Stockholm-based software developer Ingrid Cloud has brought to market a revolutionary cloud-based computational tool designed to “automate the entire process of flow simulation and design optimization by building the computational model without human intervention.”
The company says the “proprietary self-learning algorithms which form the core of Ingrid Cloud enable the automation of the entire simulation process, increasing accuracy and eliminating costly process repetition due to human error. The algorithms also reduce computing costs, since they optimize the usage of computational resources.”
The foundation of Ingrid Cloud is the groundbreaking CFD framework developed by its precursor organization, Adaptive Simulations, which uses the finite element method together with adaptive mesh refinement based on adjoint techniques and a posteriori error estimation. Since 2010, Adaptive Simulations’ technology has been regularly validated in benchmark workshops organized by the American Institute of Aeronautics and Astronautics (AIAA) and by NASA. The team behind Adaptive Simulations has dedicated over 30 person-years of research to:
- Develop a methodology that allows automatic creation of highly complex simulation models from CAD geometry,
- Implement this method in a scientific code, and
- Optimize and test the code on the fastest supercomputers in the world (K computer in Japan, Beskow in Stockholm and Hazel Hen in Stuttgart, among others).
- High-fidelity turbulent flow simulations.
- Setup simulation with simple wizard and intuitive user interface.
- Automated, smart mesh generation based on adjoint techniques and error estimation.
- No explicit turbulence model needed.
- Very few input parameters compared with traditional CFD.
The company explains that its technology is based on two unique innovations that provide superior capabilities. The capabilities are:
- A parameter-free method for simulation of turbulent flow at high Reynolds numbers, in the form of weak solutions of the Navier-Stokes equations approximated by adaptive FEM. Here, viscous dissipation is assumed to be dominated by turbulent dissipation proportional to the residual of the equations, and the effect of skin friction is observed to be small compared with inertial effects.
- Algorithms for adaptive optimization of the mesh based on adjoint techniques and a posteriori error estimation, so that the output quantities of interest, in the form of functionals of the solution, converge to become independent of mesh resolution.
The method resulting from these innovations has no adjustable parameters, and no ad hoc design of the mesh is needed, enabling full automation of the simulation workflow, according to the company.
Vision: “Human-aided engineering”
Ingrid Cloud’s vision is that “instead of having computers aid humans, humans should support computers doing the design. In other words: computational design. We have developed intelligent algorithms that simulate flow and optimize the design based on the simulation.”
The company’s “innovation is the result of a spinout from world-leading research conducted over more than a decade by a team of researchers at KTH Royal Institute of Technology in Stockholm.” In 2014 the team was awarded a grant from the European Research Council to commercialize its research.
The company behind Ingrid Cloud, Adaptive Simulations, was founded in January 2015, and has been led since then by CEO and cofounder Sebastian Desand. The vision “was at first to create an easy-to-use, fully automated flow simulation service. That vision has evolved into a vision with more far-reaching implications.”
Funding and partners
In 2016 the company received funding from Vinnova, the Swedish Agency for Innovation and Growth, as well as from the EU Commission’s Horizon2020 program for disruptive innovations. In April 2017 the company raised a seed round of $1.5 million from Karma Ventures, Creathor Venture and KTH Holding. From 2015 to 2018 the company has developed its product in close collaboration with pilot customers of varying sizes in several industries. The first public version of Ingrid Cloud was launched in January 2018. The company has its principal office near its origin on the KTH Campus.