Skip to content

This repository contains the simulation codes for the paper: Data-Efficient Constrained Learning for Optimal Tracking of Batch Processes, 2021.

Notifications You must be signed in to change notification settings

Zhou-ust/Data-efficient-constrained-learning

Repository files navigation

Data-efficient-constrained-learning

This is a repository of the codes for data-efficient constrained learning [1] for linear uncertain batch processes.

Required software/toolboxes for MATLAB

The following software/toolboxes for MATLAB are required for using the codes in this folder:

  1. Multi-Parametric Toolbox 3: https://www.mpt3.org/;
  2. YALMIP: https://yalmip.github.io/;
  3. MOSEK(Version 9.3.6): https://www.mosek.com/;
  4. Gurobi: https://www.gurobi.com/;

Note that you can readily adapt these codes to your model after installing the software/toolboxes above.

Citation

You are more than welcome to use the code for your research if it is useful. If you use the code for 1) building the data-related learning control implementations; or/and 2) synthesizing the batch process controller, please cite the following paper:

@article{zhou2021data,
  title={Data-efficient constrained learning for optimal tracking of batch processes},
  author={Zhou, Yuanqiang and Gao, Kaihua and Li, Dewei and Xu, Zuhua and Gao, Furong},
  journal={Industrial \& Engineering Chemistry Research},
  volume={60},
  number={43},
  pages={15658--15668},
  year={2021},
  publisher={ACS Publications}
}

References

[1] Y. Zhou, K. Gao, D. Li, Z. Xu, & F. Gao, Data-efficient constrained learning for optimal tracking of batch processes, In: Industrial & Engineering Chemistry Research, vol. 60, no. 43, pp. 15658-15668, 2021.

About

This repository contains the simulation codes for the paper: Data-Efficient Constrained Learning for Optimal Tracking of Batch Processes, 2021.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages