TY - GEN
T1 - RAIL NEUTRAL TEMPERATURE ESTIMATION USING FIELD DATA, NUMERICAL MODELS, and MACHINE LEARNING
AU - Wu, Yuning
AU - Zhu, Xuan
AU - Huang, Chi Luen
AU - Lee, Sangmin
AU - Dersch, Marcus
AU - Popovics, John S.
N1 - This work was supported by the U.S. National Academy of Sciences Rail Safety IDEA program, project RS-41 and partially funded by the startup package at the University of Utah. The authors appreciate the input from IDEA program manager Dr. Basemera-Fitzpatrick and the expert review panel associated with the project. The opinion expressed in this paper are solely of the authors, and the U.S. National Academy of Sciences, Engineering, and Medicine and the U.S. Government do not necessarily concur with, endorse, or adopt the findings, conclusions, and recommendations either inferred or expressly stated in the paper. The field data collection was coordinated and supported by BNSF Railway Company.
PY - 2021
Y1 - 2021
N2 - Effective Rail Neutral Temperature (RNT) management is needed for continuous welded rail (CWR). RNT is the temperature at which the longitudinal stress of a rail is zero. Due to the lack of expansion joints, CWR develops internal tensile or compressive stresses when the rail temperature is below or above, respectively, the RNT. Mismanagement of RNT can lead to rail fracture or buckling when thermal stresses exceed the limits of rail steel. In this work, we propose an effective RNT estimation method structured around four hypotheses. The work leverages field-collected vibration test data, high-fidelity numerical models, and machine learning techniques. First, a contactless non-destructive and non-disruptive sensing technology was developed to collect real-world rail vibrational data. Second, the team established an instrumented field test site at a revenue-service line in the state of Illinois and performed multi-day data collection to cover a wide range of temperature and thermal stress levels. Third, numerical models were developed to understand and predict rail vibration behavior under the influence of temperature and longitudinal load. Excellent agreement between model and experimental results were obtained using an optimization approach. Finally, a supervised machine learning algorithm was developed to estimate RNT using the field-collected rail vibration data. Sensitivity studies and error analyses were included in this work. The system performance with field data indicates that the proposed framework can support reasonable RNT estimation accuracy when measurement or model noise is low.
AB - Effective Rail Neutral Temperature (RNT) management is needed for continuous welded rail (CWR). RNT is the temperature at which the longitudinal stress of a rail is zero. Due to the lack of expansion joints, CWR develops internal tensile or compressive stresses when the rail temperature is below or above, respectively, the RNT. Mismanagement of RNT can lead to rail fracture or buckling when thermal stresses exceed the limits of rail steel. In this work, we propose an effective RNT estimation method structured around four hypotheses. The work leverages field-collected vibration test data, high-fidelity numerical models, and machine learning techniques. First, a contactless non-destructive and non-disruptive sensing technology was developed to collect real-world rail vibrational data. Second, the team established an instrumented field test site at a revenue-service line in the state of Illinois and performed multi-day data collection to cover a wide range of temperature and thermal stress levels. Third, numerical models were developed to understand and predict rail vibration behavior under the influence of temperature and longitudinal load. Excellent agreement between model and experimental results were obtained using an optimization approach. Finally, a supervised machine learning algorithm was developed to estimate RNT using the field-collected rail vibration data. Sensitivity studies and error analyses were included in this work. The system performance with field data indicates that the proposed framework can support reasonable RNT estimation accuracy when measurement or model noise is low.
KW - Vibration
KW - continuous welded rails
KW - finite element simulation
KW - machine learning
KW - rail neutral temperature
KW - thermal buckling prevention
UR - http://www.scopus.com/inward/record.url?scp=85109075794&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85109075794&partnerID=8YFLogxK
U2 - 10.1115/JRC2021-58324
DO - 10.1115/JRC2021-58324
M3 - Conference contribution
AN - SCOPUS:85109075794
T3 - Proceedings of the 2021 Joint Rail Conference, JRC 2021
BT - Proceedings of the 2021 Joint Rail Conference, JRC 2021
PB - American Society of Mechanical Engineers (ASME)
T2 - 2021 Joint Rail Conference, JRC 2021
Y2 - 20 April 2021 through 21 April 2021
ER -