Speed control of a BLDC motor using Artificial Neural Network with ESP32 microcontroller based implementation
Brushless Direct Current (BLDC) motors has suppressed other types of DC motors as they are known to have better speed/torque characteristics, high dynamic response high efficiency, long operating life, noiseless operation, and so on. The speed control of BLDC motors can be achieved using conventiona...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Book Section |
Published: |
Springer Science and Business Media Deutschland GmbH
2022
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/100873/ http://dx.doi.org/10.1007/978-981-19-3923-5_31 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utm.100873 |
---|---|
record_format |
eprints |
spelling |
my.utm.1008732023-05-18T03:50:07Z http://eprints.utm.my/id/eprint/100873/ Speed control of a BLDC motor using Artificial Neural Network with ESP32 microcontroller based implementation Saleh, Isiyaku Bature, Amir Abdullahi Buyamin, Salinda Shamsudin, Mohamad Amir TK Electrical engineering. Electronics Nuclear engineering Brushless Direct Current (BLDC) motors has suppressed other types of DC motors as they are known to have better speed/torque characteristics, high dynamic response high efficiency, long operating life, noiseless operation, and so on. The speed control of BLDC motors can be achieved using conventional Proportional, Integral and Derivative (PID) controllers but to ensure robustness and noise rejection ability intelligent controllers are superior to PID. The major problem of intelligent controllers is high cost of implementation as it needs high computational microprocessor. Artificial Neural Network (ANN) controllers with an improved control law is designed and implemented in this work using cheap and efficient microcontroller, the ESP32. The new control law has increased the efficiency of the controller in tracking the set point. A three layers ANN design was achieved using Keras and TensorFlow deep learning module using python language, the data used was from PID controller implemented via an experimental DC motor trainer with Arduino IDE as the programming interface. The ANN controller was then programmed in the ESP32. The results obtained have demonstrated an excellent performance of the developed ANN controller over the conventional PID controller in terms of rising time, settling time, maximum overshoot and noise/disturbance rejection ability. Springer Science and Business Media Deutschland GmbH 2022 Book Section PeerReviewed Saleh, Isiyaku and Bature, Amir Abdullahi and Buyamin, Salinda and Shamsudin, Mohamad Amir (2022) Speed control of a BLDC motor using Artificial Neural Network with ESP32 microcontroller based implementation. In: Control, Instrumentation and Mechatronics: Theory and Practice. Lecture Notes in Electrical Engineering, 921 (NA). Springer Science and Business Media Deutschland GmbH, Singapore, pp. 358-368. ISBN 978-981193922-8 http://dx.doi.org/10.1007/978-981-19-3923-5_31 DOI:10.1007/978-981-19-3923-5_31 |
institution |
Universiti Teknologi Malaysia |
building |
UTM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Malaysia |
content_source |
UTM Institutional Repository |
url_provider |
http://eprints.utm.my/ |
topic |
TK Electrical engineering. Electronics Nuclear engineering |
spellingShingle |
TK Electrical engineering. Electronics Nuclear engineering Saleh, Isiyaku Bature, Amir Abdullahi Buyamin, Salinda Shamsudin, Mohamad Amir Speed control of a BLDC motor using Artificial Neural Network with ESP32 microcontroller based implementation |
description |
Brushless Direct Current (BLDC) motors has suppressed other types of DC motors as they are known to have better speed/torque characteristics, high dynamic response high efficiency, long operating life, noiseless operation, and so on. The speed control of BLDC motors can be achieved using conventional Proportional, Integral and Derivative (PID) controllers but to ensure robustness and noise rejection ability intelligent controllers are superior to PID. The major problem of intelligent controllers is high cost of implementation as it needs high computational microprocessor. Artificial Neural Network (ANN) controllers with an improved control law is designed and implemented in this work using cheap and efficient microcontroller, the ESP32. The new control law has increased the efficiency of the controller in tracking the set point. A three layers ANN design was achieved using Keras and TensorFlow deep learning module using python language, the data used was from PID controller implemented via an experimental DC motor trainer with Arduino IDE as the programming interface. The ANN controller was then programmed in the ESP32. The results obtained have demonstrated an excellent performance of the developed ANN controller over the conventional PID controller in terms of rising time, settling time, maximum overshoot and noise/disturbance rejection ability. |
format |
Book Section |
author |
Saleh, Isiyaku Bature, Amir Abdullahi Buyamin, Salinda Shamsudin, Mohamad Amir |
author_facet |
Saleh, Isiyaku Bature, Amir Abdullahi Buyamin, Salinda Shamsudin, Mohamad Amir |
author_sort |
Saleh, Isiyaku |
title |
Speed control of a BLDC motor using Artificial Neural Network with ESP32 microcontroller based implementation |
title_short |
Speed control of a BLDC motor using Artificial Neural Network with ESP32 microcontroller based implementation |
title_full |
Speed control of a BLDC motor using Artificial Neural Network with ESP32 microcontroller based implementation |
title_fullStr |
Speed control of a BLDC motor using Artificial Neural Network with ESP32 microcontroller based implementation |
title_full_unstemmed |
Speed control of a BLDC motor using Artificial Neural Network with ESP32 microcontroller based implementation |
title_sort |
speed control of a bldc motor using artificial neural network with esp32 microcontroller based implementation |
publisher |
Springer Science and Business Media Deutschland GmbH |
publishDate |
2022 |
url |
http://eprints.utm.my/id/eprint/100873/ http://dx.doi.org/10.1007/978-981-19-3923-5_31 |
_version_ |
1768006578218205184 |
score |
13.160551 |