Data-Driven Integrated Molecular and Process Design Using Bayesian Optimization

This repository contains the data and scripts involved in the manuscript:

BayesCAMPD: Data-Efficient and Closed-Loop Integrated Molecular and Process Design Using Bayesian Optimization

Requirements

Library (Python 3.10)

• SMT: mixed integer sampling
• scikit-learn: Gaussian process regression
• SciPy: differential evolution
• Matplotlib: visualization

Software

• Aspen Plus: chemical process simulation

Note

The process simulation involved in this work is largely supported by our automated simulation tool, which can be found in the repository Aspen-Plus-Automation.

Authors

• Zihao Wang
• Prof. Dr.-Ing. Teng Zhou
• Prof. Dr.-Ing. Kai Sundmacher