Optimal Digital Techniques for Advanced Process Control
Overview
In today's industrial landscape, traditional control methods often fall short in addressing the complexities and dynamic nature of modern production processes. Optimal control techniques offer a powerful solution by providing a systematic approach to designing advanced process control (APC) strategies that maximize production performance across multiple objectives while adhering to technical and regulatory constraints.
In this webinar, you will learn the fundamentals of optimal process control with a specific focus on model predictive control (MPC) and reinforcement learning (RL). You will also hear real-world stories about MathWorks customers who successfully implemented such techniques in process-intensive industries such as petroleum, chemical processing, and manufacturing.
Highlights
- Representing complex processes using high-fidelity multi-physics models with Simscape
- Using a plant model to define an MPC controller with MPC Designer
- Interactively creating, tuning, and training an RL agent using Reinforcement Learning Designer
About the Presenter
Jordan Olson
Application Engineer | MathWorks
Jordan specializes in advanced control design, particularly reinforcement learning and model predictive control. Jordan supports customers across a wide range of industries, including aerospace, automotive, energy, robotics, and consumer electronics. He holds a B.S. and M.S. in Mechanical Engineering, as well as an M.S. in Electrical Engineering, all from The University of Alabama. During his graduate studies, Jordan worked on advanced vehicle systems development, including powertrain control, autonomy, and electrification.
