| 406 | 1 | 78 |
| 下载次数 | 被引频次 | 阅读次数 |
【背景】汽车保有量的急剧增长导致城市交通拥堵和安全问题日益严重，城市快速路成为交通事故频发地，其交通事故发生率已经占城市公路交通事故的50%以上。【目标】为探究城市快速路上驾驶人状态变化、驾驶风格、驾驶风险程度之间的相互作用和关联机制，提出四种基于多源信息融合的驾驶风险辨识模型，辨识不同风格的驾驶人驾驶危险等级并寻找最优模型。【方法】以驾驶人生理、心理及车辆运行数据为基础，构建多源信息融合的驾驶数据集，首先使用皮尔逊相关性分析和K-means聚类得出驾驶人驾驶风格；其次通过熵权法并结合驾驶风格标签量化不同风格驾驶人的驾驶风险率；最后使用MLP、SVM、CNN、LSTM搭建四种驾驶风险辨识模型，采用模型性能评价指标选取最优模型。【结果】根据车辆运行数据将驾驶人驾驶风格分为保守、稳健和冲动型，基于驾驶风格结果将驾驶人风险等级量化为低、中、高三类；四种驾驶风险辨识模型中CNN-LSTM模型辨识效果最好，准确率为0.90，能有效辨识驾驶人风险等级；在城市快速路匝道入口、出口驾驶人车速平均变化率为22.14%、14.8%。【应应用用】研究结果可为城市道路交通安全管理和道路人因事故预防保障提供参考，更好地针对高风险驾驶人进行重点管理，后续可以结合驾驶人眼动数据进行进一步分析，提高城市道路运行安全。
Abstract：[Background] Owing to the rapid growth of car ownership, urban traffic congestion and safety problems are becoming increasingly severe. Urban expressways have become common locations of traffic accidents, and traffic-accident rates constitute more than 50% of urban-highway traffic accidents. [Objective] To analyze the interaction and correlation mechanism between driver-state change, driving style, and driving-risk degree in urban expressways, four driving-risk identification models based on multisource information fusion are proposed, the driving danger levels of drivers with different styles are determined, and an optimal model is identified. [Methods] Based on the physiological, psychological, and vehicle operation data of a driver, a driving dataset with multisource information fusion is constructed. First, the driver's driving style is obtained via Pearson correlation analysis and K-means clustering. Second, the entropy-weight method and driving-style labels are used to quantify the driving-risk rates of drivers with different driving styles. Finally, MLP,SVM, CNN, and LSTM are used to develop four driving-risk identification models, and a model-performance evaluation index is used to select the optimal model. [Results] Based on the vehicle operation data, the driver's driving style is classified into conservative, stable, and impulsive type, and the driver's risk level is quantified into three categories, i.e., low, medium, and high, based on the driving-style results. Among the four driving-risk identification models, the CNN-LSTM model demonstrates the best recognition effect, with an accuracy rate of 0.90, which can effectively identify the driver's risk level. The average change rate of the driver's speed at the entrance and exit of an urban expressway ramp is 22.14% and 14.8%, respectively. [Applications] The results of this study provide a reference for managing urban-road traffic safety and preventing human-induced road accidents. They enable targeted management of high-risk drivers. Future studies should incorporate eyemovement data to further enhance urban-road safety.
[1]吴玲涛,何勇,米晓艺,等.浅析城市快速路交通事故特性[J].道路交通与安全, 2008, 8(5):10-12, 17.WU Lingtao, HE Yong, MI Xiaoyi, et al. Research on characteristic of traffic accidents on urban expressway[J].Road Traffic&Safety, 2008, 8(5):10-12, 17.
[2]侯珊珊,张杰,张雪榆,等.考虑驾驶风格的高密度立交群出入口车辆驾驶风险研究[J].科学技术与工程,2024, 24(10):4317-4328.HOU Shanshan, ZHANG Jie, ZHANG Xueyu, et al. Investigation on the driving risk of high-density over-exchange group vehicles considering driving style[J]. Science Technology and Engineering, 2024, 24(10):4317-4328.
[3]朱兴林,姚亮,刘泓君,等.考虑驾驶风格差异的高原公路危险路段识别研究[J].交通运输系统工程与信息,2022, 22(6):172-182.ZHU Xinglin, YAO Liang, LIU Hongjun, et al. Identification of dangerous sections of highland roads considering different driving behaviors[J]. Journal of Transportation Systems Engineering and Information Technology, 2022,22(6):172-182.
