This work correlated the detailed work zone location and time data from the Wis LCS system with the five-min inductive loop detector data. One-sample percentile value test and two-sample Kolmogorov-Smirnov(K-S) test w...This work correlated the detailed work zone location and time data from the Wis LCS system with the five-min inductive loop detector data. One-sample percentile value test and two-sample Kolmogorov-Smirnov(K-S) test were applied to compare the speed and flow characteristics between work zone and non-work zone conditions. Furthermore, we analyzed the mobility characteristics of freeway work zones within the urban area of Milwaukee, WI, USA. More than 50% of investigated work zones have experienced speed reduction and 15%-30% is necessary reduced volumes. Speed reduction was more significant within and at the downstream of work zones than at the upstream.展开更多
The time resolution of the existing traffic flow prediction model is too big to be applied to adaptive signal timing optimization.Based on the view of the platoon dispersion model,the relationship between vehicle arri...The time resolution of the existing traffic flow prediction model is too big to be applied to adaptive signal timing optimization.Based on the view of the platoon dispersion model,the relationship between vehicle arrival at the downstream intersection and vehicle departure from the upstream intersection was analyzed.Then,a high-resolution traffic flow prediction model based on deep learning was developed.The departure flow rate from the upstream and the arrival flow rate at the downstream intersection was taking as the input and output in the proposed model,respectively.Finally,the parameters of the proposed model were trained by the field data,and the proposed model was implemented to forecast the arrival flow rate of the downstream intersection.Results show that the proposed model can better capture the fluctuant traffic flow and reduced MAE,MRE,and RMSE by 9.53%,39.92%,and 3.56%,respectively,compared with traditional models and algorithms,such as Robertson's model and artificial neural network.Therefore,the proposed model can be applied for realtime adaptive signal timing optimization.展开更多
In order to understand how the uncertainties in the output can be apportioned to different sources of uncertainties in its inputs, it is critical to investigate the sensitivity of MOVES model. The MOVES model sensitiv...In order to understand how the uncertainties in the output can be apportioned to different sources of uncertainties in its inputs, it is critical to investigate the sensitivity of MOVES model. The MOVES model sensitivity for regional level has been well studied. However, the uncertainty analysis for project level running emissions has not been well understood. In this research, the MOVES model project level sensitivity tests on running emissions were conducted thru the analysis of vehicle specific power (VSP), scaled tractive power (STP), and MOVES emission rates versus speed curves. This study tested the speed, acceleration, and grade-three most critical variables for vehicle specific power for light duty vehicles and scaled tractive power for heavy duty vehicles. For the testing of STP, four regulatory classes of heavy duty vehicles including light heavy duty (LHD), medium heavy duty (MHD), heavy heavy duty (HHD) and bus were selected. MOVES project running emission rates were also tested for CO, PM2.5, NOx, and VOC versus the operating speeds. A Latin Hypercube (LH) sampling based on method for estimation of the "Sobal" sensitivity indices shows that the speed is the most critical variable among the three inputs for both VSP and STP. Acceleration and grades show lower response to the main effects and sensitivity indices. MOVES emission rates versus speeds curves for light duty vehicles show that highest emission occurs at lower speed range. No significant differences on emission rates among the regulatory classes of heavy duty vehicles are identified.展开更多
基金Project(61620106002)supported by the National Natural Science Foundation of ChinaProject(2016YFB0100906)supported by the National Key R&D Program in China+1 种基金Project(2015364X16030)supported by the Information Technology Research Project of Ministry of Transport of ChinaProject(2242015K42132)supported by the Fundamental Sciences of Southeast University,China
文摘This work correlated the detailed work zone location and time data from the Wis LCS system with the five-min inductive loop detector data. One-sample percentile value test and two-sample Kolmogorov-Smirnov(K-S) test were applied to compare the speed and flow characteristics between work zone and non-work zone conditions. Furthermore, we analyzed the mobility characteristics of freeway work zones within the urban area of Milwaukee, WI, USA. More than 50% of investigated work zones have experienced speed reduction and 15%-30% is necessary reduced volumes. Speed reduction was more significant within and at the downstream of work zones than at the upstream.
文摘The time resolution of the existing traffic flow prediction model is too big to be applied to adaptive signal timing optimization.Based on the view of the platoon dispersion model,the relationship between vehicle arrival at the downstream intersection and vehicle departure from the upstream intersection was analyzed.Then,a high-resolution traffic flow prediction model based on deep learning was developed.The departure flow rate from the upstream and the arrival flow rate at the downstream intersection was taking as the input and output in the proposed model,respectively.Finally,the parameters of the proposed model were trained by the field data,and the proposed model was implemented to forecast the arrival flow rate of the downstream intersection.Results show that the proposed model can better capture the fluctuant traffic flow and reduced MAE,MRE,and RMSE by 9.53%,39.92%,and 3.56%,respectively,compared with traditional models and algorithms,such as Robertson's model and artificial neural network.Therefore,the proposed model can be applied for realtime adaptive signal timing optimization.
基金support by U.S.Environmental Protection AgencyOhio Department of Transportation
文摘In order to understand how the uncertainties in the output can be apportioned to different sources of uncertainties in its inputs, it is critical to investigate the sensitivity of MOVES model. The MOVES model sensitivity for regional level has been well studied. However, the uncertainty analysis for project level running emissions has not been well understood. In this research, the MOVES model project level sensitivity tests on running emissions were conducted thru the analysis of vehicle specific power (VSP), scaled tractive power (STP), and MOVES emission rates versus speed curves. This study tested the speed, acceleration, and grade-three most critical variables for vehicle specific power for light duty vehicles and scaled tractive power for heavy duty vehicles. For the testing of STP, four regulatory classes of heavy duty vehicles including light heavy duty (LHD), medium heavy duty (MHD), heavy heavy duty (HHD) and bus were selected. MOVES project running emission rates were also tested for CO, PM2.5, NOx, and VOC versus the operating speeds. A Latin Hypercube (LH) sampling based on method for estimation of the "Sobal" sensitivity indices shows that the speed is the most critical variable among the three inputs for both VSP and STP. Acceleration and grades show lower response to the main effects and sensitivity indices. MOVES emission rates versus speeds curves for light duty vehicles show that highest emission occurs at lower speed range. No significant differences on emission rates among the regulatory classes of heavy duty vehicles are identified.