基于人工免疫机制的营运货车运行风险评价研究

交通运输系统工程与信息 ›› 2021, Vol. 21 ›› Issue (1): 149-155.

基于人工免疫机制的营运货车运行风险评价研究

胡立伟^*1a，何越人^1b，李耀平^{1a, 1b}，孟玲²，殷秀芬^1a

1. 昆明理工大学，a. 交通工程学院，b. 津桥学院，理工学院，昆明 650500； 2. 云南建投基础工程有限责任公司，昆明 650500

收稿日期:2020-07-16 修回日期:2020-10-07 出版日期:2021-02-25 发布日期:2021-02-25
作者简介:胡立伟(1978- )，男，山东潍坊人，教授，博士。
基金资助:
国家自然科学基金/National Natural Science Foundation of China(61863019)。

Commercial Truck Driving Risk Evaluation Based on Artificial Immune Mechanism

HU Li-wei^*1a, HE Yue-ren^1b, LI Yao-ping^{1a, 1b}, MENG Ling², YIN Xiu-fen^1a

1a. Institute of Traffic Engineering, 1b. Science Institute, Oxbridge College, Kunming University of Science and Technology, Kunming 650500, China; 2. Yunnan Construction Investment Infrastructure Engineering Co. Ltd, Kunming 650500, China

Received:2020-07-16 Revised:2020-10-07 Online:2021-02-25 Published:2021-02-25

摘要/Abstract

摘要：

为预防营运货车交通事故，动态监管营运货车提高其运输安全性，本文从营运货车道路交通事故调查报告中统计货车交通事故发生运行风险因素频率，提取营运货车运行风险关键因素，建立完整的营运货车运行风险指标体系。运用人工免疫思想，以营运货车运行风险评价指标等级值作为抗原向量，将人工免疫危险理论的信号处理机制及改进的树突细胞算法应用于营运货车风险评价，构建基于树突细胞算法的营运货车运行风险评价模型，并以云南省某运输集团的营运货车为例进行应用分析。研究结果表明：营运货车高风险的发生通常是多因素耦合的结果；基于人工免疫机制的营运货车运行风险评价模型可利用营运车辆监控平台实时数据，从动态实时的角度评价营运货车运行风险性；模型具有合理性和有效性，且有较高的准确率及较低的误报率，可为营运货车运行风险防控提供依据。

关键词: 公路运输, 运行风险, 人工免疫机制, 营运货车, 树突细胞算法

Abstract:

This study evaluates driving risks of commercial trucks to prevent traffic accidents and to monitor commercial trucks in real-time to improve the transportation safe. From the traffic accidents investigation reports, the study calculates the frequency of driving risk factors relevant to truck traffic accidents, extracts the key factors of commercial truck driving risks and establishes a driving risk indicator system for risk evaluation. The study applies the signal processing mechanism of the artificial immune danger theory and the improved dendritic cell algorithm to the commercial truck risk assessment, which uses the level value of the risk evaluation index as the antigen vector. The driving risk evaluation model is then developed based on dendritic cell algorithm, and the commercial truck data from a transportation group in Yunnan Province was used as the empirical analysis. The results indicate that the high driving risk of commercial trucks is usually the effects of multiple factors. The proposed model is able to evaluate the driving risks of commercial trucks using the real-time data from the monitoring platform. The model is reliable and effective, and produces high accuracy rate and low false alarm rate. It also provides a basis for the prevention and management of commercial trucks driving risks.

Key words: highway transportation, driving risk, artificial immune mechanism, commercial trucks, dendritic cell algorithm

中图分类号:

U491

胡立伟，何越人，李耀平，孟玲，殷秀芬. 基于人工免疫机制的营运货车运行风险评价研究[J]. 交通运输系统工程与信息, 2021, 21(1): 149-155.

HU Li-wei, HE Yue-ren, LI Yao-ping, MENG Ling, YIN Xiu-fen. Commercial Truck Driving Risk Evaluation Based on Artificial Immune Mechanism[J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(1): 149-155.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/abstract/abstract20198.shtml

http://www.tseit.org.cn/CN/Y2021/V21/I1/149

参考文献

[1] 高建平, 柳本民, 郭忠印. 货车交通对高速公路安全性的影响[J]. 同济大学学报(自然科学版), 2005, 33(6): 763- 767. [GAO J P, LIU B M, GUO Z Y. Influence of heavy vehicles on traffic safety of freeways[J]. Journal of Tongji University (Natural Science), 2005, 33(6): 763- 767.]

[2] 姜琪. 高速公路货车最小安全行车间距研究[D]. 西安: 长安大学, 2017. [JIANG Q. Study on the minimum security following distances of trucks on freeway[D]. Xi'an: Chang'an University, 2017.]

[3] 尹心怡. 基于G42高速公路的货车运行安全评价研究 [D]. 北京: 北京交通大学, 2019. [YIN X Y. Research on evaluation of truck driving on expressway based on G42 data[D]. Beijing: Beijing Jiaotong University, 2019.]

[4] JOSE I, MANZANO C, CASTRONUNO M, et al. Exploring the relationship between truck load capacity and traffic accidents in the European union[J]. Transportation Research Part E: Logistics and Transportation Review, 2016, 88(4): 94-109.

