Julia Computing introduced JuliaSim, a next-generation cloud-based simulation platform, combining the latest techniques in SciML with equation-based digital twin modeling and simulation. Its ML-based techniques accelerate simulation by up to 500x, changing the paradigm of what is possible with computational design.
Industrial-scale modeling and simulation
JuliaSim enables directly importing models from its Model Store into your Julia environment, making it easy to build large complex simulations. Pre-trained machine learning models leveraging SciML are integrated into the engineer’s workflow, saving both model development and simulation time.
Case studies of Julia for simulation include pharmaceutical development of Pfizer, robot locomotion of MIT, planning space missions and more. It combines models with tools like DiffEqFlux and NeuralPDE to discover missing physics and generate digital twins. In addition, JuliaSim uses the latest techniques from scientific machine learning and model order reduction. With advanced techniques like Polynomial Chaos and Koopman Operator, it approaches to create designs robust to uncertainty and stochasticity.