[4]李思贤,邢增勇,钱大琳,等.危险货物道路运输车辆驾驶人风险倾向性分类研究[J].交通运输系统工程与信息, 2023, 23(3):161-173.LI Sixian, XING Zengyong, QIAN Dalin, et al. Risk tendency classification of drivers of road transport vehicles of hazardous materials[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(3):161-173.
[5]丁瑞,刘俊,蒋艳,等.基于车辆加速度数据的互通立交匝道驾驶风险分析[J].交通信息与安全, 2021, 39(1):17-25.DING Rui, LIU Jun, JIANG Yan, et al. Driving risks of interchange ramps based on vehicle acceleration data[J].Journal of Transport Information and Safety, 2021, 39(1):17-25.
[6]程泽阳,孙凌霞,丁恒,等.车路协同环境下道路交通安全研究进展[J].交通运输工程与信息学报, 2024, 22(3):14-33.CHENG Zeyang, SUN Lingxia, DING Heng, et al. Research progress of road traffic safety in cooperative vehicle infrastructure environment[J]. Journal of Transportation Engineering and Information, 2024, 22(3):14-33.
[7]姜平,范虹慧,黄鹤,等.跟驰工况下考虑风险分布的驾驶风格分类[J].合肥工业大学学报（自然科学版）, 2024,47(11):1514-1518.JIANG Ping, FAN Honghui, HUANG He, et al. Driving style classification considering risk distribution in car-following condition[J]. Journal of Hefei University of Technology(Natural Science), 2024, 47(11):1514-1518.
[8]戢晓峰,王健,徐迎豪,等.基于驾驶风格的山区公路穿村镇段行车风险场灵敏度分析[J].交通运输系统工程与信息, 2024,24(6):316-325.JI Xiaofeng, WANG Jian, XU Yinghao, et al. Driving style-based sensitivity analysis of driving risk field in mountain highway through village and town sections[J].Journal of Transportation Systems Engineering and Information Technology, 2024, 24(6):316-325.
[9]马国忠,李燕,郭孜政,等.驾驶行为险态辨识方法[J].公路交通科技, 2013, 30(7):113-118.MA Guozhong, LI Yan, GUO Zizheng, et al. A method for identifying risk status of driving behavior[J]. Journal of Highway and Transportation Research and Development, 2013, 30(7):113-118.
[10]刘应吉,曾诚,王书举,等.基于卫星定位数据的驾驶行为安全与节能评价方法[J].公路交通科技, 2018, 35(1):121-128, 158.LIU Yingji, ZENG Cheng, WANG Shuju, et al. An evaluation method of safety and energy-saving driving behavior based on satellite positioning data[J]. Journal of Highway and Transportation Research and Development, 2018, 35(1):121-128, 158.
[11]芮红睿,武加宝,胡立伟.基于可拓云模型的高速公路隧道入口段行车风险评价研究[J].交通运输工程与信息学报, 2023, 21(2):55-65.RUI Hongrui, WU Jiabao, HU Liwei. Driving risk assessment of highway tunnel entrances based on extended cloud model[J]. Journal of Transportation Engineering and Information, 2023, 21(2):55-65.
[12]张佳薇,郑岳涵,李明宝.组合赋权-模糊综合评价的安全驾驶行为分析[J].科学技术与工程, 2022, 22(23):10255-10261.ZHANG Jiawei, ZHENG Yuehan, LI Mingbao. Analysis of safe driving behavior based on combination weighting and fuzzy comprehensive evaluation[J]. Science Technology and Engineering, 2022, 22(23):10255-10261.
[13]张驰,向宇杰,兰富安,等.基于合成坡度的连续下坡路段货车行车风险评价方法[J].公路交通科技, 2023,40(10):51-61.ZHANG Chi, XIANG Yujie, LAN Fuan, et al. Risk assessment method for trucks on continuous downhill section based on synthetic slope[J]. Journal of Highway and Transportation Research and Development, 2023, 40(10):51-61.
[14]刘韶新,苏东兰,叱干都,等.基于驾驶模拟实验的快速路交织区运行风险评价[J].科学技术与工程, 2021,21(2):751-757.LIU Shaoxin, SU Donglan, CHI Gandu, et al. Operation risk evaluation of weaving area of expressway based on the driving simulation[J]. Science Technology and Engineering, 2021, 21(2):751-757.
[15] WANG J, HUANG H, LI Y, et al. Driving risk assessment based on naturalistic driving study and driver attitude questionnaire analysis[J]. Accident Analysis&Prevention, 2020, 145:105680.
