Optimized machine learning approaches for identifying vertical temperature gradient on ballastless track in natural environments

Due to the exposure of ballastless track to various geographical and meteorological conditions, the effects of temperature evolution on the performance of ballastless track should be considered. However, accurately pre-dicting the vertical temperature gradient (VTG) on ballastless track in thermal environments has been chal-lenging. This study develops four machine learning (ML) approaches, i.e., support vector regression (SVR), random forest (RF), extreme gradient boosting (XGBOOST), and artificial neural network (ANN), to identify the ballastless track's VTG evolution in natural environments. The above ML approaches with hyperparameters optimized are trained and tested by 2000 samples from full-scale finite element simulation. The temperature field monitoring on ballastless track is performed to validate its temperature distribution simulation. The results show the XGBOOST-based method has the best accuracy for identifying the ballastless track's VTG among the four selected ML approaches. Furthermore, the stacking-based hybrid framework is proposed to further improve the four selected ML approaches. For the stacking strategy, the improvement percentage of MAE of performance and transferability to the four selected ML approaches are 11.51%-55.43%, and 42.27%-77.79%, respectively. The proposed ML approaches are proven capable and efficient for predicting the temperature evolution of track engineering.

Automated summary

As ballastless track is exposed to different geographical and meteorological conditions, the impact of temperature changes on its performance must be considered. However, accurately predicting the vertical temperature gradient (VTG) on ballastless track in thermal environments has been challenging. This study develops four machine learning approaches to identify the ballastless track's VTG evolution and proposes a stacking-based hybrid framework to further improve the accuracy of prediction. The results show that the XGBOOST-based method has the best accuracy among the four selected machine learning approaches.