Study on Securing the Reliability of the Supply and Demand Plan for Wheel Exchange through the Prediction of Wheel Exchange Cycle 


Vol. 36,  No. 6, pp. 86-93, Dec.  2021
10.14346/JKOSOS.2021.36.6.86


PDF
  Abstract

Planning of the annual demand and supply of wheel exchanges should be based on accurate data. However, in several cases, supply and demand exceed the planned amounts every year. To manage such cases, six linear regression models were designed using Scikit-Learn, a Python-based machine learning library, to identify characteristics such as wheel thickness (mm), mileage (km), number of trips, flange thickness (mm), and flange wear (mm). Among these models, RandomForestRegressor, which yielded the best performance evaluation index for the model and the most accurate prediction in the verification of new data in terms of root mean square error and R-Squared values, was selected as the predictive model. By using this final model to accurately predict the wheel exchange cycle, we intend to secure the reliability of the wheel exchange demand and supply plan.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

이대은 and 구정서, "Study on Securing the Reliability of the Supply and Demand Plan for Wheel Exchange through the Prediction of Wheel Exchange Cycle," Journal of the Korean Society of Safety, vol. 36, no. 6, pp. 86-93, 2021. DOI: 10.14346/JKOSOS.2021.36.6.86.

[ACM Style]

이대은 and 구정서. 2021. Study on Securing the Reliability of the Supply and Demand Plan for Wheel Exchange through the Prediction of Wheel Exchange Cycle. Journal of the Korean Society of Safety, 36, 6, (2021), 86-93. DOI: 10.14346/JKOSOS.2021.36.6.86.

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)

pISSN : 1229 - 9197
eISSN : 1875 - 0052

Impact Factor(2022): 2.5