Highway agencies all around the country, including the Wyoming Department of Transportation (WYDOT), have deep concerns about truck crashes resulting from brake temperatures exceeding the critical brake temperature as they descend steep downgrades. Through a series of research initiatives starting in the 1980s, WYDOT has developed a Grade Severity Rating System (GSRS) to estimate the maximum safe speed for trucks during downgrade descent. In 2020, the updated mathematical model was automated through an interactive, intuitive, aesthetically appealing, and user-friendly objected-oriented Visual Basic.net software. Additional research on the GSRS model was commissioned by WYDOT to account for large truck vehicle stability—specifically, rollovers and skidding/side slip during grade descent. These scenarios become relevant in the presence of horizontal curves. Consequently, this latest mathematical model has been automated to simplify the computation of maximum safe descent speed on the downgrades combined with curves, all based on the truck weight. As in the previous version of the software, it provides functionality for both the continuous slope and the separate downgrade method. The primary beneficiaries of the software will be highway agencies who will be able to estimate the maximum safe speed of descent for trucks descending downgrades with horizontal curves at various weight categories and therefore produce Weight Specific Speed (WSS) signs for each downgrade or multi-grade section.
Truck crashes on steep downgrades due to excessive brake heating, resulting from brake applications to control speeding, are a continuing cause of concern for the Wyoming Department of Transportation (WYDOT). In 2016, WYDOT funded a project to update the existing Grade Severity Rating System. Furthermore, in 2020, WYDOT commissioned a research project to automate the updated version of the mathematical model through an interactive, intuitive, aesthetically appealing and user-friendly Visual Basic.net objected-oriented software to simplify the computation of the maximum safe descent speed on these downgrades based on the truck weight. The software provides functionality for both the continuous Slope and separate downgrade methods. The primary beneficiaries of this software will be the highway agencies who will be able to estimate the maximum safe speed of descent for trucks with various weight categories and hence produce Weight Specific Speed (WSS) signs for each downgrade or a multigrade section.
This study involved the investigation of various machine learning methods, including four classification tree-based ML models, namely the Adaptive Boosting tree, Random Forest, Gradient Boost Decision Tree, Extreme Gradient Boosting tree, and three non-tree-based ML models, namely Support Vector Machines, Multi-layer Perceptron and k-Nearest Neighbors for predicting the level of severity of large truck crashes on Wyoming road networks. The accuracy of these seven methods was then compared. The Final ROC AUC score for the optimized random forest model is 95.296 %. The next highest performing model was the k-NN with 92.780 %, M.L.P. with 87.817 %, XGBoost with 86.542 %, Gradboost with 74.824 %, SVM with 72.648 % and AdaBoost with 67.232 %. Based on the analysis, the top 10 predictors of severity were obtained from the feature importance plot. These may be classified into whether safety equipment was used, whether airbags were deployed, the gender of the driver and whether alcohol was involved.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.