Compare NVIDIA Modulus vs. NeuralWing

NVIDIA Modulus is an advanced neural network framework that integrates the principles of physics, represented through governing partial differential equations (PDEs), with data to create accurate, parameterized surrogate models that operate with near-instantaneous latency. This framework is ideal for those venturing into AI-enhanced physics challenges or for those crafting digital twin models to navigate intricate non-linear, multi-physics systems, offering robust support throughout the process. It provides essential components for constructing physics-based machine learning surrogate models that effectively merge physics principles with data insights. Its versatility ensures applicability across various fields, including engineering simulations and life sciences, while accommodating both forward simulations and inverse/data assimilation tasks. Furthermore, NVIDIA Modulus enables parameterized representations of systems that can tackle multiple scenarios in real time, allowing users to train offline once and subsequently perform real-time inference repeatedly. As such, it empowers researchers and engineers to explore innovative solutions across a spectrum of complex problems with unprecedented efficiency.

NeuralWing serves as a cutting-edge model for real-time neural simulation and design optimization specifically tailored for transonic aircraft aerodynamics. It leverages the most comprehensive 3D transonic wing dataset, derived from 30,000 steady-state CFD simulations that span a 3D wing operating within the transonic regime, incorporating variations in four distinct geometry parameters and two different inflow conditions. By utilizing Emmi’s AB-UPT surrogate model, which has been meticulously trained on this extensive dataset, NeuralWing empowers users to effortlessly alter wing geometries, conduct optimizations, and enhance aerodynamic efficiency within mere seconds. The model is designed to facilitate transonic 3D wing simulations, accommodating variations in geometry and inflow, while offering real-time inference and optimization of design parameters. Users input a geometry mesh in STL format along with speed and angle of attack, and in return, they receive outputs that include pressure, friction, velocity fields, and integral forces such as lift and drag. Geometry meshes are generated dynamically in response to four design parameters, employing a differentiable approach that allows for swift assessment of design modifications. Furthermore, NeuralWing boasts an impressive accuracy rate of 99.5%, making it an invaluable tool for aerodynamics research and development. This level of precision ensures that engineers can trust the results as they iterate on their designs.