanks to faster simulations. ML can speed up traditional methods, which makes it easier to integrate their capabilities within established company software and processes. Read about our ML engineering innovation journey in the frame of the research project ML4SIM!

Automation with VLMs

Visual Language Models: Turning design chaos into order

Visual Language Models (VLMs) are revolutionizing design by combining visual perception with language understanding, enabling engineers to classify, search, and explore complex models with natural prompts. Their remarkable generalization abilities make them invaluable for component identification. With VLMs, design chaos transforms into streamlined efficiency.

GenAI Automation through code generaiton

The role of Generative AI in simulation tool automation: From zero to hero

Imagine being able to express your simulation queries in natural language, with the software dynamically responding to carry out tasks and provide solutions. This development could democratize the use of advanced tools from the Simcenter portfolio making them more accessible to users with varying levels of expertise.