Field oriented control dataset of a 3-phase permanent magnet synchronous motor

Area of Science:

• Electrical Engineering
• Control Systems Engineering
• Robotics

Background:

• Permanent Magnet Synchronous Motors (PMSMs) are crucial in robotics and machine tools.
• Field Oriented Control (FOC) is a prevalent method for PMSM speed and torque regulation.
• Traditional FOC relies on hand-tuned Proportional-Integrative-Derivative (PID) controllers, often using Look-Up Tables (LUTs), which can limit performance under extreme conditions.

Purpose of the Study:

• To present a comprehensive dataset of a 3-phase PMSM under FOC.
• To evaluate PMSM control performance against various input signal shapes and extreme scenarios.
• To facilitate the development of advanced non-linear control techniques, such as Machine Learning (ML) and Neural Networks (NN), to enhance FOC.

Main Methods:

• A simulated FOC motor control environment was developed in Simulink.
• A dataset was generated capturing PMSM response to diverse input speed variations, including extreme conditions challenging PID linearity.
• Both outer and inner-loop FOC signals were measured for detailed analysis.

Main Results:

• The dataset captures the PMSM's dynamic response under various operational conditions, including challenging, high-magnitude speed variations.
• The limitations of linear PID controllers in FOC were highlighted under extreme dynamic stresses.
• The collected data provides a foundation for training and validating non-linear control models.

Conclusions:

• The generated dataset is valuable for advancing PMSM control beyond traditional PID methods.
• The data supports research into ML and NN-based controllers for FOC, potentially improving robustness and performance.
• This work paves the way for more adaptive and efficient motor control solutions in demanding applications.