| Academic Year |
2024Year |
School/Graduate School |
Graduate School of Advanced Science and Engineering (Master's Course) Division of Advanced Science and Engineering Smart Innovation Program |
| Lecture Code |
WSS20501 |
Subject Classification |
Specialized Education |
| Subject Name |
データ駆動型システム特論 |
Subject Name
（Katakana） |
データクドウガタシステムトクロン |
Subject Name in
English |
Advanced Data-Driven Systems Design |
| Instructor |
KINOSHITA TAKUYA |
Instructor
(Katakana) |
キノシタ タクヤ |
| Campus |
Higashi-Hiroshima |
Semester/Term |
1st-Year, First Semester, 2Term |
| Days, Periods, and Classrooms |
(2T) Inte：ENG 101 |
| Lesson Style |
Lecture |
Lesson Style
(More Details) |
|
| |
| Credits |
2.0 |
Class Hours/Week |
|
Language of Instruction |
B
:
Japanese／English |
| Course Level |
6
:
Graduate Advanced
|
| Course Area（Area） |
25
:
Science and Technology |
| Course Area（Discipline） |
11
:
Electrical, Systems, and Control Engineering |
| Eligible Students |
Students in the Graduate School of Advanced Science and Engineering |
| Keywords |
data-driven control, control system design, PID control |
| Special Subject for Teacher Education |
|
Special Subject |
|
Class Status
within Educational
Program
(Applicable only to targeted subjects for undergraduate students) | |
|---|
Criterion referenced
Evaluation
(Applicable only to targeted subjects for undergraduate students) | |
|---|
Class Objectives
/Class Outline |
This lecture will cover the fundamentals of data-driven control systems. The main contents of this lecture are as follows.
(1) Basic concept of data-driven control methods for linear systems
(2) Basic concept of data-driven control methods for nonlinear systems
(3) Basic concept of machine learning |
| Class Schedule |
lesson1: Basic Concepts of Data-Driven Control
(Model-based control, PID control, data-driven control)
lesson2: Fundamentals of Numerical Simulation
(Matlab/Simulink exercise)
lesson3: Data-driven control: FRIT method
(reference model, pseudo-reference signal)
lesson4: Data-driven control: FRIT method
(PC exercise)
lesson5: Nonlinear Optimization Method
（Gauss-Newton method)
lesson6: Nonlinear Optimization Method
(PC exercise)
lesson7: Data-driven control: VRFT method
(Comparison with FRIT method)
lesson8: Data-driven control: VRFT method
(PC exercise)
lesson9: Machine Learning: Support Vector Machine
(classification problems)
lesson10: Machine Learning: Support Vector Machine
(PC exercise)
lesson11: Data-driven Control: Database-driven Control
(Overview of database-driven control)
lesson12: Data-driven Control: Database-driven Control
(Neighborhood data selection method, online learning)
lesson13: Data-driven Control: Database-driven Control
(PC Exercise 1)
lesson14: Data-driven Control: Database-driven Control
(PC Exercise 2)
lesson15: Introduction to industrial application case studies (final report) |
Text/Reference
Books,etc. |
Power Point materials are used in the lecture. |
PC or AV used in
Class,etc. |
|
| (More Details) |
Power Point |
| Learning techniques to be incorporated |
|
Suggestions on
Preparation and
Review |
PC exercises will be conducted to deepen understanding of the lecture content. Therefore, it is effective to keep this in mind when preparing for and reviewing the lectures. |
| Requirements |
It is advisable to take lectures on the basics of differentiation and integration, linear algebra, and control engineering.
Since MATLAB / Simulink (Version is 2020a) is used in the exercise, consult with the instructor in advance if you cannot install it on your PC. |
| Grading Method |
Exercises (including computer exercises) 30%, final report 60%, Attitude towards participation 10% |
| Practical Experience |
|
| Summary of Practical Experience and Class Contents based on it |
|
| Message |
|
| Other |
Computer exercises will be given as part of the lecture. Bring your computer on the designated day. |
Please fill in the class improvement questionnaire which is carried out on all classes.
Instructors will reflect on your feedback and utilize the information for improving their teaching. |