[16]孙宫昊,荣建,常鑫,等.基于驾驶行为模式转移的驾驶行为风险评估方法[J].汽车技术, 2021(11):22-29.SUN Gonghao, RONG Jian, CHANG Xin, et al. Evaluation method of driving behavior risk based on driving behavior pattern shift[J]. Automobile Technology, 2021(11):22-29.
[17]李守义,任方涛.基于聚类的营运客车驾驶行为风险评估模型[J].信息技术与信息化, 2024(8):52-56.
[18] HICKS T G, WIERWILLE W W. Comparison of five mental workload assessment procedures in a movingbase driving simulator[J]. Human Factors, 1979, 21(2):129-143.
[19] CONSTANTINOU E, PANAYIOTOU G, KONSTANTINOU N, et al. Risky and aggressive driving in young adults:personality matters[J]. Accident Analysis&Prevention, 2011, 43(4):1323-1331.
[20] SHANGGUAN Q, FU T, WANG J, et al. An integrated methodology for real-time driving risk status prediction using naturalistic driving data[J]. Accident Analysis&Prevention, 2021, 156:106122.
[21] SEACRIST T, DOUGLAS E C, HANNAN C, et al.Near crash characteristics among risky drivers using the SHRP2 naturalistic driving study[J]. Journal of Safety Research, 2020, 73:263-269.
[22] XING L, HE J, LI Y, et al. Comparison of different models for evaluating vehicle collision risks at upstream diverging area of toll plaza[J]. Accident Analysis&Prevention, 2020, 135:105343.
[23]尚婷,连冠,黄龙显,等.基于多源数据的特长隧道驾驶疲劳模型[J].交通信息与安全, 2024, 42(4):30-41.SHANG Ting, LIAN Guan, HUANG Longxian et al. A driving fatigue model for extra-long tunnels based on multi-source data[J]. Journal of Transport Information and Safety, 2024, 42(4):30-41.
[24]王永亮,李超,许恩永,等.基于XGBoost算法的商用车驾驶风险辨识模型[J].机械设计与制造, 2024(8):84-89, 95.WANG Yongliang, LI Chao, XU Enyong, et al. Commercial vehicle driving risk recognition model based on XGBoost algorithm[J]. Machinery Design&Manufacture,2024(8):84-89, 95.
[25]胡立伟,林玉珍.驾驶人公路驾车过程中主要生理参数变化规律研究[J].交通运输系统工程与信息, 2014,14(1):41-46.HU Liwei, LIN Yuzhen. Variation law of driver’s main physiological indicators driving on highway[J]. Journal of Transportation Systems Engineering and Information Technology, 2014, 14(1):41-46.
[26]邵玫华.心率变异性分析的研究进展[J].山东医药,2014, 54(17):91-93.
[27]李晓阳,刘树伟.驾驶风格研究综述[J].时代汽车,2020(15):189-190.LI Xiaoyang, LIU Shuwei. Overview of driving style research[J]. Auto Time, 2020(15):189-190.
[28]陈正欢.高密度互通立交驾驶人精神负荷与安全风险研究[D].重庆:重庆交通大学, 2023.CHEN Zhenghuan. Study on driver’s mental workload and safety risks of high-density interchanges[D]. Chongqing:Chongqing Jiaotong University, 2023.
[29]孙子秋.高密度互通立交出口驾驶人动态视觉特性研究[D].重庆:重庆交通大学, 2022.SUN Ziqiu. Study on car driver’s dynamic visual characters in exit of high-density interchange[D]. Chongqing:Chongqing Jiaotong University, 2022.
[30] LEBEDEV V, LEMPITSKY V. Speeding-up convolutional neural networks:a survey[J]. Bulletin of the Polish Academy of Sciences Technical Sciences, 2018, 66(6):799-810.
基本信息:
DOI：10.19961/j.cnki.1672-4747.2024.12.005
中图分类号:U495;U491.25
引用信息:
[1]朱兴林,陈梦瑶,刘泓君等.基于多源信息融合的城市快速路驾驶风险辨识与方法[J].交通运输工程与信息学报,2025,23(02):110-121.DOI:10.19961/j.cnki.1672-4747.2024.12.005.
基金信息:
2024年新疆维吾尔自治区自然科学基金项目（2524KJTZRJJ）; 2024年新疆维吾尔自治区高校科研计划项目（2224GXKYJH）; 数字时代新疆高校交通运输专业学位研究生优质课程建设与实践项目（XJ2024GY14）