Toshiba AI Technology Catalog

  • Placement and Design

Simulation optimization

Reduce the repetition of trials in manufacturing.


  • Discover good solutions with fewer trials, by combining Bayesian optimization with low-dimensionalization.
  • Used to increase efficiency of design operations; e.g., for thermal power turbines and wind turbines.

Applications



  • Optimize parameters for thermal power turbine design
  • Optimize wind farm layout
  • Investigate compositions in drug discovery and new functional materials
  • Can be used to resolve problems where optimum parameters and combinations are determined by repeated trials

Benchmarks, strengths, and track record



  • Low-dimension Bayesian optimization technologies reduce the number of trials by 50% compared to conventional methods

Inquiries



Please include the title “AI Technology Catalog: Simulation optimization” or the URL in the inquiry text.
Please note that because this technology is currently the subject of R&D activities, immediate responses to inquiries may not be possible.

References:

  • Daiki Kiribuchi et.al.; “Modification of Bayesian optimization for efficient calibration of simulation models”; In 2020 Winter Simulation Conference (WSC),pp. 2821-2831, 2020.