ABSTRACT
This paper presents a dataset of a 3-phase Permanent Magnet Synchronous Motor (PMSM) controlled by a Field Oriented Control (FOC) scheme. The data set was generated from a simulated FOC motor control environment developed in Simulink; the model is available in the public GitHub repository. The dataset includes the motor response to various input signal shapes that are fed to the control scheme to verify the control capabilities when the motor is subjected to real life scenarios and corner conditions. Motor control is one of the most widespread fields in control engineering as it is widely used in machine tools and robots, the FOC scheme is one of the most used control approaches thanks to its performance in speed and torque control, with the drawback of having to handcraft the Proportional-Integrative-Derivative (PID) regulators using Look Up Tables (LUT). The test conditions are designed by setting a motor desired speed. Different input speed variations shapes are proposed as well as extreme scenarios where the linear behaviour of the PID regulator is challenged by applying fast and high magnitude speed variations so that the PID controller is not able to correctly follow the reference. The measured data includes both the outer and inner-loop signals of the FOC, which opens the possibility to develop non-linear control approaches such as Machine Learning (ML) and Neural Networks (NN) with different topologies to replace the linear controllers in the FOC scheme.
ABSTRACT
This paper presents a dataset for Bluetooth 5.1 direction of arrival (DoA). The dataset was generated with a specifically designed mathematical model of a non-uniform rectangular antenna array. The Python source files that generated the dataset are also provided. The dataset was conceived as a starting point for developing and validating DoA algorithms for real-life scenarios. Unlike other datasets, it contains Bluetooth signals with not only varying intensity of additive white Gaussian noise, but also coherent interfering signals with random DoA coordinates. The dataset is divided into two branches, one consisting of pure sinusoidal tones and the second comprised of baseband Bluetooth signals. Since the codebase which generates the data is included, this dataset has a high reuse potential, and it can be modified to suit also other types of signals or different array topologies.
