Data-Driven Control with MATLAB and Simulink

Traditional control methods often face challenges in handling complex systems with unknown dynamics and disturbances, such as in aerospace systems, automated driving, robotics, and motor control applications.

Data-driven control provides a powerful solution to the challenges posed by complex systems by utilizing measured data to learn controllers. This webinar introduces various data-driven control techniques such as active disturbance rejection control (ADRC), deep-learning-based model predictive control (MPC), and reinforcement learning (RL).

We will discuss the basics of these methods, their benefits and drawbacks, and share success stories from our customers who have successfully implemented data-driven controllers in their applications. Additionally, we will showcase practical demonstrations of different data-driven control methods in various applications with MATLAB and Simulink.

Resources:

Chapters:
00:00 Introduction
00:31 Key takeaways & agenda
2:34 Why use data-driven control?
5:24 Why use MATLAB and Simulink for data-driven control?
7:03 Active disturbance rejection control (ADRC) basics
10:14 PMSM control using ADRC
18:17 Model predictive control (MPC) basics
22:36 House heating system control using data-driven MPC
26:47 Creating AI-based reduced order models
27:47 Reinforcement learning (RL) basics
30:57 Rotary inverted pendulum control using RL
36:57 Summary and resources

--------------------------------------------------------------------------------------------------------

© 2024 The MathWorks, Inc. MATLAB and Simulink are registered trademarks of The MathWorks, Inc.

[amel]

Thank you for sharing. However, I have a question, please. I am currently implementing an MPC to control the temperature inside a room. To model the system, I used a neural network that takes as input a window of data (disturbance_w, control_w, output_w) to predict the output over a prediction horizon. Then, I use these predictions to calculate an objective function in order to obtain the first command to apply to my system to get the first output. For this, I use scipy, but the control proposed by this library remains constant regardless of the output values (the output does not follow the reference). Do you have any advice to improve this?