Staff View: Failure prediction for hemodialysis units using machine learning and hall effect sensors

Failure prediction for hemodialysis units using machine learning and hall effect sensors

Hemodialysis Units (HDUs) are critical for providing essential dialysis treatments to patients with renal failure. However, failures in HDUs, particularly water pump failures, can disrupt patient care and compromise safety. This study focused on predicting water pump failures in HDUs using machine l...

Full description

Saved in:

Bibliographic Details
Main Authors:	Noordin, Muhammad Khair, Amran, Mohd. Effendi, Bani, Nurul Aini, Ahmad Kamil, Ahmad Safwan, Md. Nasir, Ahmad Nabil, Arsat, Mahyuddin
Format:	Conference or Workshop Item
Published:	2023
Subjects:	H Social Sciences (General)
Online Access:	http://eprints.utm.my/107782/ http://dx.doi.org/10.1109/NBEC58134.2023.10352619
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.utm.107782
record_format	eprints
spelling	my.utm.1077822024-10-02T07:33:18Z http://eprints.utm.my/107782/ Failure prediction for hemodialysis units using machine learning and hall effect sensors Noordin, Muhammad Khair Amran, Mohd. Effendi Bani, Nurul Aini Ahmad Kamil, Ahmad Safwan Md. Nasir, Ahmad Nabil Arsat, Mahyuddin H Social Sciences (General) Hemodialysis Units (HDUs) are critical for providing essential dialysis treatments to patients with renal failure. However, failures in HDUs, particularly water pump failures, can disrupt patient care and compromise safety. This study focused on predicting water pump failures in HDUs using machine learning algorithms and Hall Effect sensors. By monitoring the magnetic field strength of water pump motors and leveraging machine learning, the research successfully estimated the Remaining Useful Life (RUL) of water pumps. The findings of this study demonstrated the effectiveness of the proposed approach in enhancing maintenance and reliability, thereby improving patient safety and care. The use of Hall Effect sensors provided non-invasive monitoring capabilities, ensuring easy integration into existing HDU infrastructure while minimizing disruptions. The cost-effectiveness of the sensors allowed for the widespread deployment of multiple sensors across different pumps, enhancing monitoring capabilities and reducing maintenance costs. The discussion surrounding this research highlighted the advantages of AI and machine learning in predictive maintenance for medical equipment. The ability to accurately estimate the RUL of water pumps enabled early intervention, reducing the risks associated with failures and minimizing treatment disruptions. The data-driven insights provided by machine learning algorithms facilitated informed decision-making and optimized maintenance planning, resulting in enhanced operational efficiency and improved patient outcomes. In conclusion, this study presented a proactive maintenance approach for water pump failure prediction in HDUs, leveraging machine learning algorithms and Hall Effect sensors. The findings demonstrated the successful estimation of the RUL of water pumps, enabling early intervention and minimizing risks. The implementation of AI and machine learning techniques, along with Hall Effect sensors, offered valuable insights for maintenance planning, ensuring reliable HDU system operation. By adopting such approaches, healthcare facilities can optimize their operations, enhance patient safety, and deliver high-quality care in HDUs. 2023 Conference or Workshop Item PeerReviewed Noordin, Muhammad Khair and Amran, Mohd. Effendi and Bani, Nurul Aini and Ahmad Kamil, Ahmad Safwan and Md. Nasir, Ahmad Nabil and Arsat, Mahyuddin (2023) Failure prediction for hemodialysis units using machine learning and hall effect sensors. In: 2023 IEEE 2nd National Biomedical Engineering Conference (NBEC), 5 September 2023-7 September 2023, Melaka, Malaysia. http://dx.doi.org/10.1109/NBEC58134.2023.10352619
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	H Social Sciences (General)
spellingShingle	H Social Sciences (General) Noordin, Muhammad Khair Amran, Mohd. Effendi Bani, Nurul Aini Ahmad Kamil, Ahmad Safwan Md. Nasir, Ahmad Nabil Arsat, Mahyuddin Failure prediction for hemodialysis units using machine learning and hall effect sensors
description	Hemodialysis Units (HDUs) are critical for providing essential dialysis treatments to patients with renal failure. However, failures in HDUs, particularly water pump failures, can disrupt patient care and compromise safety. This study focused on predicting water pump failures in HDUs using machine learning algorithms and Hall Effect sensors. By monitoring the magnetic field strength of water pump motors and leveraging machine learning, the research successfully estimated the Remaining Useful Life (RUL) of water pumps. The findings of this study demonstrated the effectiveness of the proposed approach in enhancing maintenance and reliability, thereby improving patient safety and care. The use of Hall Effect sensors provided non-invasive monitoring capabilities, ensuring easy integration into existing HDU infrastructure while minimizing disruptions. The cost-effectiveness of the sensors allowed for the widespread deployment of multiple sensors across different pumps, enhancing monitoring capabilities and reducing maintenance costs. The discussion surrounding this research highlighted the advantages of AI and machine learning in predictive maintenance for medical equipment. The ability to accurately estimate the RUL of water pumps enabled early intervention, reducing the risks associated with failures and minimizing treatment disruptions. The data-driven insights provided by machine learning algorithms facilitated informed decision-making and optimized maintenance planning, resulting in enhanced operational efficiency and improved patient outcomes. In conclusion, this study presented a proactive maintenance approach for water pump failure prediction in HDUs, leveraging machine learning algorithms and Hall Effect sensors. The findings demonstrated the successful estimation of the RUL of water pumps, enabling early intervention and minimizing risks. The implementation of AI and machine learning techniques, along with Hall Effect sensors, offered valuable insights for maintenance planning, ensuring reliable HDU system operation. By adopting such approaches, healthcare facilities can optimize their operations, enhance patient safety, and deliver high-quality care in HDUs.
format	Conference or Workshop Item
author	Noordin, Muhammad Khair Amran, Mohd. Effendi Bani, Nurul Aini Ahmad Kamil, Ahmad Safwan Md. Nasir, Ahmad Nabil Arsat, Mahyuddin
author_facet	Noordin, Muhammad Khair Amran, Mohd. Effendi Bani, Nurul Aini Ahmad Kamil, Ahmad Safwan Md. Nasir, Ahmad Nabil Arsat, Mahyuddin
author_sort	Noordin, Muhammad Khair
title	Failure prediction for hemodialysis units using machine learning and hall effect sensors
title_short	Failure prediction for hemodialysis units using machine learning and hall effect sensors
title_full	Failure prediction for hemodialysis units using machine learning and hall effect sensors
title_fullStr	Failure prediction for hemodialysis units using machine learning and hall effect sensors
title_full_unstemmed	Failure prediction for hemodialysis units using machine learning and hall effect sensors
title_sort	failure prediction for hemodialysis units using machine learning and hall effect sensors
publishDate	2023
url	http://eprints.utm.my/107782/ http://dx.doi.org/10.1109/NBEC58134.2023.10352619
_version_	1814043521463615488
score	13.211869

Failure prediction for hemodialysis units using machine learning and hall effect sensors

Similar Items