NeuralWing
NeuralWing is a real-time neural simulation and design optimization model for transonic aircraft aerodynamics. It is built around the largest 3D transonic wing dataset, created from 30,000 steady-state CFD simulations of a 3D wing in the transonic regime, with variations across four geometry parameters and two inflow conditions. Using Emmi’s AB-UPT surrogate model trained on this data, NeuralWing enables users to modify wing geometry, test optimizations, and maximize aerodynamic efficiency in seconds. The model supports transonic 3D wing simulation, geometry and inflow variations, real-time inference, and design-parameter optimization. Its inputs include a geometry mesh in STL format, speed, and angle of attack, while its outputs include pressure, friction, velocity fields, and integral forces such as lift and drag. Geometry meshes are created in real time from four design parameters in a differentiable manner, allowing fast exploration of design changes.
Learn more
Alchemite
Alchemite provides AI-augmented physical modeling and solutions that help organizations extract actionable insights from experimental and simulation data by combining machine learning with physics-informed models to improve prediction accuracy, reduce experimental costs, and optimize product and process development. Its solutions span materials discovery and design, predictive modelling of performance and reliability, multiscale modelling that connects atomistic to macroscopic behaviour, and automation of workflow tasks such as data integration, surrogate modelling, and model validation. It supports physics-aware neural networks and hybrid modelling approaches that respect underlying scientific laws while learning from data to enable faster and more accurate simulations, reduced reliance on expensive physical testing, and improved decision-making. Intellegens’ tools are applied in areas such as battery performance prediction, chemical process optimization, etc.
Learn more
NVIDIA Modulus
NVIDIA Modulus is a neural network framework that blends the power of physics in the form of governing partial differential equations (PDEs) with data to build high-fidelity, parameterized surrogate models with near-real-time latency. Whether you’re looking to get started with AI-driven physics problems or designing digital twin models for complex non-linear, multi-physics systems, NVIDIA Modulus can support your work. Offers building blocks for developing physics machine learning surrogate models that combine both physics and data. The framework is generalizable to different domains and use cases—from engineering simulations to life sciences and from forward simulations to inverse/data assimilation problems. Provides parameterized system representation that solves for multiple scenarios in near real time, letting you train once offline to infer in real time repeatedly.
Learn more
FEATool Multiphysics
FEATool Multiphysics - "Physics Simulation Made Easy" - a fully integrated physics, FEA, and CFD simulation toolbox.
FEATool Multiphysics is a fully integrated simulation platform with a unified interface for several Finite Element Analysis (FEA) and Computational Fluid Dynamics (CFD) multi-physics solvers, such as OpenFOAM, SU2 Code, and FEniCS. This uniquely allows for modeling coupled physics phenomena such as found in fluid flow, heat transfer, structural, electromagnetics, acoustics, and chemical engineering applications, within a single user-friendly interface. With these capabilities, FEATool Multiphysics has become trusted tool by engineers and researchers worldwide to accelerate innovation and quickly achieve results in the energy, automotive, semi-conductor, and process industries.
Learn more
