高速列车智能驾驶算法仿真研究
|
摘要
对应用于高速列车智能驾驶系统的智能驾驶算法进行研究,可以有效弥补人工驾驶的缺陷。对智能驾驶算法进行研究,需要综合考虑线路限速信息和列车实时运行信息,完成智能驾驶算法设计。传统的智能驾驶算法先根据限速曲线设定目标速度曲线并精确跟踪,实现高速列车的智能驾驶,但忽略了工况切换次数,导致能耗大且舒适性低。提出基于数据挖掘的高速列车智能驾驶算法,突破跟踪目标速度曲线的控制思想,将人工驾驶策略应用于高速列车智能驾驶中,无需设定列车目标速度曲线,仅采用人工驾驶数据和数据挖掘方法,利用挖掘的人工驾驶策略实现列车的多目标智能驾驶。仿真结果表明,所提算法能够有效降低能耗提高舒适度,实现列车的平稳、舒适、准点、精确运行。
An intelligent operation algorithm for high-speed train intelligent operation system based on data mining is proposed. The common intelligent operation algorithms neglect the number of switching of working conditions, resulting in large energy consumption and low comfort. In this paper, we breaks through the control idea of tracking target speed curve and apply a manual operation strategy to intelligent driving of high-speed train. Firstly, the data mining method was used to mine manual operation strategy, and the manual driving data were collected. Then, the mined manual operation strategy was used as the train running control model. Thus the multi-target intelligent operation of the train was accurately achieved. Simulation result shows that the proposed algorithm can effectively reduce energy consumption and improve comfort, achieving a smooth, comfortable, punctual and precise operation.
An intelligent operation algorithm for high-speed train intelligent operation system based on data mining is proposed. The common intelligent operation algorithms neglect the number of switching of working conditions, resulting in large energy consumption and low comfort. In this paper, we breaks through the control idea of tracking target speed curve and apply a manual operation strategy to intelligent driving of high-speed train. Firstly, the data mining method was used to mine manual operation strategy, and the manual driving data were collected. Then, the mined manual operation strategy was used as the train running control model. Thus the multi-target intelligent operation of the train was accurately achieved. Simulation result shows that the proposed algorithm can effectively reduce energy consumption and improve comfort, achieving a smooth, comfortable, punctual and precise operation.
引文
[1] 冷勇林. 基于专家经验和机器学习的列车智能驾驶算法研究[D]. 北京交通大学, 2013.
[2] E Schüler—Hainsch,柳欣生. 优化行车方法,节省长途运输中的牵引能量[J]. 国外内燃机车, 1990,(9):47-53.
[3] Panou K, Tzieropoulos P, Emery D. Railway driver advice systems: Evaluation of methods, tools and systems[J]. Journal of Rail Transport Planning & Management, 2013,3(4):150-162.
[4] 冈田宏. 日本新干线的现状和未来的发展[J]. 中国铁道科学, 2002,23(2):21-25.
[5] Q Song, Y D Song, W Cai. Adaptive backstepping control of train systems with traction/braking dynamics and uncertain resistive forces[J]. Vehicle System Dynamics, 2011,49(9):1441-1454.
[6] 罗强. 基于模糊PID的列车自动驾驶算法研究[J]. 自动化应用, 2015,(9):26-28.
[7] D Chen, C Gao. Soft computing methods applied to train station parking in urban rail transit[J]. Applied Soft Computing, 2012,12(2):759-767.
[8] 李诚,王小敏. 基于粒子群优化的ATO控制策略[J]. 铁道学报, 2017,39(3):53-58.
[9] 谭莉,王长林. CTCS3级列控系统ATP防护曲线算法[J]. 铁路计算机应用, 2014,23(7): 48-52.
[10] 中华人民共和国铁道行业标准. 列车牵引计算规程[S]. TB/T1407-1998, 1998.
[11] 饶忠. 列车牵引计算(第三版)[M]. 北京:中国铁道出版社, 2010:30-36.
[12] 李艳美,张卓奎. 基于贝叶斯网络的数据挖掘方法[J]. 计算机仿真, 2008,25(2):87-89.
[13] 施彦,韩力群,陈秀新. 基于集成协同PSO算法的车辆路径优化仿真[J]. 计算机仿真, 2012,(6):339-342.
[14] 常卫东,王正华,鄢喜爱. 基于集成神经网络入侵检测系统的研究与实现[J]. 计算机仿真, 2007, 24(3):134-137.
[2] E Schüler—Hainsch,柳欣生. 优化行车方法,节省长途运输中的牵引能量[J]. 国外内燃机车, 1990,(9):47-53.
[3] Panou K, Tzieropoulos P, Emery D. Railway driver advice systems: Evaluation of methods, tools and systems[J]. Journal of Rail Transport Planning & Management, 2013,3(4):150-162.
[4] 冈田宏. 日本新干线的现状和未来的发展[J]. 中国铁道科学, 2002,23(2):21-25.
[5] Q Song, Y D Song, W Cai. Adaptive backstepping control of train systems with traction/braking dynamics and uncertain resistive forces[J]. Vehicle System Dynamics, 2011,49(9):1441-1454.
[6] 罗强. 基于模糊PID的列车自动驾驶算法研究[J]. 自动化应用, 2015,(9):26-28.
[7] D Chen, C Gao. Soft computing methods applied to train station parking in urban rail transit[J]. Applied Soft Computing, 2012,12(2):759-767.
[8] 李诚,王小敏. 基于粒子群优化的ATO控制策略[J]. 铁道学报, 2017,39(3):53-58.
[9] 谭莉,王长林. CTCS3级列控系统ATP防护曲线算法[J]. 铁路计算机应用, 2014,23(7): 48-52.
[10] 中华人民共和国铁道行业标准. 列车牵引计算规程[S]. TB/T1407-1998, 1998.
[11] 饶忠. 列车牵引计算(第三版)[M]. 北京:中国铁道出版社, 2010:30-36.
[12] 李艳美,张卓奎. 基于贝叶斯网络的数据挖掘方法[J]. 计算机仿真, 2008,25(2):87-89.
[13] 施彦,韩力群,陈秀新. 基于集成协同PSO算法的车辆路径优化仿真[J]. 计算机仿真, 2012,(6):339-342.
[14] 常卫东,王正华,鄢喜爱. 基于集成神经网络入侵检测系统的研究与实现[J]. 计算机仿真, 2007, 24(3):134-137.