Aspen Automation Framework

Python pipeline turning Aspen Plus into an automated engine — DOE, parallel simulation, surrogate training, optimization. 1,575 cases in hours instead of weeks.

Photo 1 — coming soon
Photo 2 — coming soon
Photo 3 — coming soon

What it is

A Python pipeline that turns Aspen Plus from an interactive tool into an automated engine — DOE generation, parallel simulation, surrogate training, and optimization, end to end.

Highlights

  • 1,575 simulations completed in hours instead of weeks of manual clicking
  • COM-driven engine with failure isolation — one crashed case never aborts the run
  • Surrogate comparison (RF · GB · NN · GP) feeding Bayesian and NSGA-II optimizers
  • Configuration-driven: a new study is a new YAML file, not new code
  • Powers the CCPP-LOHC Optimization study end-to-end

Repository

github.com/LEE-Inseok/aspen-automation

PythonCOM APIDOESurrogate ModelingNSGA-IIBayesian Optimization