曹磊1,陈长文2,孙强1
（1、山东大学 能源与动力工程学院，山东 济南 250061；2、中国人民解放军94270部队，山东 济南250117）
摘要：城市道路中汽车的行驶工况复杂多变。本文首先基于统计学方法探究不同地理特征对车辆速度行为的影响规律，建立不同地理特征的车辆行为数据库，详细阐述了实验数据的处理与转移概率矩阵的求解。在此基础上，利用马尔可夫链对未来行驶路线已知的汽车行驶工况进行预测。最后，以实测数据对工况的预测精度进行分析和验证，验证结果表明特征参数中平均速度的相对误差最小仅1.1%，匀速时间比的相对误差最大为14.7%，此预测方法可行。
关键词：地理特征；行驶工况预测；马尔可夫链；转移概率矩阵
Abstract Driving conditions of automobiles in the city are complicated and changeful. Based on the statistical method, this paper explores the influence of different geographical features on vehicle velocity behavior, and establishes a vehicle behavior database with different geographical features. Also, the paper elaborates the processing method of experimental data and the resolution method of transition matrix in detail. Based on these, the Markov chain is used to predict the driving conditions of the vehicles with known future routes. Finally, the prediction precision of the driving conditions is analyzed and validated with the measured data, and the verification results show that the relative error of the average velocity is only 1.1%, and the relative error of the constant velocity ratio is 14.7%, proving the feasibility of this approach.
Key words: Geography Features；Prediction of Driving Conditions；Markov Chain；Matrix of Transition Probability
|
