As an important task of multi-floor localization, floor detection has elicited great attention. Wireless infrastructures like Wi-Fi and Bluetooth low-energy play important roles in floor detection. However, most floor detection research studies tend to focus on data modeling but pay little attention to the data collection system, which is the basis of wireless infrastructure-based floor detection. In fact, the floor detection task can be greatly simplified with proper data collection system design. In this paper, a floor detection solution is developed in a multi-floor life science automation lab. A data collection system consisting of BLE beacons, receiver node, and IoT cloud is provided. The features of the BLE beacon under different settings are evaluated in detail. A mean filter is designed to deal with the fluctuation of the RSSI data. A simple floor detection method without a training process was implemented and evaluated in more than 100 floor detection tests. The time delay and floor detection accuracy under different settings are discussed. Finally, floor detection is evaluated on the H20 multi-floor transportation robot. Two sensor nodes are installed on the robot at different heights. The floor detection performance with different installation heights is discussed. The experimental results indicate that the proposed floor detection method provides floor detection accuracy of 0.9877 to 1 with a time delay of 5 s.
{"title":"BLE Beacon-based floor detection for mobile robots in a multi-floor automation Laboratory","authors":"Haiping Wu, Hui Liu, T. Roddelkopf, K. Thurow","doi":"10.1093/tse/tdad024","DOIUrl":"https://doi.org/10.1093/tse/tdad024","url":null,"abstract":"\u0000 As an important task of multi-floor localization, floor detection has elicited great attention. Wireless infrastructures like Wi-Fi and Bluetooth low-energy play important roles in floor detection. However, most floor detection research studies tend to focus on data modeling but pay little attention to the data collection system, which is the basis of wireless infrastructure-based floor detection. In fact, the floor detection task can be greatly simplified with proper data collection system design. In this paper, a floor detection solution is developed in a multi-floor life science automation lab. A data collection system consisting of BLE beacons, receiver node, and IoT cloud is provided. The features of the BLE beacon under different settings are evaluated in detail. A mean filter is designed to deal with the fluctuation of the RSSI data. A simple floor detection method without a training process was implemented and evaluated in more than 100 floor detection tests. The time delay and floor detection accuracy under different settings are discussed. Finally, floor detection is evaluated on the H20 multi-floor transportation robot. Two sensor nodes are installed on the robot at different heights. The floor detection performance with different installation heights is discussed. The experimental results indicate that the proposed floor detection method provides floor detection accuracy of 0.9877 to 1 with a time delay of 5 s.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2023-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42728982","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}
The increasing use of mobile robots in laboratory settings has led to a higher degree of laboratory automation. However, when mobile robots move in laboratory environments, mechanical errors, environmental disturbances, and signal interruptions are inevitable. This can compromise the accuracy of the robot's localization, which is crucial for the safety of staff, robots, and the laboratory. A novel time-series predicting model based on the data processing method is proposed to handle the unexpected localization measurement of mobile robots in laboratory environments. The proposed model serves as an auxiliary localization system that can accurately correct unexpected localization errors by relying solely on the historical data of mobile robots. The experimental results demonstrate the effectiveness of this proposed method.
{"title":"Correcting of Unexpected Localization Measurement for Indoor Automatic Mobile Robot Transportation Based on neural network","authors":"Jiahao Huang, S. Junginger, Hui Liu, K. Thurow","doi":"10.1093/tse/tdad019","DOIUrl":"https://doi.org/10.1093/tse/tdad019","url":null,"abstract":"\u0000 The increasing use of mobile robots in laboratory settings has led to a higher degree of laboratory automation. However, when mobile robots move in laboratory environments, mechanical errors, environmental disturbances, and signal interruptions are inevitable. This can compromise the accuracy of the robot's localization, which is crucial for the safety of staff, robots, and the laboratory. A novel time-series predicting model based on the data processing method is proposed to handle the unexpected localization measurement of mobile robots in laboratory environments. The proposed model serves as an auxiliary localization system that can accurately correct unexpected localization errors by relying solely on the historical data of mobile robots. The experimental results demonstrate the effectiveness of this proposed method.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2023-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44357201","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}
Tunnels on freeways, as one of the critical bottlenecks, frequently cause severe congestion and passenger delay. To solve the tunnel bottleneck problem, most of the existing research can be divided into two types. One is to adopt Variable Speed Limits (VSL) to regulate a predetermined speed for vehicles to get through a bottleneck smoothly. The other is to adopt High-Occupancy Vehicle (HOV) lane management. In HOV lane management strategies, all traffic is divided into HOVs and Low-occupancy Vehicles (LOV). HOVs are vehicles with a driver and one or more passengers. LOVs are vehicles just with a driver. This kind of research can grant priority to HOVs by providing a dedicated HOV lane. However, the existing research cannot both mitigate congestion and maximize passenger-oriented benefits. To address the research gap, this paper leverages Connected and Automated Vehicle (CAV) technologies on intelligent freeways and develops a tunnel bottleneck management strategy with a Dynamic HOV Lane (DHL). The strategy bears the following features: 1) enable tunnel bottleneck management at a microscopic level; 2) maximize passenger-oriented benefits; 3) grant priority to HOVs even when the HOV lane is open to LOVs; 4) allocate right-of-way segments for HOVs and LOVs in real time; 5) perform well in a mixed traffic environment. The proposed strategy is evaluated through comparison against the non-control baseline and a VSL strategy. Sensitivity analysis is conducted under different congestion levels and penetration rates. The results demonstrate that the proposed strategy outperforms in terms of passenger-oriented delay reduction and HOVs'priority level improvement.
{"title":"Tunnel bottleneck management with high-occupancy vehicles priority on intelligent freeways","authors":"Jinyong Gao, Juncheng Zeng, Xinyuan Wang, Cheng Zhou, Hailin Zhang, Jintao Lai","doi":"10.1093/tse/tdad022","DOIUrl":"https://doi.org/10.1093/tse/tdad022","url":null,"abstract":"\u0000 Tunnels on freeways, as one of the critical bottlenecks, frequently cause severe congestion and passenger delay. To solve the tunnel bottleneck problem, most of the existing research can be divided into two types. One is to adopt Variable Speed Limits (VSL) to regulate a predetermined speed for vehicles to get through a bottleneck smoothly. The other is to adopt High-Occupancy Vehicle (HOV) lane management. In HOV lane management strategies, all traffic is divided into HOVs and Low-occupancy Vehicles (LOV). HOVs are vehicles with a driver and one or more passengers. LOVs are vehicles just with a driver. This kind of research can grant priority to HOVs by providing a dedicated HOV lane. However, the existing research cannot both mitigate congestion and maximize passenger-oriented benefits. To address the research gap, this paper leverages Connected and Automated Vehicle (CAV) technologies on intelligent freeways and develops a tunnel bottleneck management strategy with a Dynamic HOV Lane (DHL). The strategy bears the following features: 1) enable tunnel bottleneck management at a microscopic level; 2) maximize passenger-oriented benefits; 3) grant priority to HOVs even when the HOV lane is open to LOVs; 4) allocate right-of-way segments for HOVs and LOVs in real time; 5) perform well in a mixed traffic environment. The proposed strategy is evaluated through comparison against the non-control baseline and a VSL strategy. Sensitivity analysis is conducted under different congestion levels and penetration rates. The results demonstrate that the proposed strategy outperforms in terms of passenger-oriented delay reduction and HOVs'priority level improvement.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2023-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42424135","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}
Remaining useful life (RUL) prediction for bearing is a significant part of the maintenance of urban rail transit trains. Bearing RUL is closely linked to the reliability and safety of train running, but the current prediction accuracy is difficult to meet the requirements of high reliability operation. Aiming at the problem, a prediction model based on improved long short-term memory(ILSTM) network is proposed. Firstly, the variational mode decomposition is used to process the signal, and the intrinsic mode function with stronger representation ability is determined according to energy entropy, and the degradation feature data is constructed combined with the time domain characteristics. Then, to improve learning ability, rectified linear unit (ReLU) is applied to activate a fully connected layer lying after LSTM, the hidden state outputs of the layer are weighted by attention mechanism. Harris hawks optimization algorithm is introduced to adaptively set the hyperparameters to improve the performance of LSTM. Finally, the ILSTM is applied to predict bearing RUL. Through experimental cases, the better performance in bearing RUL prediction and the effectiveness of each improving measures of the model are validated, and its superiority of hyperparameters setting is demonstrated.
{"title":"Remaining useful life prediction for train bearing based on ILSTM network with adaptive hyperparameter optimization","authors":"Deqiang He, Jingren Yan, Zhenzhen Jin, Xueyan Zou, S. Shan, Zaiyu Xiang, Jian Miao","doi":"10.1093/tse/tdad021","DOIUrl":"https://doi.org/10.1093/tse/tdad021","url":null,"abstract":"\u0000 Remaining useful life (RUL) prediction for bearing is a significant part of the maintenance of urban rail transit trains. Bearing RUL is closely linked to the reliability and safety of train running, but the current prediction accuracy is difficult to meet the requirements of high reliability operation. Aiming at the problem, a prediction model based on improved long short-term memory(ILSTM) network is proposed. Firstly, the variational mode decomposition is used to process the signal, and the intrinsic mode function with stronger representation ability is determined according to energy entropy, and the degradation feature data is constructed combined with the time domain characteristics. Then, to improve learning ability, rectified linear unit (ReLU) is applied to activate a fully connected layer lying after LSTM, the hidden state outputs of the layer are weighted by attention mechanism. Harris hawks optimization algorithm is introduced to adaptively set the hyperparameters to improve the performance of LSTM. Finally, the ILSTM is applied to predict bearing RUL. Through experimental cases, the better performance in bearing RUL prediction and the effectiveness of each improving measures of the model are validated, and its superiority of hyperparameters setting is demonstrated.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2023-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"61099120","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}
Yang Zeyun, Xu Gang, Wu Fan, Zhang Lei, Du Jian, D. Vainchtein
The purpose of this study is to establish the correlation between the boundary layer over the subgrade and the aerodynamic loads acting on the train model in conventional wind tunnel tests. Firstly, flow characteristics around the subgrade with different leading-edge angles (15◦, 30◦, and 45◦) are investigated through PIV experimental test method. Then, wind tunnel tests of the aerodynamic performance of a high-speed train are carried out. The results are compared with previous experimental data obtained by moving model tests. Results show that, due to the presence of boundary layer, the pressure acting on the lower part of the train head decreases, while on other location is not significantly affected. This is the reason for the reduction of the aerodynamic drag and lift on the train. In addition, the reduction effects become more obviously when the thickness of boundary layer increasing. The experimental results obtained could serve as a calibration of aerodynamic forces for wind tunnel tests on high-speed trains.
{"title":"Influence of leading-edge angle of subgrade on aerodynamic loads of high-speed train in wind tunnel","authors":"Yang Zeyun, Xu Gang, Wu Fan, Zhang Lei, Du Jian, D. Vainchtein","doi":"10.1093/tse/tdad020","DOIUrl":"https://doi.org/10.1093/tse/tdad020","url":null,"abstract":"\u0000 The purpose of this study is to establish the correlation between the boundary layer over the subgrade and the aerodynamic loads acting on the train model in conventional wind tunnel tests. Firstly, flow characteristics around the subgrade with different leading-edge angles (15◦, 30◦, and 45◦) are investigated through PIV experimental test method. Then, wind tunnel tests of the aerodynamic performance of a high-speed train are carried out. The results are compared with previous experimental data obtained by moving model tests. Results show that, due to the presence of boundary layer, the pressure acting on the lower part of the train head decreases, while on other location is not significantly affected. This is the reason for the reduction of the aerodynamic drag and lift on the train. In addition, the reduction effects become more obviously when the thickness of boundary layer increasing. The experimental results obtained could serve as a calibration of aerodynamic forces for wind tunnel tests on high-speed trains.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2023-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43989656","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}
Chengyong Liu, Shijie Li, Shuzhe Chen, Qifan Chen, Kang Liu
Due to the flammability and explosive nature of liquefied natural gas (LNG), an extremely strict process is followed for the transportation of LNG carriers in China. Particularly, no LNG carriers are operating in inland rivers within the country. Therefore, to ensure the future navigation safety of LNG carriers entering the Yangtze River, the risk sources of LNG carriers' navigation safety must be identified and evaluated. Based on the Delphi and expert experience method, this paper analyzes and discusses the navigation risk factors of LNG carriers in the lower reaches of the Yangtze River from four aspects (human, ship, environment, and management), and identifies 12 risk indicators affecting the navigation of LNG carriers, and establishes a risk evaluation index system. Further, an entropy weight fuzzy model is utilized to reduce the influence of subjective judgment on the index weight as well as to conduct a segmented and overall evaluation of LNG navigation risks in the Baimaosha Channel. Finally, the cloud model is applied to validate the consistent feasibility of the entropy weight fuzzy model. The research results indicate that the method provides effective technical support for further study on the navigation security of LNG carriers in inland rivers.
{"title":"Research on the navigational risk of liquefied natural gas carriers in an inland river based on entropy: a cloud evaluation model","authors":"Chengyong Liu, Shijie Li, Shuzhe Chen, Qifan Chen, Kang Liu","doi":"10.1093/tse/tdad018","DOIUrl":"https://doi.org/10.1093/tse/tdad018","url":null,"abstract":"\u0000 Due to the flammability and explosive nature of liquefied natural gas (LNG), an extremely strict process is followed for the transportation of LNG carriers in China. Particularly, no LNG carriers are operating in inland rivers within the country. Therefore, to ensure the future navigation safety of LNG carriers entering the Yangtze River, the risk sources of LNG carriers' navigation safety must be identified and evaluated. Based on the Delphi and expert experience method, this paper analyzes and discusses the navigation risk factors of LNG carriers in the lower reaches of the Yangtze River from four aspects (human, ship, environment, and management), and identifies 12 risk indicators affecting the navigation of LNG carriers, and establishes a risk evaluation index system. Further, an entropy weight fuzzy model is utilized to reduce the influence of subjective judgment on the index weight as well as to conduct a segmented and overall evaluation of LNG navigation risks in the Baimaosha Channel. Finally, the cloud model is applied to validate the consistent feasibility of the entropy weight fuzzy model. The research results indicate that the method provides effective technical support for further study on the navigation security of LNG carriers in inland rivers.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48077048","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}
Zhuo Yan, Wang Tiantian, Shen Ruiyuan, Xie Jingsong, Yang Jingsong, Zhang Guoqin, Tian Hongqi, Liang Xifeng
With the improvement of the running speed of China's high-speed trains, the demands for running status monitoring and security assurance of High-speed Electric Multiple Units(EMU) have increased significantly. However, the current safety monitoring systems are independent, which is not conducive to the comprehensive monitoring and information sharing of the whole vehicle. The temperature monitoring of running gear is insensitive to early failures. How to develop a train operation safety monitoring system with strong engineering implementation and high integration is a key problem to be solved. For the monitoring of running stationarity, frame stability and running gear health of China's high-speed trains, an integrated safety monitoring system framework is designed, and the logic and algorithm for diagnosis of stationarity, stability and health states of rotating parts are constructed. A monitoring software which fused the temperature, high and low frequency vibration data is developed, and the design and installation of the vibration temperature composite sensors are completed. The research results have realized the integration and comprehensive processing of multiple monitoring systems, completed the improvement from single component and single vehicle level safety monitoring to multiple systems, vehicle level and interactive monitoring. In the process of real vehicle application, the developed monitoring system acquires the vehicle operation status data in real time and accurately. The constructed diagnosis algorithm and logic evaluate the vehicle operation status timely and accurately, and avoid the evolution from fault to accident. The research results show that the integrated safety monitoring system can provide technical support for train operation safety.
{"title":"Development and engineering application of integrated safety monitoring system for China's high-speed trains","authors":"Zhuo Yan, Wang Tiantian, Shen Ruiyuan, Xie Jingsong, Yang Jingsong, Zhang Guoqin, Tian Hongqi, Liang Xifeng","doi":"10.1093/tse/tdad017","DOIUrl":"https://doi.org/10.1093/tse/tdad017","url":null,"abstract":"\u0000 With the improvement of the running speed of China's high-speed trains, the demands for running status monitoring and security assurance of High-speed Electric Multiple Units(EMU) have increased significantly. However, the current safety monitoring systems are independent, which is not conducive to the comprehensive monitoring and information sharing of the whole vehicle. The temperature monitoring of running gear is insensitive to early failures. How to develop a train operation safety monitoring system with strong engineering implementation and high integration is a key problem to be solved. For the monitoring of running stationarity, frame stability and running gear health of China's high-speed trains, an integrated safety monitoring system framework is designed, and the logic and algorithm for diagnosis of stationarity, stability and health states of rotating parts are constructed. A monitoring software which fused the temperature, high and low frequency vibration data is developed, and the design and installation of the vibration temperature composite sensors are completed. The research results have realized the integration and comprehensive processing of multiple monitoring systems, completed the improvement from single component and single vehicle level safety monitoring to multiple systems, vehicle level and interactive monitoring. In the process of real vehicle application, the developed monitoring system acquires the vehicle operation status data in real time and accurately. The constructed diagnosis algorithm and logic evaluate the vehicle operation status timely and accurately, and avoid the evolution from fault to accident. The research results show that the integrated safety monitoring system can provide technical support for train operation safety.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2023-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43677238","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}
In order to improve the emergency management capability of the urban rail transit system and reduce accidents during metro operation, an emergency management capability evaluation method combining theAnalytic Hierarchy Process (AHP) and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) is proposed. Based on the PPRR (Prevention Preparation Response Recovery) model, the factors influencing the emergency management capability of the urban rail transit system are summarized from the perspective of ‘human, machine, environment, and management’. Then, an emergency management capability evaluation index system containing 20 secondary indicators is constructed in four stages: emergency prevention, emergency preparation, emergency response, and emergency recovery. The weights of indicators are calculated using the AHP method, and the closeness of each indicator to the optimal solution is analyzed with the TOPSIS method. Finally, take the Beijing metro line 13 as an example to investigate the level of emergency management capability of urban rail transit. The results show that the emergency management capability of Beijing urban rail transit system is ‘well’, among which hazard prevention measures (0.31) and emergency response team (0.34) have a greater weight on the emergency management capability of rail transit. The model can more accurately assess the emergency management capability of urban rail transit and provide a basis for emergency event management.
{"title":"Emergency Management Capacity assessment for Urban Rail transit——An example of Beijing Metro Line 13","authors":"J. Liu, Yun-song Qi, W. Wang","doi":"10.1093/tse/tdad015","DOIUrl":"https://doi.org/10.1093/tse/tdad015","url":null,"abstract":"\u0000 In order to improve the emergency management capability of the urban rail transit system and reduce accidents during metro operation, an emergency management capability evaluation method combining theAnalytic Hierarchy Process (AHP) and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) is proposed. Based on the PPRR (Prevention Preparation Response Recovery) model, the factors influencing the emergency management capability of the urban rail transit system are summarized from the perspective of ‘human, machine, environment, and management’. Then, an emergency management capability evaluation index system containing 20 secondary indicators is constructed in four stages: emergency prevention, emergency preparation, emergency response, and emergency recovery. The weights of indicators are calculated using the AHP method, and the closeness of each indicator to the optimal solution is analyzed with the TOPSIS method. Finally, take the Beijing metro line 13 as an example to investigate the level of emergency management capability of urban rail transit. The results show that the emergency management capability of Beijing urban rail transit system is ‘well’, among which hazard prevention measures (0.31) and emergency response team (0.34) have a greater weight on the emergency management capability of rail transit. The model can more accurately assess the emergency management capability of urban rail transit and provide a basis for emergency event management.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2023-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42556396","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}
Xinyuan Liu, Jinjun Tang, Chen Yuan, Fan Gao, Xizhi Ding
Understanding the characteristics of time and distance gaps between the primary and second crashes is crucial for preventing secondary crash occurrences and improving road safety. Although previous studies have tried to analyze the variation of gaps, there is limited evidence in quantifying the relationships between different gaps and various influential factors. This study proposed a two-layer Stacking framework to discuss the time and distance gaps. Specifically, the framework took Random Forests, Gradient Boosting Decision Tree, and eXtreme Gradient Boosting as the base classifiers in the first layer and applied Logistic Regression as a combiner in the second layer. On this basis, the Local Interpretable Model-agnostic Explanations (LIME) technology was used to interpret the output of the Stacking model from both local and global perspectives. Through secondary crash identification and feature selection, 346 secondary crashes and 22 crash-related factors were collected from California interstate freeways. The results showed that the Stacking model outperformed base models evaluated by accuracy, precision, and recall indicators. The explanations based on LIME suggest that collision type, distance, speed, and volume are the critical features that affect the time and distance gaps. Higher volume can prolong queue length and increase the distance gap from the secondary to primary crashes. And collision types, peak periods, workday, truck involved, and tow away likely induce a long-distance gap. Conversely, there is a shorter distance gap when secondary roads run in the same direction and are close to the primary roads. Lower speed is a significant factor resulting in a long-time gap, while the higher speed is correlated with a short-time gap. These results are expected to provide insights into how contributory features affect the time and distance gaps and help decision-makers develop accurate decisions to prevent secondary crashes.
{"title":"Examining the characteristics between time and distance gaps of secondary crashes","authors":"Xinyuan Liu, Jinjun Tang, Chen Yuan, Fan Gao, Xizhi Ding","doi":"10.1093/tse/tdad014","DOIUrl":"https://doi.org/10.1093/tse/tdad014","url":null,"abstract":"\u0000 Understanding the characteristics of time and distance gaps between the primary and second crashes is crucial for preventing secondary crash occurrences and improving road safety. Although previous studies have tried to analyze the variation of gaps, there is limited evidence in quantifying the relationships between different gaps and various influential factors. This study proposed a two-layer Stacking framework to discuss the time and distance gaps. Specifically, the framework took Random Forests, Gradient Boosting Decision Tree, and eXtreme Gradient Boosting as the base classifiers in the first layer and applied Logistic Regression as a combiner in the second layer. On this basis, the Local Interpretable Model-agnostic Explanations (LIME) technology was used to interpret the output of the Stacking model from both local and global perspectives. Through secondary crash identification and feature selection, 346 secondary crashes and 22 crash-related factors were collected from California interstate freeways. The results showed that the Stacking model outperformed base models evaluated by accuracy, precision, and recall indicators. The explanations based on LIME suggest that collision type, distance, speed, and volume are the critical features that affect the time and distance gaps. Higher volume can prolong queue length and increase the distance gap from the secondary to primary crashes. And collision types, peak periods, workday, truck involved, and tow away likely induce a long-distance gap. Conversely, there is a shorter distance gap when secondary roads run in the same direction and are close to the primary roads. Lower speed is a significant factor resulting in a long-time gap, while the higher speed is correlated with a short-time gap. These results are expected to provide insights into how contributory features affect the time and distance gaps and help decision-makers develop accurate decisions to prevent secondary crashes.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41849294","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}
In this paper, an adaptive composite anti-disturbance control of heavy haul trains (HHTs) is proposed. First, the mechanical principle and characteristics of couplers are analyzed and the longitudinal multi-particles nonlinear dynamic model of HHTs is established, which can satisfy that the forces of vehicles in different positions are different. Subsequently, a radial basis function network (RBFNN) is employed to approximate the uncertainties of HHTs, and a nonlinear disturbance observer (NDO) is constructed to estimate the approximation error and external disturbances. To indicate and improve the approximation accuracy, a serial-parallel identification model of HHTs is constructed to generate a prediction error, and an adaptive composite anti-disturbance control scheme is developed, where the prediction error and tracking error are employed to update RBFNN weights and an auxiliary variable of NDO. Finally, the feasibility and effectiveness of proposed control scheme are demonstrated through the Lyapunov theory and simulation experiments.
{"title":"Adaptive composite anti-disturbance control for heavy haul trains","authors":"Longsheng Chen, Hui Yang","doi":"10.1093/tse/tdad009","DOIUrl":"https://doi.org/10.1093/tse/tdad009","url":null,"abstract":"\u0000 In this paper, an adaptive composite anti-disturbance control of heavy haul trains (HHTs) is proposed. First, the mechanical principle and characteristics of couplers are analyzed and the longitudinal multi-particles nonlinear dynamic model of HHTs is established, which can satisfy that the forces of vehicles in different positions are different. Subsequently, a radial basis function network (RBFNN) is employed to approximate the uncertainties of HHTs, and a nonlinear disturbance observer (NDO) is constructed to estimate the approximation error and external disturbances. To indicate and improve the approximation accuracy, a serial-parallel identification model of HHTs is constructed to generate a prediction error, and an adaptive composite anti-disturbance control scheme is developed, where the prediction error and tracking error are employed to update RBFNN weights and an auxiliary variable of NDO. Finally, the feasibility and effectiveness of proposed control scheme are demonstrated through the Lyapunov theory and simulation experiments.","PeriodicalId":52804,"journal":{"name":"Transportation Safety and Environment","volume":null,"pages":null},"PeriodicalIF":2.2,"publicationDate":"2023-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45118407","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：