[5] PENG Y, WANG X H, PENG S L, et al. Investigation on the injuries of drivers and copilots in rear- end crashes between trucks based on real world accident data in China[J]. Future Generation Computer Systems, 2018, 86 (8): 1251-1258.

[6] 马艳丽, 王要武, 裴玉龙. 疲劳与驾驶时间关系的实验心理学研究[J]. 西南交通大学学报, 2009, 44(4): 535- 540. [MA Y L, WANG Y W, PEI Y L. Experimental psychology study on relationship between fatigue and driving time[J]. Journal of Southwest Jiaotong University, 2009, 44(4): 535-540.]

[7] 孙蕊, 李德慧, 胡江碧. 货车驾驶员驾驶行为的研究 [C]. 国际公路安全研讨会, 2004: 382-388. [SUN R, LI D H, HU J B. Research on the driving behavior of truck drivers[C]. International Highway Safety Seminar, 2004: 382-388.]

[8] 张辉. 分心驾驶行为对交通安全影响机理与建模研究 [D]. 北京: 北京交通大学, 2018. [ZHANG H. Research on the mechanism and modeling of the influence of distracted driving behavior on traffic safety[D]. Beijing: Beijing Jiaotong University, 2018.]

[9] 胡立伟, 李林育, 王淼, 等. 基于台架试验的长下坡路段满载中型货车制动风险阈值研究[J]. 公路交通科技, 2017, 34(7): 135-144. [HU L W, LI L Y, WANG M, et al. Study on braking risk threshold value for fullloaded medium trucks on continuous long and steep downhill sections based on bench test[J]. Journal of Highway and Transportation Research and Development, 2017, 34(7): 135-144.]

[10] 许多, 方守恩, 陈雨人, 等. 高海拔地区货车运行车速影响因素研究[J]. 交通运输系统工程与信息, 2019, 19 (4): 246- 251. [XU D, FANG S E, CHEN Y R, et al. Influencing factors of truck operating speed at high altitude area[J]. Journal of Transportation Systems Engineering and Information Technology, 2019, 19(4): 246-251.]

[1]	王宁, 张佳蕊, 赵姣. 城际零担货运平台车辆路径问题研究[J]. 交通运输系统工程与信息, 2022, 22(2): 163-177.
[2]	谭二龙, 李宏海, 钟厚岳, 霍恩泽, 马晓磊. 基于轨迹数据的货车自发编队节油潜力估计[J]. 交通运输系统工程与信息, 2022, 22(1): 74-84.
[3]	贾术艳, 宋雨童, 杨紫都. 基于生长曲线函数的货车运营环节碳达峰研究[J]. 交通运输系统工程与信息, 2021, 21(6): 310-318.
[4]	甘蜜, 卿三东, 刘晓波, 李丹丹. 货车轨迹数据在公路货运系统中应用研究综述[J]. 交通运输系统工程与信息, 2021, 21(5): 91-101.
[5]	李根, 翟伟, 朱兴贝, 杨晟, 邬岚. 侧向碰撞风险对交织区汇合行为的影响[J]. 交通运输系统工程与信息, 2021, 21(4): 204-210.
[6]	李桃迎，王婷，张羽琪. 考虑多特征的高速公路交通流预测模型[J]. 交通运输系统工程与信息, 2021, 21(3): 101-111.
[7]	袁方，杨轸，周雄峰. 双车道公路弯道半径及回旋线长度对转向行为的影响[J]. 交通运输系统工程与信息, 2021, 21(1): 116-123.
[8]	戢晓峰，吴亚欣，郝京京，房锐，胡澄宇. 平纵组合路段事故严重程度致因辨识模型[J]. 交通运输系统工程与信息, 2020, 20(6): 197-204.
[9]	程颖，张佳乐，张少君，郭继孚，张达. 大型货运车辆生态驾驶及节油潜力评估[J]. 交通运输系统工程与信息, 2020, 20(6): 253-258.
[10]	段莉珍，栾庆熊，赵鑫. 区域路网货物运输量统计方法改进[J]. 交通运输系统工程与信息, 2020, 20(4): 28-33.
[11]	王岩韬，李景良，谷润平. 基于EEMD-ELM 的航班运行风险混沌预测[J]. 交通运输系统工程与信息, 2020, 20(3): 198-205.
[12]	刘昱，吴志新，李孟良，于晗正男，汪洋，贺可勋，安晓盼. 中国乘用车工况构建[J]. 交通运输系统工程与信息, 2020, 20(3): 233-240.
[13]	何永明，裴玉龙，冉斌. 基于智能路钮的超高速公路虚拟轨道系统研究[J]. 交通运输系统工程与信息, 2020, 20(2): 55-60.
[14]	王海星，王翔宇，王招贤，李学东. 基于数据挖掘的危险货物运输风险驾驶行为聚类分析[J]. 交通运输系统工程与信息, 2020, 20(1): 183-189.
[15]	王岩韬，刘毓. 基于复杂网络的航班运行风险传播分析[J]. 交通运输系统工程与信息, 2020, 20(1): 198-205.