My research interests are in the general area of Process Systems Engineering (PSE), with emphasis on, optimization under uncertainty, artificial intelligence, nonlinear programming, optimal control (dynamic optimization), and numerical computations.
On the applications domain, I work extensively on applying optimization, control and machine learning algorithms to bioprocess modelling and intensification, particularly to biofuels. For more detailed information you can refer to my group's page.
Optimization, Control & Reinforcement Learning
Applying technique such as (stochastic) model predictive control, reinforcement learning, dynamic optimization, among others, we can control and optimize nonlinear stochastic dynamical systems.
Machine Learning Applied to Bioprocesses
We can combine emerging techniques from the are of machine learning and artificial intelligence to make bioprocesses more efficient, and increase their economic viability against their non-renewable counterparts.
Real-Time Optimization for Stochastic Processes
Real-time optimization (RTO) systems deal with optimizing ongoing processes under model and process uncertainty.
This is a well-accepted methodology by industrial practitioners, with numerous successful applications reported over the last few decades.
Lately, we have combined traditional RTO techniques, with Machine-Learning technologies to create efficient and robust algorithms.
Development of New Algorithms for Systems Engineering
We design and create new algorithms that can enhance the performance of different systems, from distributed optimization and networks to highly nonlinear optimization of dynamical systems.