Adam Siekmann, V. Sujan, M. Uddin, Yuandong Liu, Fei Xie
The development of a future hydrogen energy economy will require the development of several hydrogen market and industry segments including a hydrogen-based commercial freight transportation ecosystem. For a sustainable freight transportation ecosystem, the supporting fueling infrastructure and the associated vehicle powertrains making use of hydrogen fuel will need to be co-established. This article introduces the OR-AGENT (Optimal Regional Architecture Generation for Electrified National Transportation) tool developed at the Oak Ridge National Laboratory, which has been used to optimize the hydrogen refueling infrastructure requirements on the I-75 corridor for heavy-duty (HD) fuel cell electric commercial vehicles (FCEV). This constraint-based optimization model considers existing fueling locations, regional-specific vehicle fuel economy and weight, vehicle origin and destination (O-D), and vehicle volume by class and infrastructure costs to characterize in-mission refueling requirements for a given freight corridor. The authors applied this framework to determine the ideal public access locations for hydrogen refueling (constrained by existing fueling stations), the minimal viable cost to deploy sufficient hydrogen fuel dispensers, and associated equipment, to accommodate a growing population of hydrogen fuel cell trucks. The framework discussed in this article can be expanded and applied to a larger interstate system, expanded regional corridor, or other transportation network. This article is the third in a series of papers that defined the model development to optimize a national hydrogen refueling infrastructure ecosystem for HD commercial vehicles.
{"title":"Optimizing Hydrogen Fueling Infrastructure Plans on Freight Corridors\u0000 for Heavy-Duty Fuel Cell Electric Vehicles","authors":"Adam Siekmann, V. Sujan, M. Uddin, Yuandong Liu, Fei Xie","doi":"10.4271/13-05-01-0008","DOIUrl":"https://doi.org/10.4271/13-05-01-0008","url":null,"abstract":"The development of a future hydrogen energy economy will require the development\u0000 of several hydrogen market and industry segments including a hydrogen-based\u0000 commercial freight transportation ecosystem. For a sustainable freight\u0000 transportation ecosystem, the supporting fueling infrastructure and the\u0000 associated vehicle powertrains making use of hydrogen fuel will need to be\u0000 co-established. This article introduces the OR-AGENT (Optimal Regional\u0000 Architecture Generation for Electrified National Transportation) tool developed\u0000 at the Oak Ridge National Laboratory, which has been used to optimize the\u0000 hydrogen refueling infrastructure requirements on the I-75 corridor for\u0000 heavy-duty (HD) fuel cell electric commercial vehicles (FCEV). This\u0000 constraint-based optimization model considers existing fueling locations,\u0000 regional-specific vehicle fuel economy and weight, vehicle origin and\u0000 destination (O-D), and vehicle volume by class and infrastructure costs to\u0000 characterize in-mission refueling requirements for a given freight corridor. The\u0000 authors applied this framework to determine the ideal public access locations\u0000 for hydrogen refueling (constrained by existing fueling stations), the minimal\u0000 viable cost to deploy sufficient hydrogen fuel dispensers, and associated\u0000 equipment, to accommodate a growing population of hydrogen fuel cell trucks. The\u0000 framework discussed in this article can be expanded and applied to a larger\u0000 interstate system, expanded regional corridor, or other transportation network.\u0000 This article is the third in a series of papers that defined the model\u0000 development to optimize a national hydrogen refueling infrastructure ecosystem\u0000 for HD commercial vehicles.","PeriodicalId":181105,"journal":{"name":"SAE International Journal of Sustainable Transportation, Energy, Environment, & Policy","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130825105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Wankel engine is an eccentric rotary internal combustion engine known for its simplicity, compactness, reliability, and efficiency. However, issues related to sealing, efficiency, and emissions have hindered its widespread use. Recent advancements in sealing technology, novel designs, material coatings, and alternative fuels have addressed some of these problems, leading to improvements in Wankel engine performance. This study examines these advancements in Wankel engine technology and proposes three potential applications for future automotive use. The first application involves utilizing a Wankel engine with a continuously variable transmission to replace the powertrain in conventional vehicles. The second application suggests replacing the engine in a series-parallel electric-hybrid architecture with a Wankel engine. Lastly, the third application explores using a Wankel engine as a range extender for electric vehicles. To evaluate the benefits in terms of fuel consumption for different drive cycles, each of these applications was modeled using the Future Automotive System Technology Simulator (FASTSim). The models were assessed with both standard Wankel engines and those incorporating recent advancements. The results indicate a potential reduction in fuel consumption when utilizing improved Wankel engine designs compared to traditional piston-based engines. However, it should be noted that these improved Wankel engines still face significant challenges regarding hydrocarbon emissions. Furthermore, the study identified a promising application for Wankel engines as range extenders in electric vehicles, suggesting their potential to enhance the overall efficiency of electric transportation.
{"title":"Analyzing the Usage of Wankel Engine Technology in Future Automotive\u0000 Powertrains","authors":"Vikram Mittal, Rajesh Shah, A. Przyborowski","doi":"10.4271/13-05-02-0009","DOIUrl":"https://doi.org/10.4271/13-05-02-0009","url":null,"abstract":"The Wankel engine is an eccentric rotary internal combustion engine known for its\u0000 simplicity, compactness, reliability, and efficiency. However, issues related to\u0000 sealing, efficiency, and emissions have hindered its widespread use. Recent\u0000 advancements in sealing technology, novel designs, material coatings, and\u0000 alternative fuels have addressed some of these problems, leading to improvements\u0000 in Wankel engine performance. This study examines these advancements in Wankel\u0000 engine technology and proposes three potential applications for future\u0000 automotive use. The first application involves utilizing a Wankel engine with a\u0000 continuously variable transmission to replace the powertrain in conventional\u0000 vehicles. The second application suggests replacing the engine in a\u0000 series-parallel electric-hybrid architecture with a Wankel engine. Lastly, the\u0000 third application explores using a Wankel engine as a range extender for\u0000 electric vehicles. To evaluate the benefits in terms of fuel consumption for\u0000 different drive cycles, each of these applications was modeled using the Future\u0000 Automotive System Technology Simulator (FASTSim). The models were assessed with\u0000 both standard Wankel engines and those incorporating recent advancements. The\u0000 results indicate a potential reduction in fuel consumption when utilizing\u0000 improved Wankel engine designs compared to traditional piston-based engines.\u0000 However, it should be noted that these improved Wankel engines still face\u0000 significant challenges regarding hydrocarbon emissions. Furthermore, the study\u0000 identified a promising application for Wankel engines as range extenders in\u0000 electric vehicles, suggesting their potential to enhance the overall efficiency\u0000 of electric transportation.","PeriodicalId":181105,"journal":{"name":"SAE International Journal of Sustainable Transportation, Energy, Environment, & Policy","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128644793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the sustainable development of the social economy and the continuous maturity of science and technology, urban rail transit has developed rapidly. It solved the problems of urban road load and people’s travel and brought about the problem of rail transit passenger congestion. The image detection algorithm for rail transit congestion is established based on the convolutional neural networks (CNN) structure to realize intelligent video image monitoring. The CNN structure is optimized through the backpropagation (BP) algorithm so that the model can detect and analyze the riding environment through the monitoring camera and extract the relevant motion characteristics of passengers from the image. Furthermore, the crowding situation of the riding environment is analyzed to warn the rail transit operators. In practical application, the detection accuracy of the algorithm reached 91.73%, and the image processing speed met the second-level processing. In the performance test, the proposed algorithm had the lowest mean absolute error (MAE) and mean square error (MSE). In Part B, the MAE and MSE values of the model were 16.3 and 24.9, respectively. The error values were small, so the performance was excellent. The purpose of this study is to reduce the possibility of abnormal crowd accidents at stations and provide new ideas for intelligent management of rail transit.
{"title":"Research on Image Detection Algorithm of Rail Traffic Congestion\u0000 Degree Based on Convolutional Neural Networks","authors":"Xin Lin, Shuang Wu","doi":"10.4271/13-05-01-0007","DOIUrl":"https://doi.org/10.4271/13-05-01-0007","url":null,"abstract":"With the sustainable development of the social economy and the continuous\u0000 maturity of science and technology, urban rail transit has developed rapidly. It\u0000 solved the problems of urban road load and people’s travel and brought about the\u0000 problem of rail transit passenger congestion. The image detection algorithm for\u0000 rail transit congestion is established based on the convolutional neural\u0000 networks (CNN) structure to realize intelligent video image monitoring. The CNN\u0000 structure is optimized through the backpropagation (BP) algorithm so that the\u0000 model can detect and analyze the riding environment through the monitoring\u0000 camera and extract the relevant motion characteristics of passengers from the\u0000 image. Furthermore, the crowding situation of the riding environment is analyzed\u0000 to warn the rail transit operators. In practical application, the detection\u0000 accuracy of the algorithm reached 91.73%, and the image processing speed met the\u0000 second-level processing. In the performance test, the proposed algorithm had the\u0000 lowest mean absolute error (MAE) and mean square error (MSE). In Part B, the MAE\u0000 and MSE values of the model were 16.3 and 24.9, respectively. The error values\u0000 were small, so the performance was excellent. The purpose of this study is to\u0000 reduce the possibility of abnormal crowd accidents at stations and provide new\u0000 ideas for intelligent management of rail transit.","PeriodicalId":181105,"journal":{"name":"SAE International Journal of Sustainable Transportation, Energy, Environment, & Policy","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115064129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To investigate the interplay between driver handling behaviors, this article collects data on vehicle kinematic parameters characterizing driver handling characteristics under natural driving, estimates the probability density curves of the parameters using the kernel density method, and fits the curve equations. On this basis, a percentile correlation analysis was performed between the parameters to obtain the influence relationship between the handling behaviors. The results show that longitudinal maneuvers are frequent and intense in the 0–10 km/h speed range, lateral maneuvers are more intense in the 10–30 km/h speed range, and the interaction between longitudinal and lateral maneuvers is more intense in the acceleration phase. This study enriches the natural driving dataset and illustrates the correlation of driving behavior under natural driving, providing a theoretical and data basis for the development of driver-oriented intelligent driving technologies.
{"title":"Correlation Analysis of Drivers’ Natural Driving Behavior Based on\u0000 Kernel Density Estimation","authors":"Tianjun Sun, Hongyu Hu, Ronggui Cai, Tong Yu, Feng Yu","doi":"10.4271/13-04-02-0012","DOIUrl":"https://doi.org/10.4271/13-04-02-0012","url":null,"abstract":"To investigate the interplay between driver handling behaviors, this article\u0000 collects data on vehicle kinematic parameters characterizing driver handling\u0000 characteristics under natural driving, estimates the probability density curves\u0000 of the parameters using the kernel density method, and fits the curve equations.\u0000 On this basis, a percentile correlation analysis was performed between the\u0000 parameters to obtain the influence relationship between the handling behaviors.\u0000 The results show that longitudinal maneuvers are frequent and intense in the\u0000 0–10 km/h speed range, lateral maneuvers are more intense in the 10–30 km/h\u0000 speed range, and the interaction between longitudinal and lateral maneuvers is\u0000 more intense in the acceleration phase. This study enriches the natural driving\u0000 dataset and illustrates the correlation of driving behavior under natural\u0000 driving, providing a theoretical and data basis for the development of\u0000 driver-oriented intelligent driving technologies.","PeriodicalId":181105,"journal":{"name":"SAE International Journal of Sustainable Transportation, Energy, Environment, & Policy","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115182211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Through connectivity with the electric grid, electric vehicles (EVs) minimize or eliminate the need for fossil fuels. Despite the rapid adoption of EVs in recent times, most government adoption objectives have not been attained. This article aims to comprehend the reasons behind the limited uptake of electric scooters in India and the driving aspects. This research used a grounded theory methodology. Using a snowball sampling technique, we conducted 25 in-depth interviews with EV owners, mainly based in Delhi and Mumbai. As an outcome of the study, four drivers and four impediments to the adoption of EVs have been formulated. The study shows that there are Financial, Technological, Operational, and Psychological drivers and Technological/Infrastructural, Operational, and Psychological impediments to the adoption. The study identifies the key concern areas in the form of categories of drivers and impediments, which can be considered in industrial and public policymaking. This research broadens our understanding of India’s uptake of EVs and provides key insights to organizations and policymakers regarding EV adoption in India.
{"title":"Dynamics of Adopting Electric Vehicles in India: A Grounded Theory Approach","authors":"Ankit Suri, B. Deepthi, Yogesh Sharma","doi":"10.4271/13-05-01-0006","DOIUrl":"https://doi.org/10.4271/13-05-01-0006","url":null,"abstract":"Through connectivity with the electric grid, electric vehicles (EVs) minimize or eliminate the need for fossil fuels. Despite the rapid adoption of EVs in recent times, most government adoption objectives have not been attained. This article aims to comprehend the reasons behind the limited uptake of electric scooters in India and the driving aspects. This research used a grounded theory methodology. Using a snowball sampling technique, we conducted 25 in-depth interviews with EV owners, mainly based in Delhi and Mumbai. As an outcome of the study, four drivers and four impediments to the adoption of EVs have been formulated. The study shows that there are Financial, Technological, Operational, and Psychological drivers and Technological/Infrastructural, Operational, and Psychological impediments to the adoption. The study identifies the key concern areas in the form of categories of drivers and impediments, which can be considered in industrial and public policymaking. This research broadens our understanding of India’s uptake of EVs and provides key insights to organizations and policymakers regarding EV adoption in India.","PeriodicalId":181105,"journal":{"name":"SAE International Journal of Sustainable Transportation, Energy, Environment, & Policy","volume":"155 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116227104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the United States (USA), transportation is the largest single source of greenhouse gas (GHG) emissions, representing 27% of total GHGs emitted in 2020. Eighty-three percent of these came from road transport, and 57% from light-duty vehicles (LDVs). Internal combustion engine (ICE) vehicles, which still form the bulk of the United States (US) fleet, struggle to meet climate change targets. Despite increasingly stringent regulatory mechanisms and technology improvements, only three US states have been able to reduce their transport emissions to the target of below 1990 levels. Fifteen states have made some headway to within 10% of their 1990 baseline. Largely, however, it appears that current strategies are not generating effective results. Current climate-change mitigation measures in road transport tend to be predominantly technological. One of the most popular measures in the USA is fleet electrification, receiving regulatory and fiscal encouragement from 45 US states and federal bills. However, zero-emission vehicles (ZEVs) might not be the climate change panacea for the transport sector. ZEVs are facing adoption issues ranging from affordability, equity, and charging infrastructure to vehicle class availability limitations. Despite increasing sales, US electric vehicle (EV) adoption has been behind the curve with a current market penetration of 4.5%. Outside of ZEVs, emission reduction in the US road transport sector has been sluggish. In road transport, which contributes the bulk of traffic-related air pollution (TRAP), there are clear gaps between policy targets, technology-based expectations, and actual results. For a sector that is struggling to meet climate change targets, broadening its scope of climate change mitigation measures for road transport would be useful. Driver behavior may be an underexplored strategy. Eco-driving is a known strategy and has been attributed to reducing TRAP by up to 50% (through nontechnological means) in various studies in the USA and across the world. If technological eco-driving measures are included, they can improve fuel economy in excess of 100%. But the extent to which it is included in driver education and licensing protocols in US states is unclear. This study, therefore, evaluates eco-driving in state-sponsored non-commercial Driving License Manuals (DLMs). Provisions in state DLMs were assessed based on the intent of the prescribed practices (collision safety, environmental exposure, or both), the extent to which these were included, and the strength of the recommended mechanisms (prescriptive or regulatory). The scores were converted into Grades A–D. The results are revealing. Despite thirty-three US states (66%) with extant climate change commitments, almost the same percentage (62%) of states received a “D” grade and entirely omitted to mention driver influence on fuel consumption and emissions. Only five states (10%) received an “A” grade with substantive eco-driving measures in their DLMs.
{"title":"A Climate-Change Scorecard for United States Non-commercial Driver Education","authors":"Ritu Vasu Primlani, Kajri Misra","doi":"10.4271/13-05-01-0005","DOIUrl":"https://doi.org/10.4271/13-05-01-0005","url":null,"abstract":"In the United States (USA), transportation is the largest single source of greenhouse gas (GHG) emissions, representing 27% of total GHGs emitted in 2020. Eighty-three percent of these came from road transport, and 57% from light-duty vehicles (LDVs). Internal combustion engine (ICE) vehicles, which still form the bulk of the United States (US) fleet, struggle to meet climate change targets. Despite increasingly stringent regulatory mechanisms and technology improvements, only three US states have been able to reduce their transport emissions to the target of below 1990 levels. Fifteen states have made some headway to within 10% of their 1990 baseline. Largely, however, it appears that current strategies are not generating effective results. Current climate-change mitigation measures in road transport tend to be predominantly technological. One of the most popular measures in the USA is fleet electrification, receiving regulatory and fiscal encouragement from 45 US states and federal bills. However, zero-emission vehicles (ZEVs) might not be the climate change panacea for the transport sector. ZEVs are facing adoption issues ranging from affordability, equity, and charging infrastructure to vehicle class availability limitations. Despite increasing sales, US electric vehicle (EV) adoption has been behind the curve with a current market penetration of 4.5%. Outside of ZEVs, emission reduction in the US road transport sector has been sluggish. In road transport, which contributes the bulk of traffic-related air pollution (TRAP), there are clear gaps between policy targets, technology-based expectations, and actual results. For a sector that is struggling to meet climate change targets, broadening its scope of climate change mitigation measures for road transport would be useful. Driver behavior may be an underexplored strategy. Eco-driving is a known strategy and has been attributed to reducing TRAP by up to 50% (through nontechnological means) in various studies in the USA and across the world. If technological eco-driving measures are included, they can improve fuel economy in excess of 100%. But the extent to which it is included in driver education and licensing protocols in US states is unclear. This study, therefore, evaluates eco-driving in state-sponsored non-commercial Driving License Manuals (DLMs). Provisions in state DLMs were assessed based on the intent of the prescribed practices (collision safety, environmental exposure, or both), the extent to which these were included, and the strength of the recommended mechanisms (prescriptive or regulatory). The scores were converted into Grades A–D. The results are revealing. Despite thirty-three US states (66%) with extant climate change commitments, almost the same percentage (62%) of states received a “D” grade and entirely omitted to mention driver influence on fuel consumption and emissions. Only five states (10%) received an “A” grade with substantive eco-driving measures in their DLMs. ","PeriodicalId":181105,"journal":{"name":"SAE International Journal of Sustainable Transportation, Energy, Environment, & Policy","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126472188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ridesharing is a shared vehicle service with the potential to meet the growing travel demand and shortage in transportation infrastructure capacity. Ridesharing services reduce the number of vehicles and reduce traffic congestion and emissions while providing mobility services to the same number of people with no additional transportation infrastructure investment. One of the significant challenges in implementing ridesharing services is matching drivers and riders. Conflicts between matching objectives in satisfying the interests of diverse stakeholders influence ridesharing efficiency in a transportation system. This study investigates the conflicts between two ridesharing matching objectives (i.e., minimization of system-wide trip time [TT] and minimization of system-wide vehicle miles traveled [VMT]) by applying a multi-objective optimization technique. The results indicate that an acceptable performance of a ridesharing system in terms of TT and VMT can be achieved by optimizing a ridesharing system for conflicting objectives. A trade-off analysis was performed to evaluate the compromise needed between two conflicting objectives in satisfying diverse stakeholders’ interest in a ridesharing system.
{"title":"Multi-objective Optimization in a “Specified Driver’s Origin and Destination” Ridesharing System","authors":"Mohammad Nasr Azadani, A. Abolhassani","doi":"10.4271/13-05-01-0003","DOIUrl":"https://doi.org/10.4271/13-05-01-0003","url":null,"abstract":"Ridesharing is a shared vehicle service with the potential to meet the growing travel demand and shortage in transportation infrastructure capacity. Ridesharing services reduce the number of vehicles and reduce traffic congestion and emissions while providing mobility services to the same number of people with no additional transportation infrastructure investment. One of the significant challenges in implementing ridesharing services is matching drivers and riders. Conflicts between matching objectives in satisfying the interests of diverse stakeholders influence ridesharing efficiency in a transportation system. This study investigates the conflicts between two ridesharing matching objectives (i.e., minimization of system-wide trip time [TT] and minimization of system-wide vehicle miles traveled [VMT]) by applying a multi-objective optimization technique. The results indicate that an acceptable performance of a ridesharing system in terms of TT and VMT can be achieved by optimizing a ridesharing system for conflicting objectives. A trade-off analysis was performed to evaluate the compromise needed between two conflicting objectives in satisfying diverse stakeholders’ interest in a ridesharing system.","PeriodicalId":181105,"journal":{"name":"SAE International Journal of Sustainable Transportation, Energy, Environment, & Policy","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114460223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The two-wheel system design is widely used in various mobile tools, such as remote-control vehicles and robots, due to its simplicity and stability. However, the specific wheel and body models in the real world can be complex, and the control accuracy of existing algorithms may not meet practical requirements. To address this issue, we propose a double inverted pendulum on mobile device (DIPM) model to improve control performances and reduce calculations. The model is based on the kinetic and potential energy of the DIPM system, known as the Euler-Lagrange equation, and is composed of three second-order nonlinear differential equations derived by specifying Lagrange. We also propose a stable feedback control method for mobile device drive systems. Our experiments compare several mainstream reinforcement learning (RL) methods, including linear quadratic regulator (LQR) and iterative linear quadratic regulator (ILQR), as well as Q-learning, SARSA, DQN (Deep Q Network), and AC. The simulation results demonstrate that the DQN and AC methods are superior to ILQR in our designed nonlinear system. In all aspects of the test, the performance of Q-learning and SARSA is comparable to that of ILQR, with some slight improvements. However, ILQR shows its advantages at 10 deg and 20 deg. In the small deflection (between 5 and 10 deg), the DQN and AC methods perform 2% better than the traditional ILQR, and in the large deflection (10–30 deg), the DQN and AC methods perform 15% better than the traditional ILQR. Overall, RL not only has the advantages of strong versatility, wide application range, and parameter customization but also greatly reduces the difficulty of control system design and human investment, making it a promising field for future research.
{"title":"A New Optimal Design of Stable Feedback Control of Two-Wheel System Based on Reinforcement Learning","authors":"Zhenghong Yu, Xuebin Zhu","doi":"10.4271/13-05-01-0004","DOIUrl":"https://doi.org/10.4271/13-05-01-0004","url":null,"abstract":"The two-wheel system design is widely used in various mobile tools, such as remote-control vehicles and robots, due to its simplicity and stability. However, the specific wheel and body models in the real world can be complex, and the control accuracy of existing algorithms may not meet practical requirements. To address this issue, we propose a double inverted pendulum on mobile device (DIPM) model to improve control performances and reduce calculations. The model is based on the kinetic and potential energy of the DIPM system, known as the Euler-Lagrange equation, and is composed of three second-order nonlinear differential equations derived by specifying Lagrange. We also propose a stable feedback control method for mobile device drive systems. Our experiments compare several mainstream reinforcement learning (RL) methods, including linear quadratic regulator (LQR) and iterative linear quadratic regulator (ILQR), as well as Q-learning, SARSA, DQN (Deep Q Network), and AC. The simulation results demonstrate that the DQN and AC methods are superior to ILQR in our designed nonlinear system. In all aspects of the test, the performance of Q-learning and SARSA is comparable to that of ILQR, with some slight improvements. However, ILQR shows its advantages at 10 deg and 20 deg. In the small deflection (between 5 and 10 deg), the DQN and AC methods perform 2% better than the traditional ILQR, and in the large deflection (10–30 deg), the DQN and AC methods perform 15% better than the traditional ILQR. Overall, RL not only has the advantages of strong versatility, wide application range, and parameter customization but also greatly reduces the difficulty of control system design and human investment, making it a promising field for future research.","PeriodicalId":181105,"journal":{"name":"SAE International Journal of Sustainable Transportation, Energy, Environment, & Policy","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128634454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the rapid development of the Internet and intelligent control technology, intelligent transportation has become a research hotspot in building a smart city. Under the background of intelligent transportation, it is particularly important to effectively evaluate the rail transit as the framework of urban public transport in this study, and fuzzy mechanism is introduced to optimize the support vector machine (SVM), and on this basis, analytic hierarchy process (AHP) and SVM are combined to improve the classification accuracy and improve the rail transit operation safety evaluation index system. The experimental results show that the classification accuracy of the fuzzy SVM combined with AHP is above 85% on all the datasets, and it can effectively eliminate the less-relevant indicators. In the actual evaluation of Shanghai Rail Transit safety, the prediction accuracy exceeded 80% and the highest reached 94.51%. Among them, the accuracy of management level and infrastructure were increased by 24.1% and 18.34%, respectively, indicating that this method can effectively screen the evaluation indicators. In the evaluation of Beijing Rail Transit, the accuracy rate of the combined algorithm reaches 95.67%, with high classification accuracy, which provides a reference direction for the establishment of the rail transit operation safety evaluation system.
{"title":"Research on the Evaluation System of Urban Rail Transit Operation Safety in the Context of Intelligent Transportation","authors":"Xiuhong Shi, Kaixin Wu","doi":"10.4271/13-05-01-0001","DOIUrl":"https://doi.org/10.4271/13-05-01-0001","url":null,"abstract":"With the rapid development of the Internet and intelligent control technology, intelligent transportation has become a research hotspot in building a smart city. Under the background of intelligent transportation, it is particularly important to effectively evaluate the rail transit as the framework of urban public transport in this study, and fuzzy mechanism is introduced to optimize the support vector machine (SVM), and on this basis, analytic hierarchy process (AHP) and SVM are combined to improve the classification accuracy and improve the rail transit operation safety evaluation index system. The experimental results show that the classification accuracy of the fuzzy SVM combined with AHP is above 85% on all the datasets, and it can effectively eliminate the less-relevant indicators. In the actual evaluation of Shanghai Rail Transit safety, the prediction accuracy exceeded 80% and the highest reached 94.51%. Among them, the accuracy of management level and infrastructure were increased by 24.1% and 18.34%, respectively, indicating that this method can effectively screen the evaluation indicators. In the evaluation of Beijing Rail Transit, the accuracy rate of the combined algorithm reaches 95.67%, with high classification accuracy, which provides a reference direction for the establishment of the rail transit operation safety evaluation system.","PeriodicalId":181105,"journal":{"name":"SAE International Journal of Sustainable Transportation, Energy, Environment, & Policy","volume":"93 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125056111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hong Ji, Jian Meng, Zongyu Li, Baoli Wang, Fan-Zhi Meng, Wenke Xu
The demand for fossil fuels can be reduced and environmental harm can be minimized by producing biodiesel from used cooking oil. This article was focused on investigating the combustion characteristics and regulated and unregulated emissions of a common-rail diesel engine fueled with different mixed concentrations of biodiesel and diesel fuel, including pure diesel fuel (B0), B10 (diesel containing 10%vol of biodiesel), B20, and B30. Experiments were conducted with three engine loads, corresponding to brake mean effective pressures (BMEP) of 0.289 MPa, 0.578 MPa, and 0.867 MPa at a constant speed of 1540 rpm. At medium and high loads, the waste cooking oil biodiesel (WCOB) increased in-cylinder pressure, advanced both the peak heat release rate and heat release center (CA50), shrunk the ignition delay (ID), and extended combustion duration (CD). The high viscosity of B30 blends under low load worsened the spray and led to poor combustion. Under high-load conditions, carbon dioxide (CO2) and nitrogen oxides (NOx) emissions increased by 14.3% and 3.1%, while carbon monoxide (CO), soot, and total hydrocarbon (THC) emissions decreased by 13.3%, 31.4%, and 30.37%, respectively, for the B30 blend compared to diesel. The emission trends for nitrogen dioxide (NO2), formaldehyde (HCHO), methane (CH4), ammonia (NH3), ethylene (C2H4), and formic acid (HCOOH) were consistent with increasing volume ratios of WCOB under the three loads. And they had the lowest emissions at 75% load for B30, with reductions of 70.5%, 66.7%, 18.4%, 78.8%, 13.2%, and 84.6%, respectively, compared to diesel. Acetaldehyde (MECHO) emissions increased with increasing WCOB blending volume ratio at 25% load condition and were highest at the B30 blend. The above results show that the B30 blend is the most effective in reducing unregulated emissions under all three load conditions, especially at medium and high loads.
{"title":"Experimental Study on Combustion Characteristics and Regulated and\u0000 Unregulated Emissions of a Common-Rail Diesel Engine Fueled with Waste Cooking\u0000 Oil Biodiesel","authors":"Hong Ji, Jian Meng, Zongyu Li, Baoli Wang, Fan-Zhi Meng, Wenke Xu","doi":"10.4271/13-04-02-0013","DOIUrl":"https://doi.org/10.4271/13-04-02-0013","url":null,"abstract":"The demand for fossil fuels can be reduced and environmental harm can be\u0000 minimized by producing biodiesel from used cooking oil. This article was focused\u0000 on investigating the combustion characteristics and regulated and unregulated\u0000 emissions of a common-rail diesel engine fueled with different mixed\u0000 concentrations of biodiesel and diesel fuel, including pure diesel fuel (B0),\u0000 B10 (diesel containing 10%vol of biodiesel), B20, and B30. Experiments were\u0000 conducted with three engine loads, corresponding to brake mean effective\u0000 pressures (BMEP) of 0.289 MPa, 0.578 MPa, and 0.867 MPa at a constant speed of\u0000 1540 rpm. At medium and high loads, the waste cooking oil biodiesel (WCOB)\u0000 increased in-cylinder pressure, advanced both the peak heat release rate and\u0000 heat release center (CA50), shrunk the ignition delay (ID), and extended\u0000 combustion duration (CD). The high viscosity of B30 blends under low load\u0000 worsened the spray and led to poor combustion. Under high-load conditions,\u0000 carbon dioxide (CO2) and nitrogen oxides (NOx) emissions\u0000 increased by 14.3% and 3.1%, while carbon monoxide (CO), soot, and total\u0000 hydrocarbon (THC) emissions decreased by 13.3%, 31.4%, and 30.37%, respectively,\u0000 for the B30 blend compared to diesel. The emission trends for nitrogen dioxide\u0000 (NO2), formaldehyde (HCHO), methane (CH4), ammonia\u0000 (NH3), ethylene (C2H4), and\u0000 formic acid (HCOOH) were consistent with increasing volume ratios of WCOB under\u0000 the three loads. And they had the lowest emissions at 75% load for B30, with\u0000 reductions of 70.5%, 66.7%, 18.4%, 78.8%, 13.2%, and 84.6%, respectively,\u0000 compared to diesel. Acetaldehyde (MECHO) emissions increased with increasing\u0000 WCOB blending volume ratio at 25% load condition and were highest at the B30\u0000 blend. The above results show that the B30 blend is the most effective in\u0000 reducing unregulated emissions under all three load conditions, especially at\u0000 medium and high loads.","PeriodicalId":181105,"journal":{"name":"SAE International Journal of Sustainable Transportation, Energy, Environment, & Policy","volume":"26 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120868376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：