Summary
- Profile Type
- Business Offer
- POD Reference
- BOSK20231201015
- Term of Validity
- 7 December 2023 - 6 December 2024
- Company's Country
- Slovakia
- Type of partnership
- Commercial agreementInvestment agreementOutsourcing agreementSupplier agreement
- Targeted Countries
- All countries
Contact the EEN partner nearest to you for more information.
Find my local partner
General information
- Short Summary
- We are building platform for AI-based engineering for engineers and researchers to tame the physics of their projects in hours, some even in minutes. In addition, we’re also focusing on makers and creators, who are not trained physicists or mathematicians and want to leverage the extreme effectiveness of AI for physics without dealing with its complexities.
- Full Description
- The goal of the platform is to streamline and significantly speedup the process of physics experimentation in CFD, by leveraging physics-informed neural networks or Fourier neural operators, that can outperform even the most optimized, traditional numerical solvers in CFD. Software platform is for AI Engineering. It provides powerful tools for building high-performance AI-based physics simulators and easy-to-use interface to use them in their projects. There’s a paradigm shift happening in the world of physics simulation. Deep learning methods are outperforming even the most optimized classical numerical solvers. The key component of these methods are physics-informed neural networks (PINNs).
- Advantages and Innovations
-
In complex physics simulations, it’s important to precisely quantify the underlying physical mechanisms in order to analyze them. High-dimensional scientific simulations are computationally very expensive to run, and solvers and parameters must often be tuned individually to each system studied. Machine learning approaches tend to considerably decrease the load on computational resources by reducing the dimensionality of the studied problem and by factoring in the fact that AI-based simulators need to be trained only once while actual numerical simulation is computed during the inference of the model. Software platform provides a set of tools to easily create, train and deploy powerful physics-informed neural network models with complex physics and custom partial differential equations. We provide a cloud-based environment called Simulator Training Environment (STE) available through SIML Model Engineer application. STE is optimized for NVIDIA GPUs and offers everything needed for creating
AI-based physics simulators:
- NVIDIA Modulus framework for creating and training PINNs
- VS Code IDE available in browser to customize the code for PINN models
- Netdata for real-time hardware monitoring
- Ability to connect to Weights & Biases for additional PINN model monitoring - Stage of Development
- Already on the market
- Sustainable Development Goals
- Goal 9: Industry, Innovation and Infrastructure
Partner Sought
- Expected Role of a Partner
- We are searching for engineers and researchers, who wants to tame the physics of their projects in hours, some even in minutes.
- Type and Size of Partner
- SME <=10R&D InstitutionSME 50 - 249Big companyOtherUniversitySME 11-49
- Type of partnership
- Commercial agreementInvestment agreementOutsourcing agreementSupplier agreement
Dissemination
- Technology keywords
- 002006009 - Simulation, Simulation Engineering
- Market keywords
- 02007001 - Systems software08006001 - Process control and logistics02007011 - Manufacturing/industrial software02007015 - Integrated software02007016 - Artificial intelligence related software
- Targeted countries
- All countries