A Rail-Temperature-Prediction Model Considering Meteorological Conditions and the Position of the Sun

Hong, Sung Uk; Kim, Hyong Uk; Lim, Nam-Hyoung; Kim, Kyung Ho; Kim, Hong-jip; Cho, Seong Jin

doi:10.1007/s12541-019-00015-1

Cited by 10 publications

(27 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Direct sampling of the actual rail environment during train operation is impractical for safety reasons. Rail temperatures are usually measured indirectly within a measurement station that simulates the environment of the railway installation [ 7 , 10 , 11 , 13 , 19 ]. As in previous work, we collected the rail temperature and weather data every 10 min at a measurement station from August of 2016 to May of 2017 [ 7 , 20 ].…”

Section: Measurementmentioning

confidence: 99%

“…Rail temperatures are usually measured indirectly within a measurement station that simulates the environment of the railway installation [ 7 , 10 , 11 , 13 , 19 ]. As in previous work, we collected the rail temperature and weather data every 10 min at a measurement station from August of 2016 to May of 2017 [ 7 , 20 ]. The constructed measurement station consisted of a 500-mm long KS 50n rail, a data acquisition system (DAQ), a weather station, and K-type thermocouples.…”

Section: Measurementmentioning

confidence: 99%

“…The previous RTPMs are classified into three types: empirical equation-based models, multivariate regression models, and thermal analysis models [ 7 , 8 , 9 , 10 , 11 , 12 , 13 ].…”

Section: Introductionmentioning

confidence: 99%

“…Since thermodynamic models consider the laws of nature, they are more generalizable than RTPMs based on statistical methods, which tend to require specific data. However, to guarantee high performance ( R 2 = 0.9334, RMSE = 3.799 °C), such models require precise knowledge of the rail properties, such as the reflectance and emissivity properties [ 7 , 10 , 11 , 12 , 13 , 14 ].…”

Section: Introductionmentioning

confidence: 99%

“…First, their performance in predicting the rail temperature is too low for practical use. In previous RTPMs based on thermodynamic principles ( R 2 = 0.9334, RMSE = 3.799 °C), the predicted rail temperature deviated by up to 15 °C from the measured rail temperature [ 7 ]. Since the main goal of RTPMs is preventing buckling on hot days, this difference is unacceptable in practical use.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Rail-Temperature-Prediction Model Based on Machine Learning: Warning of Train-Speed Restrictions Using Weather Forecasting

Hong

Park

Cho

2021

Sensors

Self Cite

View full text Add to dashboard Cite

Predicting the rail temperature of a railway system is important for establishing a rail management plan against railway derailment caused by orbital buckling. The rail temperature, which is directly responsible for track buckling, is closely related to air temperature, which continuously increases due to global warming effects. Moreover, railway systems are increasingly installed with continuous welded rails (CWRs) to reduce train vibration and noise. Unfortunately, CWRs are prone to buckling. This study develops a reliable and highly accurate novel model that can predict rail temperature using a machine learning method. To predict rail temperature over the entire network with high-prediction performance, the weather effect and solar effect features are used. These features originate from the analysis of the thermal environment around the rail. Precisely, the presented model has a higher performance for predicting high rail temperature than other models. As a convenient structural health-monitoring application, the train-speed-limit alarm-map (TSLAM) was also proposed, which visually maps the predicted rail-temperature deviations over the entire network for railway safety officers. Combined with TSLAM, our rail-temperature prediction model is expected to improve track safety and train timeliness.

show abstract

Section: Measurementmentioning

confidence: 99%

Section: Measurementmentioning

confidence: 99%

“…The previous RTPMs are classified into three types: empirical equation-based models, multivariate regression models, and thermal analysis models [ 7 , 8 , 9 , 10 , 11 , 12 , 13 ].…”

Section: Introductionmentioning

confidence: 99%