Physics based Machine Learning leverages the power of ADT’s inverse design method to rapidly and efficiently explore vast turbomachinery design spaces. To arrive at global optimum designs that meet multiple objectives and constraints and multiple operating points.
Discover how turbomachinery optimization is a process that requires the efficient integration and blending of algebraic tools with low- and high-fidelity simulation. Then see our Machine Learning algorithm set about the task of improving the multi-point performance and cavitation margin of a hydraulic Francis runner.
See our demonstration of simulation data management, managed as a simple, integrated process, where connections between the geometry-optimizer engine and the simulation tools are controlled in a couple of mouse clicks.
