Implementation of Machine Learning in Analyzing the Effect of Maintenance on the Reliability of Railway Detection Equipment


Authors : Fajar Sodik; Kusrini; Kusnawi

Volume/Issue : Volume 8 - 2023, Issue 10 - October

Google Scholar : https://tinyurl.com/yjb5sser

Scribd : https://tinyurl.com/28s2tdba

DOI : https://doi.org/10.5281/zenodo.10049761

Abstract : Maintenance is something that must be done on equipment to maintain its reliability. It is necessary to determine the correct maintenance period to make it more effective and efficient so that reliability is maintained while being efficient in terms of costs incurred. This research aims to determine the best algorithm between polynomial regression and Nadaraya Watson kernel regression to determine the maintenance period for train detection equipment and determine the variables that influence the determination of the maintenance period, which has an impact on equipment reliability. Testing the polynomial regression model produces a mean absolute error of 8.05, a mean squared error of 568.74, and a determination coefficient of 0.999, while the Nadaraya Watson regression model produces a mean absolute error of 3.14, a mean squared error of 19.43, and a determination coefficient of 0.938. Thus, it can be concluded that the Nadaraya Watson Kernel Regression model can be used well to determine the maintenance period for train detection equipment.

Keywords : Polynomial Regression; Nadaraya Watson Kernel Regression; Train Detector.

Maintenance is something that must be done on equipment to maintain its reliability. It is necessary to determine the correct maintenance period to make it more effective and efficient so that reliability is maintained while being efficient in terms of costs incurred. This research aims to determine the best algorithm between polynomial regression and Nadaraya Watson kernel regression to determine the maintenance period for train detection equipment and determine the variables that influence the determination of the maintenance period, which has an impact on equipment reliability. Testing the polynomial regression model produces a mean absolute error of 8.05, a mean squared error of 568.74, and a determination coefficient of 0.999, while the Nadaraya Watson regression model produces a mean absolute error of 3.14, a mean squared error of 19.43, and a determination coefficient of 0.938. Thus, it can be concluded that the Nadaraya Watson Kernel Regression model can be used well to determine the maintenance period for train detection equipment.

Keywords : Polynomial Regression; Nadaraya Watson Kernel Regression; Train Detector.

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe