Pub Date : 2023-11-09DOI: 10.1177/03611981231198480
Yang Song, Ang Li, Hongshuai Wang, Xiaofeng Xu, Xin Wang, Zuoming Xiao, Qiang Yuan
When shield tunneling is performed in water-rich silt and fine sand strata, the grout becomes runny when diluted by groundwater. After dilution, the filling effect of the grout is not significant, and the level of surface settlement is very high. In this study, based on bidding section 04 of Tianjin Metro Line 11, traditional grouting materials were selected to conduct response surface method (RSM) tests. The purposes of the RSM analysis were to analyze the interactions between materials and their influences on grout performance and to optimize the grout mix ratio. Various admixtures were compared to assess the effects of different admixtures and compositions on the dispersion resistance and flow performance of the grout. Finally, a shield synchronous grouting test system was developed, and a similar indoor grouting simulation test was performed to analyze the influences of the different admixtures on the filling effects and to determine a reasonable grout mix ratio. The following three results were obtained. (1) The RSM was suitable for grout performance prediction and grout mix ratio optimization, and hydroxyethyl cellulose could improve the grout performance and increase the bond performance between the cementing material and aggregate. (2) Admixture incorporation enhancement could improve the grout utilization rate and increase the diffusion distance at the top of the tunnel, which would be conducive to filling the gap at the tail end of the shield. (3) The optimal preparation scheme of grout in water-rich fine sand formations included a water–binder ratio of 0.72, cement–sand ratio of 0.80, fly ash content of 5%, bentonite content of 14.94%, and admixture content of 0.8%–0.9%
{"title":"Optimization of the Grout Mix Ratio and Simulation Test of Shield Tail Grouting Similarities in a Water-Rich Fine Sand Layer","authors":"Yang Song, Ang Li, Hongshuai Wang, Xiaofeng Xu, Xin Wang, Zuoming Xiao, Qiang Yuan","doi":"10.1177/03611981231198480","DOIUrl":"https://doi.org/10.1177/03611981231198480","url":null,"abstract":"When shield tunneling is performed in water-rich silt and fine sand strata, the grout becomes runny when diluted by groundwater. After dilution, the filling effect of the grout is not significant, and the level of surface settlement is very high. In this study, based on bidding section 04 of Tianjin Metro Line 11, traditional grouting materials were selected to conduct response surface method (RSM) tests. The purposes of the RSM analysis were to analyze the interactions between materials and their influences on grout performance and to optimize the grout mix ratio. Various admixtures were compared to assess the effects of different admixtures and compositions on the dispersion resistance and flow performance of the grout. Finally, a shield synchronous grouting test system was developed, and a similar indoor grouting simulation test was performed to analyze the influences of the different admixtures on the filling effects and to determine a reasonable grout mix ratio. The following three results were obtained. (1) The RSM was suitable for grout performance prediction and grout mix ratio optimization, and hydroxyethyl cellulose could improve the grout performance and increase the bond performance between the cementing material and aggregate. (2) Admixture incorporation enhancement could improve the grout utilization rate and increase the diffusion distance at the top of the tunnel, which would be conducive to filling the gap at the tail end of the shield. (3) The optimal preparation scheme of grout in water-rich fine sand formations included a water–binder ratio of 0.72, cement–sand ratio of 0.80, fly ash content of 5%, bentonite content of 14.94%, and admixture content of 0.8%–0.9%","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":" 20","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135242041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-09DOI: 10.1177/03611981231205876
Ahmet Yildiz, Oktay Arikan, Kemal Keskin
This manuscript presents a speed trajectory optimization to minimize driving energy consumption using four different nature-inspired algorithms. For this purpose, a model was developed that can simulate motion of a single train. To test the train motion model and speed trajectories, Istanbul M3 subway line was modeled with its actual parameters such as gradient, curve, and speed limit. Concerning computational time and energy usage, a straightforward speed profile and proposed speed profiles by the algorithms have been compared. Afterwards, variable passenger numbers at each station in a certain hour were taken as dynamic mass input. With the marine predator algorithm (MPA) that finds the best result among the four, speed profile optimization was performed again under the effect of unstable mass. Finally, a train was operated by a driver according to the optimal speed profile. As a result, energy saving is 18.75% in simulation environment and 21.27% in real-life test.
{"title":"Energy-Efficient Train Operation Optimization in Istanbul Metro Network Considering Variable Passenger Numbers","authors":"Ahmet Yildiz, Oktay Arikan, Kemal Keskin","doi":"10.1177/03611981231205876","DOIUrl":"https://doi.org/10.1177/03611981231205876","url":null,"abstract":"This manuscript presents a speed trajectory optimization to minimize driving energy consumption using four different nature-inspired algorithms. For this purpose, a model was developed that can simulate motion of a single train. To test the train motion model and speed trajectories, Istanbul M3 subway line was modeled with its actual parameters such as gradient, curve, and speed limit. Concerning computational time and energy usage, a straightforward speed profile and proposed speed profiles by the algorithms have been compared. Afterwards, variable passenger numbers at each station in a certain hour were taken as dynamic mass input. With the marine predator algorithm (MPA) that finds the best result among the four, speed profile optimization was performed again under the effect of unstable mass. Finally, a train was operated by a driver according to the optimal speed profile. As a result, energy saving is 18.75% in simulation environment and 21.27% in real-life test.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"182 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135242015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-09DOI: 10.1177/03611981231203231
Daniel Castro-Fresno, Helena Miera-Dominguez, Pedro Lastra-González, Irune Indacoechea-Vega, Ronald van Loon, Gijsjan van Blokland
Road transportation is one of the major sources of noise emissions that seriously affect human health. The porous surfaces of roads are sound absorbing, which helps to reduce noise pollution. For this purpose, different two-layer porous asphalt mixtures were evaluated both mechanically and functionally, to develop an asphalt mixture that reduces the noise generated between tires and road. This research focused on the variables that determine the main properties to be considered: texture wavelength spectrum, acoustic absorption, and flow resistivity. Void content, thickness, and maximum aggregate size were identified as the variables that should be controlled to decrease noise emissions.
{"title":"Two-Layer Porous Asphalt: Main Properties to Decrease the Noise Emissions","authors":"Daniel Castro-Fresno, Helena Miera-Dominguez, Pedro Lastra-González, Irune Indacoechea-Vega, Ronald van Loon, Gijsjan van Blokland","doi":"10.1177/03611981231203231","DOIUrl":"https://doi.org/10.1177/03611981231203231","url":null,"abstract":"Road transportation is one of the major sources of noise emissions that seriously affect human health. The porous surfaces of roads are sound absorbing, which helps to reduce noise pollution. For this purpose, different two-layer porous asphalt mixtures were evaluated both mechanically and functionally, to develop an asphalt mixture that reduces the noise generated between tires and road. This research focused on the variables that determine the main properties to be considered: texture wavelength spectrum, acoustic absorption, and flow resistivity. Void content, thickness, and maximum aggregate size were identified as the variables that should be controlled to decrease noise emissions.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":" 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135242055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-09DOI: 10.1177/03611981231205882
Xiaotong Ding, John Maleyeff, Frans Valk
A business intelligence (BI) system was designed to create a proactive, reactive, and precursor decision tool to improve safety of bus operations at the Massachusetts Bay Transportation Authority (MBTA). The system’s development was motivated in part by recommendations of a safety inspection by the Federal Transportation Administration, and the realization that the MBTA has access to vest amounts of data that are not being used to create information effectively. The developers reduced the complexity of the BI system by incorporating analytics to determine the areas of focus where safety has the most impact. Challenges were posed by the need to integrate internal and external databases with various formats and structures, and the desire to create a self-service BI solution for multiple MBTA users. The resulting BI solution includes applications that support key performance indicator analyses, root cause investigations, and targeted improvement actions. These applications represent an enhanced approach that combines data for a more holistic analysis and eliminates the need to transfer datasets or data analyses by email. The system includes various forms of visualizations to help users navigate the myriad of information, including geospatial maps, interactive pie, line, and bar charts, and word frequency and relationship mapping. The paper details the system’s development and how analytical approaches were used to expose important information that is hidden in the data. Examples of applications are shown using screenshots and a general workflow is presented that could be applicable to agencies with fewer resources.
{"title":"Bus Operation Safety Business Intelligence Solution: Applying Analytics for Key Performance Indicator, Investigation, and Targeted Actions Analyses with a Centralized Data Warehouse","authors":"Xiaotong Ding, John Maleyeff, Frans Valk","doi":"10.1177/03611981231205882","DOIUrl":"https://doi.org/10.1177/03611981231205882","url":null,"abstract":"A business intelligence (BI) system was designed to create a proactive, reactive, and precursor decision tool to improve safety of bus operations at the Massachusetts Bay Transportation Authority (MBTA). The system’s development was motivated in part by recommendations of a safety inspection by the Federal Transportation Administration, and the realization that the MBTA has access to vest amounts of data that are not being used to create information effectively. The developers reduced the complexity of the BI system by incorporating analytics to determine the areas of focus where safety has the most impact. Challenges were posed by the need to integrate internal and external databases with various formats and structures, and the desire to create a self-service BI solution for multiple MBTA users. The resulting BI solution includes applications that support key performance indicator analyses, root cause investigations, and targeted improvement actions. These applications represent an enhanced approach that combines data for a more holistic analysis and eliminates the need to transfer datasets or data analyses by email. The system includes various forms of visualizations to help users navigate the myriad of information, including geospatial maps, interactive pie, line, and bar charts, and word frequency and relationship mapping. The paper details the system’s development and how analytical approaches were used to expose important information that is hidden in the data. Examples of applications are shown using screenshots and a general workflow is presented that could be applicable to agencies with fewer resources.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"172 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135241844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-09DOI: 10.1177/03611981231206167
Clare Nelson, Gregory Rowangould
Examining substitutes to the current state and federal gasoline and diesel fuel excise taxes has become a pressing issue, exacerbated by the rise of high-efficiency and alternative-fuel vehicles threatening the revenue-generating capacity of these taxes. A mileage-based user fee has been frequently proposed in the literature as an alternative that would offer greater benefits to rural and low-income populations than to urban and higher-income populations. However, most prior analyses relied on small data sets and aggregated data. This study examined the impact of replacing the Vermont state fuels tax with a revenue-neutral, mileage-based user fee using mileage and fuel economy data for over 300,000 registered passenger vehicles. We found that, on average, Vermont households would pay an additional $23 per year, with rural households and low-income households facing smaller tax burdens than their urban and high-income counterparts. The impact of a $180 flat fee replacing the Vermont state motor fuels tax was also examined owing to state interest. Findings indicated that a flat fee would result in much larger price fluctuations, with most households paying an additional $47 per year. The disaggregated data approach presented here directly addresses public misconceptions of inequitable cost differences and provides context for public education campaigns to garner mileage-based user fee policy support. Based on our results, there is political ground for further research into the implementation of a mileage-based user fee, including the logistics of an administrative transition to mileage charging and the associated program implementation and technological costs.
{"title":"Data-Driven Analysis of Rural Equity and Cost Concerns for Mileage-Based User Fees in Vermont","authors":"Clare Nelson, Gregory Rowangould","doi":"10.1177/03611981231206167","DOIUrl":"https://doi.org/10.1177/03611981231206167","url":null,"abstract":"Examining substitutes to the current state and federal gasoline and diesel fuel excise taxes has become a pressing issue, exacerbated by the rise of high-efficiency and alternative-fuel vehicles threatening the revenue-generating capacity of these taxes. A mileage-based user fee has been frequently proposed in the literature as an alternative that would offer greater benefits to rural and low-income populations than to urban and higher-income populations. However, most prior analyses relied on small data sets and aggregated data. This study examined the impact of replacing the Vermont state fuels tax with a revenue-neutral, mileage-based user fee using mileage and fuel economy data for over 300,000 registered passenger vehicles. We found that, on average, Vermont households would pay an additional $23 per year, with rural households and low-income households facing smaller tax burdens than their urban and high-income counterparts. The impact of a $180 flat fee replacing the Vermont state motor fuels tax was also examined owing to state interest. Findings indicated that a flat fee would result in much larger price fluctuations, with most households paying an additional $47 per year. The disaggregated data approach presented here directly addresses public misconceptions of inequitable cost differences and provides context for public education campaigns to garner mileage-based user fee policy support. Based on our results, there is political ground for further research into the implementation of a mileage-based user fee, including the logistics of an administrative transition to mileage charging and the associated program implementation and technological costs.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"227 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135242169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-09DOI: 10.1177/03611981231207096
Keyong Lin, S.Nurmaya Musa, Hwa Jen Yap
This paper addresses the complex issue of managing medical waste transportation using electric vehicles, with the goal of minimizing both energy consumption and the risks associated with hazardous waste. A multi-objective mixed-integer linear programming model is introduced, incorporating practical factors such as time windows, partial recharge policy, load-dependent discharge, infection risk, and trips to waste disposal facilities. Our proposed method, a combination of the multi-objective evolutionary algorithm using decomposition (MOEA/D) with adaptive large neighborhood search (ALNS) and local search (LS) techniques, is referred to as MOEA/D-ALNS. This method demonstrates superior performance compared with the non-dominated sorting genetic algorithm, NSGA-II, modified MOEA/D and MOEA/D-LNS in benchmark instances with realistic assumptions. Our experimental results revealed an inverse correlation between energy consumption and risk objectives. Sensitivity analyses showed that eliminating time-window constraints results in more energy-efficient and safer routes while maintaining a slightly lower battery energy level can strike an ideal balance between energy consumption, risk, and battery health. This research contributes to the understanding of infectious medical waste management with its consideration of electric vehicles and waste disposal. It lays a solid foundation for future studies aiming to improve the sustainability and efficiency of medical waste routing practices.
{"title":"Adaptive Multi-Objective Algorithm for the Sustainable Electric Vehicle Routing Problem in Medical Waste Management","authors":"Keyong Lin, S.Nurmaya Musa, Hwa Jen Yap","doi":"10.1177/03611981231207096","DOIUrl":"https://doi.org/10.1177/03611981231207096","url":null,"abstract":"This paper addresses the complex issue of managing medical waste transportation using electric vehicles, with the goal of minimizing both energy consumption and the risks associated with hazardous waste. A multi-objective mixed-integer linear programming model is introduced, incorporating practical factors such as time windows, partial recharge policy, load-dependent discharge, infection risk, and trips to waste disposal facilities. Our proposed method, a combination of the multi-objective evolutionary algorithm using decomposition (MOEA/D) with adaptive large neighborhood search (ALNS) and local search (LS) techniques, is referred to as MOEA/D-ALNS. This method demonstrates superior performance compared with the non-dominated sorting genetic algorithm, NSGA-II, modified MOEA/D and MOEA/D-LNS in benchmark instances with realistic assumptions. Our experimental results revealed an inverse correlation between energy consumption and risk objectives. Sensitivity analyses showed that eliminating time-window constraints results in more energy-efficient and safer routes while maintaining a slightly lower battery energy level can strike an ideal balance between energy consumption, risk, and battery health. This research contributes to the understanding of infectious medical waste management with its consideration of electric vehicles and waste disposal. It lays a solid foundation for future studies aiming to improve the sustainability and efficiency of medical waste routing practices.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":" 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135286285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-09DOI: 10.1177/03611981231205880
Hong Zhang, Hongyan Wang, Xijun Zhang, Lei Gong
Accurate traffic flow forecasting is crucial for urban traffic control and route planning. Aiming at the difficulty in capturing dynamic spatio-temporal complexity of traffic flow, a dynamic spatio-temporal transformer (DST-Trans) model capable of modeling dynamic correlation of traffic flow is proposed, which consists of gated temporal convolutional network (GTCN), graph convolutional network (GCN), and spatio-temporal transformer (ST-TF). GTCN and GCN are utilized to capture the temporal and spatial characteristics of traffic flow, respectively. ST-TF includes a temporal transformer using temporal gated convolution and temporal multi-head self-attention to capture short-long term temporal features, and spatial transformer using spatial gated graph convolution and spatial multi-head self-attention to capture local-global dynamic spatial features. In addition, to take full advantage of the dynamic and static associations of road networks, multi-graph models of road relationship graph, similarity graph, and adaptive dynamic graph with SGGC are constructed. Experimental results show that the DST-Trans model in this paper shows good prediction performance in short-term (15 min), medium-term (30 min), and long-term (60 min) prediction, outperforming existing state-of-the-art models by up to approximately 7%.
{"title":"Research on Traffic Flow Forecasting Based on Dynamic Spatial-Temporal Transformer","authors":"Hong Zhang, Hongyan Wang, Xijun Zhang, Lei Gong","doi":"10.1177/03611981231205880","DOIUrl":"https://doi.org/10.1177/03611981231205880","url":null,"abstract":"Accurate traffic flow forecasting is crucial for urban traffic control and route planning. Aiming at the difficulty in capturing dynamic spatio-temporal complexity of traffic flow, a dynamic spatio-temporal transformer (DST-Trans) model capable of modeling dynamic correlation of traffic flow is proposed, which consists of gated temporal convolutional network (GTCN), graph convolutional network (GCN), and spatio-temporal transformer (ST-TF). GTCN and GCN are utilized to capture the temporal and spatial characteristics of traffic flow, respectively. ST-TF includes a temporal transformer using temporal gated convolution and temporal multi-head self-attention to capture short-long term temporal features, and spatial transformer using spatial gated graph convolution and spatial multi-head self-attention to capture local-global dynamic spatial features. In addition, to take full advantage of the dynamic and static associations of road networks, multi-graph models of road relationship graph, similarity graph, and adaptive dynamic graph with SGGC are constructed. Experimental results show that the DST-Trans model in this paper shows good prediction performance in short-term (15 min), medium-term (30 min), and long-term (60 min) prediction, outperforming existing state-of-the-art models by up to approximately 7%.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":" 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135242351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-09DOI: 10.1177/03611981231206175
Jasper Püschel, Lukas Barthelmes, Martin Kagerbauer, Peter Vortisch
Individual travel behavior, such as mode choice, is determined to a distinct degree by the respective portfolio of available mobility tools, such as the number of cars, public transit pass ownership, or a carsharing membership. However, the choice of different mobility tools is interdependent, and individuals weigh alternatives against each other. This process of parallel trade-offs is currently not reflected in typically used sequential logit models of agent-based travel demand models. This study fills this research gap by applying discrete choice and neural network models on a synthetic population to model multiple mobility tool ownership simultaneously. Using data from a national household travel survey, both model types approximated the given target distributions of mobility tools more accurately than the sequence of three corresponding logit models. Owing to its greater flexibility, the tested shallow and deep neural network exhibited higher predictive accuracy than simultaneous discrete choice models. The results indicated that neural networks with only one hidden layer were more robust and easier to formulate and interpret than deep networks with three hidden layers. Finally, the flat neural network was applied to a different synthetic population resulting in equally accurate results.
{"title":"Comparison of Discrete Choice and Machine Learning Models for Simultaneous Modeling of Mobility Tool Ownership in Agent-Based Travel Demand Models","authors":"Jasper Püschel, Lukas Barthelmes, Martin Kagerbauer, Peter Vortisch","doi":"10.1177/03611981231206175","DOIUrl":"https://doi.org/10.1177/03611981231206175","url":null,"abstract":"Individual travel behavior, such as mode choice, is determined to a distinct degree by the respective portfolio of available mobility tools, such as the number of cars, public transit pass ownership, or a carsharing membership. However, the choice of different mobility tools is interdependent, and individuals weigh alternatives against each other. This process of parallel trade-offs is currently not reflected in typically used sequential logit models of agent-based travel demand models. This study fills this research gap by applying discrete choice and neural network models on a synthetic population to model multiple mobility tool ownership simultaneously. Using data from a national household travel survey, both model types approximated the given target distributions of mobility tools more accurately than the sequence of three corresponding logit models. Owing to its greater flexibility, the tested shallow and deep neural network exhibited higher predictive accuracy than simultaneous discrete choice models. The results indicated that neural networks with only one hidden layer were more robust and easier to formulate and interpret than deep networks with three hidden layers. Finally, the flat neural network was applied to a different synthetic population resulting in equally accurate results.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"124 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135243000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-07DOI: 10.1177/03611981231205877
Peicheng Shi, Jianguo Zhang, Bin Hai, Dinghua Zhou
Vehicle behavior decision control plays a crucial role in the development of autonomous driving. However, existing autonomous driving behavior decision control algorithms based on deep reinforcement learning face several challenges, such as low efficiency in updating target network data and a lack of effective balancing between old and new experiences. To address these issues, this paper proposes a dueling double deep Q network (dueling DDQN) algorithm based on a single-step momentum update mechanism. Firstly, a single-step momentum update mechanism is designed to significantly improve the update speed of target network parameters and achieve a balanced weighting of old and new experiences during the parameter update process. Subsequently, the network structures of dueling networks and DDQNs are integrated to enhance the understanding capability of autonomous vehicles concerning their current states. Finally, tests are conducted on the OpenAI Gym simulation platform to validate the effectiveness of the proposed algorithm. The results verified that the dueling DDQN algorithm with single-step momentum updates contributes to improving the convergence speed of autonomous driving car behavior decisions. Compared with the DQN and DDQN algorithms, the proposed algorithm achieved a success rate increase of 6.0 and 8.4 percentage points in the challenging three-lane highway Test Scenario 1, and a success rate increase of 16.7 and 2.9 percentage points in Test Scenario 2, respectively. These findings demonstrate a safer and more efficient performance in autonomous driving decision-making.
