# Artificial Neural Networks Based Analysis of BLDC Motor Speed Control

**Authors:** Porselvi T, Sai Ganesh CS, Aouthithiye Barathwaj SR Y  
**arXiv:** [2108.12320](https://arxiv.org/abs/2108.12320)  
**Date:** 2021-08-27  
**Summary page:** https://www.summarizepaper.com/en/arxiv-id/2108.12320v1/

## Key points

- Artificial Neural Network (ANN) is a powerful tool in electrical and electronics engineering for accurately handling binary data.
- ANN algorithms have been successfully implemented in Brushless Direct Current (BLDC) motors to achieve expected results.
- BLDC motors utilize electronic closed-loop controllers to generate magnetic fields by switching DC current to motor windings.
- BLDC motors are preferred for their high speed, low maintenance, and strong torque capabilities compared to other types of motors.
- Speed control of BLDC motors involves adjusting the DC input voltage of the bridge converter using a Proportional-Integral (PI) based speed controller.
- The motor is modeled using MATLAB/Simulink software for analysis and optimization of the speed control system.
- Various parameters such as EMF signals, rotor speed, electromagnetic torque, Hall Effect signals, PWM signals are simulated and analyzed in this model.
- Data from simulations is fed into binary artificial neural networks for further analysis and accurate prediction of corresponding parameters.

## Summary

Artificial Neural Network (ANN) is a powerful tool in electrical and electronics engineering for accurately handling binary data. In the realm of Brushless Direct Current (BLDC) motors, ANN algorithms have been successfully implemented to achieve expected results. These motors utilize electronic closed-loop controllers to generate magnetic fields by switching DC current to motor windings. BLDC motors are preferred for their high speed, low maintenance, and strong torque capabilities compared to other types of motors. One common method for controlling the speed of BLDC motors involves adjusting the DC input voltage of the bridge converter that supplies power to the motor winding. This control process is facilitated by a Proportional-Integral (PI) based speed controller. To analyze and optimize this speed control system, the motor is modeled using MATLAB/Simulink software. Various parameters such as EMF signals, rotor speed, electromagnetic torque, Hall Effect signals, PWM signals are simulated and analyzed in this model. The acquired data from these simulations is then fed into binary artificial neural networks for further analysis. The ANN model accurately predicts corresponding parameters close to simulation results. In a recent study published in the Journal of Electrical Systems by Porselvi T et al., titled "Artificial Neural Networks Based Analysis of BLDC Motor Speed Control," the authors delve into the intricacies of utilizing ANN models for optimizing BLDC motor speed control systems. Through their research, they demonstrate how mathematical-based simulations combined with data-driven predictions using ANN technology yield satisfactory results in enhancing the performance and efficiency of BLDC motors in various applications within electrical and electronics engineering domains.