Simulation of Large Scale Assets Using Reduced Order Models

Akselos provides Digital Twins of industrial equipment in a range of industries, including energy (oil & gas, wind hydro), marine, mining, chemicals, and aerospace. The Akselos platform is based on RB-FEA, which is a unique combination of the Reduced Basis method for fast and accurate reduced order modeling of parametrized PDEs and a domain decomposition framework that enables large-scale component-based analysis. RB-FEA has similarities to supervised machine learning (ML), in which "full order" solutions are used as the "supervisor" during RB-FEA training. In this presentation we will discuss the similarities and differences between RB-FEA compared to other ML methods, and demonstrate applications of the RB-FEA methodology to industrial Digital Twins.

S​peaker

David Knezevic, Ph.D. is the Chief Scientific Officer (CSO) and co-founder of Akselos. Akselos is a spin-off from MIT that provides physics-based Digital Twins based on patented Reduced Order Modeling technology. Akselos currently employs over 100 people worldwide, and has delivered state-of-the-art Digital Twins in a range of industries, including Energy (Oil & Gas, Wind, Hydro), marine, mining, chemicals, and aerospace.

David is originally from Perth, Western Australia. He did his undergraduate degree in engineering and computer science at the University of Western Australia, and then completed a Ph.D. at Oxford University as a Rhodes Scholar. After his Ph.D., David joined Prof. Anthony Patera’s research group at MIT as a post-doc, where he worked with collaborators on Reduced Order Modeling (ROM) methods with certified accuracy, based on the Reduced Basis (RB) method. This led to new developments for a component-based approach to RB, which enabled large-scale, high-fidelity ROMs with certified accuracy. Akselos was founded in order to deliver this technology to industry. The component-based RB approach has evolved into Akselos’s cloud-based RB-FEA platform for Digital Twins of critical assets.