{"title":"Research on Dueling Double Deep Q Network Algorithm Based on Single-Step Momentum Update","authors":"Peicheng Shi, Jianguo Zhang, Bin Hai, Dinghua Zhou","doi":"10.1177/03611981231205877","DOIUrl":"https://doi.org/10.1177/03611981231205877","url":null,"abstract":"Vehicle behavior decision control plays a crucial role in the development of autonomous driving. However, existing autonomous driving behavior decision control algorithms based on deep reinforcement learning face several challenges, such as low efficiency in updating target network data and a lack of effective balancing between old and new experiences. To address these issues, this paper proposes a dueling double deep Q network (dueling DDQN) algorithm based on a single-step momentum update mechanism. Firstly, a single-step momentum update mechanism is designed to significantly improve the update speed of target network parameters and achieve a balanced weighting of old and new experiences during the parameter update process. Subsequently, the network structures of dueling networks and DDQNs are integrated to enhance the understanding capability of autonomous vehicles concerning their current states. Finally, tests are conducted on the OpenAI Gym simulation platform to validate the effectiveness of the proposed algorithm. The results verified that the dueling DDQN algorithm with single-step momentum updates contributes to improving the convergence speed of autonomous driving car behavior decisions. Compared with the DQN and DDQN algorithms, the proposed algorithm achieved a success rate increase of 6.0 and 8.4 percentage points in the challenging three-lane highway Test Scenario 1, and a success rate increase of 16.7 and 2.9 percentage points in Test Scenario 2, respectively. These findings demonstrate a safer and more efficient performance in autonomous driving decision-making.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"43 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135480285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-07DOI: 10.1177/03611981231207089
Ilker Boz, Jhony Habbouche, Stacey D. Diefenderfer, Griffin Coffey, Aksel Seitllari, Osman E. Ozbulut
The objective of this study was to explore the use of monotonic loading tests (“monotonic tests”) as screening tools to assess the rutting potential of dense-graded asphalt surface mixtures in Virginia. To that end, three monotonic tests—the indirect tensile at high temperature (IDT-HT) test, the rapid rutting (RR) test, and the Marshall stability and flow (MS) test—identified from the literature, were evaluated using 16 plant-produced asphalt mixtures with “A” and “D” designations. The scope of the work also included performing the multiple stress creep and recovery test on the extracted and recovered binders. The results were applied to assess the monotonic tests and the asphalt pavement analyzer (APA) test relative to each other using several performance metrics. The results were also employed to develop performance threshold criteria for the tests being considered. The results showed that the IDT-HT and RR tests can be used to screen the rutting potential of asphalt mixtures meeting the Virginia Department of Transportation (VDOT) mixture volumetric and gradation requirements for A and D mixtures. The initial performance criteria for the IDT-HT and RR tests were established for these mixtures. Based on the results, the IDT-HT test was found to be the most suitable alternative test to the APA test.
{"title":"Evaluating the Rutting Potential of Asphalt Mixtures with Simple and Practical Tests","authors":"Ilker Boz, Jhony Habbouche, Stacey D. Diefenderfer, Griffin Coffey, Aksel Seitllari, Osman E. Ozbulut","doi":"10.1177/03611981231207089","DOIUrl":"https://doi.org/10.1177/03611981231207089","url":null,"abstract":"The objective of this study was to explore the use of monotonic loading tests (“monotonic tests”) as screening tools to assess the rutting potential of dense-graded asphalt surface mixtures in Virginia. To that end, three monotonic tests—the indirect tensile at high temperature (IDT-HT) test, the rapid rutting (RR) test, and the Marshall stability and flow (MS) test—identified from the literature, were evaluated using 16 plant-produced asphalt mixtures with “A” and “D” designations. The scope of the work also included performing the multiple stress creep and recovery test on the extracted and recovered binders. The results were applied to assess the monotonic tests and the asphalt pavement analyzer (APA) test relative to each other using several performance metrics. The results were also employed to develop performance threshold criteria for the tests being considered. The results showed that the IDT-HT and RR tests can be used to screen the rutting potential of asphalt mixtures meeting the Virginia Department of Transportation (VDOT) mixture volumetric and gradation requirements for A and D mixtures. The initial performance criteria for the IDT-HT and RR tests were established for these mixtures. Based on the results, the IDT-HT test was found to be the most suitable alternative test to the APA test.","PeriodicalId":23279,"journal":{"name":"Transportation Research Record","volume":"286 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135475487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：