Topic

 

Data-Driven Control

Data-driven control systems are a broad family of control systems, in which the identification of the process model and/or the design of the controller are based entirely on experimental data collected from the plant.

In many control applications, trying to write a mathematical model of the plant is considered a hard task, requiring efforts and time to the process and control engineers. This problem is overcome by data-driven methods, which allow to fit a system model to the experimental data collected, choosing it in a specific models class. The control engineer can then exploit this model to design a proper controller for the system. However, it is still difficult to find a simple yet reliable model for a physical system, that includes only those dynamics of the system that are of interest for the control specifications. The direct data-driven methods allow to tune a controller, belonging to a given class, without the need of an identified model of the system. In this way, one can also simply weight process dynamics of interest inside the control cost function, and exclude those dynamics that are out of interest.

from Data-Driven Control System - Wikipedia

This topic includes the following resources and journeys:

 

 

Data-Driven Dynamical Systems Overview

Steve Brunton
21 min
Intermediate
Video
Theory

This video provides a high-level overview of this new series on data-driven dynamical systems. In particular, we explore the various challenges in modern dynamical systems, along with...

See More

Data-Driven Control: Overview

Steve Brunton
24 min
Beginner
Video
Theory

Overview lecture for series on data-driven control. In this lecture, we discuss how machine learning optimization can be used to discover models and effective controllers directly from data...

See More

Data-Driven Control: Balancing Transformation

Steve Brunton
11 min
Intermediate
Video
Theory

In this lecture, we derive the balancing coordinate transformation that makes the controllability and observability Gramians equal and diagonal. This is the critical step in balanced model...

See More

Data-Driven Control: Balanced Models with ERA

Steve Brunton
6 min
Intermediate
Video
Theory

In this lecture, we connect the eigensystem realization algorithm (ERA) to balanced proper orthogonal decomposition (BPOD). In particular, if enough data is collected, then ERA produces...

See More

Data-Driven Control: Balanced Truncation

Steve Brunton
14 min
Intermediate
Video
Theory

In this lecture, we describe the balanced truncation procedure for model reduction, where a handful of the most controllable and observable state directions are kept for the reduced-order...

See More