Machine Learning and Dynamic Optimization Course

Machine Learning and Dynamic Optimization is a graduate level course on the theory and applications of numerical solutions of time-varying systems with a focus on engineering design and real-time control applications. Concepts taught in this course include physics-based and empirical modeling, machine learning classification and regression, nonlinear programming, estimation, and advanced control methods such as model predictive control.

[jesusbriceno]

I just discovered this channel and I have to say that it's amazing! Thank you for sharing this great content, you are helping students from anywhere in the world.

[WooiHenYap]

best ever lecturer and course ever seen by far. Thanks sir.

[rikpome]

although i already graduated university 17years ago, and i work for power plant control engineer,
I am studying matlab and python only for following this amazing class

[footballfan]

best lecturer in ytube, god bless you from iraq

[saurabhtalele]

Yes you always share knowledge which is advance and in simple way. Thanks sir may be you can work with edx to teach....

[zhangjim]

owesome training course for process engineer

[pedrocalorio]

the classes/lectures are going to be uploaded on youtube?
in the site course there is plenty of older videos

[yuegengma]

Dear Professor, thanks for your course! I'm working on a project of optimal dynamic control of a novel power plant using supercritical co2 as the working fluid. A tricky task of the simulation of this power plant is the calculation of the co2 properties. I used to call refprop/coolprop to calculate the properties during the steady-state process simulation, but these two thermodynamic property packages do not provide first and second derivates and therefore can not be integrated with the optimization solve using deterministic algorithms (like GEKKO). I read a few papers that embed machine learning(ANN) to predict the thermodynamic properties to replace the mechanistic model and claimed good accuracy. I was wondering if it's possible for me to use machine learning to regress the thermal properties of CO2 and embed this in the process simulation model and then implement optimization with GEKKO?