Courses

Study dynamic analysis and state-space modeling of control systems

Understand and compare PID and data-driven control methods

Learn reinforcement learning-based control theory and applications

Implement and analyze motor controllers using Python and STM32

This course introduces neural network theory, including forward and backward propagation.

Various neural network architectures and training methods are studied for industrial applications.

Embedded neural networks are implemented on various STM32 MCU platforms, including dual-core CPUs and NPUs

Electric drive systems are used as target applications under real-time constraints.

Learn the fundamentals of reinforcement learning and its key concepts. 

Apply reinforcement learning to electric drive control.

Practice RL-based control using Python simulations. 

Implement lightweight RL models for embedded real-time control.

Understand aging characteristics and fault mechanisms of power systems

Learn diagnostic signal types and signal processing techniques

Analyze limitations of rule-based methods and introduce data-driven AI diagnostics

Design and deploy reliable industrial AI models for embedded systems