Description: Artificial intelligence (AI) has significantly revolutionized research activities and industrial applications in image processing and natural language processing. Likewise, the synergy of power electronics and computer science is expected to unleash great potentials in power electronic systems as well with their transition towards data-rich ones. From the power electronics perspective, this course aims to focus on two essential aspects of this interdisciplinary field, i.e., artificial intelligence and advanced data analytics. It is organized following a typical pipeline when implementing data-driven solutions in power electronics, ranging from the initial data collection to the final decision-makings. As a 3-day course, it includes fundamentals, tools, applications, hands-on exercises, and outlook, which are specifically tailored for power electronic applications. Combining with several case studies where AI has shown great benefits, the attendees are expected to establish solid foundations and skills of AI and data analytics to address core challenges in data-driven applications in power electronics.

Day-1: Fundamentals

08:30 – 08:45

Course introduction

Huai Wang

08:45– 10:15

Data and analytic methods in power electronics

Shuai Zhao

10:15 – 10:30

Coffee break

 

10:30 – 12:00

Artificial intelligence tools in power electronics

Shuai Zhao

Lunch

 

 

13:00 – 14:15

Neural network for power electronic applications I: Fundamentals

Shuai Zhao

14:15 – 14:30

Coffee break

 

14:30 – 16:00

Neural network for power electronic applications II: Hands-on implementation

Shuai Zhao

Day-2 : Applications and Examples

09:00 – 10:15

Artificial Neural Network based Thermal Model Considering the Cross-Coupling Effects of Power Modules

Yi  Zhang

10:15 – 10:30

Coffee break

 

10:30 – 12:00

AI-based design and implementation of Model Predictive Control Algorithm

Mateja Novak

Lunch

 

 

13:00 – 14:15

Physics-informed AI to Handle Adversarial Data in Power Electronics

Subham Sahoo

14:15 – 14:30

Coffee break

 

14:30 – 15:15

Digital twin & Condition and health monitoring in power electronics

Huai Wang

15:15  – 16:00

Project introduction

Shuai Zhao

Day-3: Outlook and Project Exercise

09:00 – 10:15

Frontiers of data-driven research in power electronics and beyond

Shuai Zhao

10:15 – 10:30

Coffee break

 

10:30 – 12:00

Project & Exercise (2 projects for each participant)

P1: Digital twin-based condition monitoring of Buck converter

P2: Physics-informed neural network for dynamic systems

P3: AI-aided tuning of control parameters

Shuai Zhao, Mateja Novak,

 

Lunch

 

 

13:00 – 16:00

Project exercise and support

Shuai Zhao, Mateja Novak

 Prerequisites:

  • Fundamentals of power electronics
  • Fundamentals of probabilistic models and statistical analysis
  • Experience with MATLAB/Python

* Please get familiar with Python basics and set up your Google Colab account before the course. A tutorial of Google Colab can be found: https://www.tutorialspoint.com/google_colab/google_colab_tutorial.pdf

* Matlab installed with the predictive maintenance toolbox. You may find more details in the below link: https://www.mathworks.com/products/predictive-maintenance.html

Form of evaluation: The course is accompanied by a hands-on team project so that the theoretical tools introduced in the course can be implemented in real applications. The course evaluation will be based on the project report.


Organiser:      Professor, Huai Wang, hwa@energy.aau.dk; Assistant Professor, Shuai Zhao szh@energy.aau.dk

Lecturers:       Professor, Huai Wang, hwa@energy.aau.dkAalborg University, Assistant Professor

Shuai Zhao, szh@energy.aau.dk, Aalborg University, 

Assistant Professor, Subham Sahoo sssa@energy.aau.dk, Aalborg University

Postdoc, Mateja Novak nov@energy.aau.dkAalborg University

Postdoc, Yi Zhang yiz@energy.aau.dk, Aalborg University

ECTS:                3

Date/Time:    Apr.26-28, 2023

Deadline:         5 April 2023

Place:               AAU Energy, Aalborg

Max no. of participants: 30

Price: 6000 DKK for PhD students outside of Denmark and 8000 DKK for the Industry excl. VAT
The Danish universities have entered into an agreement that allows PhD students at a Danish university (except Copenhagen Business School) the opportunity to free of charge take a subject-specific course at another Danish university.

PaymentA Online link will be annonced after deadline for registration 

Important information concerning PhD courses: We have over some time experienced problems with no-show for both project and general courses. It has now reached a point where we are forced to take action. Therefore, the Doctoral School has decided to introduce a no-show fee of DKK 3.000 for each course where the student does not show up. Cancellations are accepted no later than 2 weeks before start of the course. Registered illness is of course an acceptable reason for not showing up on those days. Furthermore, all courses open for registration approximately four months before start. This can hopefully also provide new students a chance to register for courses during the year. We look forward to your registrations.