A GitHub organization for the Mesbah Lab, Department of Chemical and Biomolecular Engineering at the University of California, Berkeley.
This organization contains all code written from past and current members of the lab for various applications. All repositories have short descriptions on their purpose, are generally categorized by keywords, and, if applicable, are linked to their associated publication.
Learning-based multi-stage NMPC algorithm with guarantees on feasibility using robust control invariant sets
MATLAB 3
This repository contains code that demonstrates the use of a variety of machine learning strategies for low temperature plasma systems.
Jupyter Notebook 1
A Study on the Role of Electric Field in Low-Temperature Plasma Catalytic Ammonia Synthesis via Integrated Density Functional Theory and Microkinetic Modeling
Fortran 1
This code is a methods toolbox for constructing non-smooth polynomial chaos expansion (nsPCE) surrogate models. The codes for the nsPCE framework are applicable to non-smooth ODE models and particu…
MATLAB 1
Towards Personalized Plasma Medicine via Data-efficient Adaptation of Fast Deep Learning-based MPC Policies
Jupyter Notebook
Code repository for the paper on A Practical Multi-Objective Learning Framework for Optimal Hardware-Software Co-Design of Control-on-a-Chip Systems by Kimberly J. Chan, Joel A. Paulson, and Ali Mesbah.
This code trains and implements a characterization framework based on deep learning for characterizing structural states of colloidal self-assembly systems.
Multivariable control strategy for a reactor system, efficient global solution method for a reaction system and rocket, solution methods for two approximate formulations of the Bayesian optimal experiment design (OED) problem, optimal control approach for a cold plasma system.
This code obtains closed-loop performance guarantees for automated controller tuning, which can be formulated as a black-box optimization problem under uncertainty.
This code trains and implements a reinforcement learning framework for control of the thermal effects of an atmospheric pressure plasma jet
This code is a methods toolbox for constructing non-smooth polynomial chaos expansion (nsPCE) surrogate models. The codes for the nsPCE framework are applicable to non-smooth ODE models and particularly for dynamic flux balance analysis (DFBA) models.
This code trains and implements machine learning models for real-time diagnostics of cold atmospheric plasma sources.
