Energy saving optimization of high-speed train based on improved genetic algorithm
-
摘要: 为有效降低列车运行能耗,针对高速列车行进过程中的能耗优化问题,讨论了列车运行阻力的计算及列车停车点的设置,以此建立以列车能耗最小为优化目标的列车运行优化模型,提出3代逼近搜索的引导机制,改进了传统遗传算法中的算子,同时引入逆转算子提高算法求解能力。以CRH380B型高速列车和合福高铁(合肥—福州)数据为基础进行仿真,列车运行能耗降低了10.7%。仿真结果表明,提出的改进遗传优化算法在高速列车行进过程中,满足列车运行准时性和安全性,且能够有效降低运行能耗。Abstract: In order to effectively reduce the energy consumption of train operation, aiming at the problem of energy consumption optimization in the process of high-speed train running, this paper discussed the calculation of train running resistance and the setting of train stop point, based on this, established the optimization model of train operation with the minimum energy consumption as the optimization objective, proposed the guidance mechanism of three generation approach search, which improved the operator in traditional genetic algorithm, and introduced the reversal operator to improve the algorithm solving ability. The paper carried out the simulation based on the data of CRH380B high-speed train and Hefei—Fuzhou high-speed railway. The energy consumption of train operation was reduced by 10.7%. The simulation results show that the improved genetic optimization algorithm proposed in this paper can meet the punctuality and safety of high-speed train operation, and can effectively reduce the operation energy consumption.
-
表 1 3代逼近搜索规则
第1代 + + + + – – – 第2代 + + – – + + – 第3代 + – + – – + 下次变异方向 保持当前标志位方向 回朔 保持当前标志位方向 更新标志位方向 回朔 保持当前标志位方向 更新标志位方向 表 2 列车参数
参数名称 参数值 列车总重 495 t 列车长度 200.3 m 最大运行速度 300 km/h 单位阻力 (0.0257+0.050 7 v+0.000 505 57 v2)kN
v为列车当前运行时速定员 510 人 表 3 改进前后列车运行数据对比分析
评价指标 优化前指标 优化后指标 性能比较 运行时间 1430 s 1459 s +2% 能耗 6.87×10 9 J 6.13×10 9 J −10.7% -
[1] Hoang H, Polis M, Haurie A. Reducing energy consumption through trajectory optimization for a metro network [J]. IEEE Transactions on Automatic Control, 1975, 20(5): 590-595. doi: 10.1109/TAC.1975.1101058 [2] Howlett P. An optimal strategy for the control of a train [J]. The Journal of the Australian Mathematical Society Series B Applied Mathematics, 1990, 31(4): 454-471. doi: 10.1017/S0334270000006780 [3] 李玉生, 侯忠生. 基于遗传算法的列车节能控制研究 [J]. 系统仿真学报,2007(2):384-387. doi: 10.3969/j.issn.1004-731X.2007.02.039 [4] Chang C S, Sim S S. Optimising train movements through coast control using genetic algorithms [J]. Electric Power Application, 1997, 144(1): 65-73. doi: 10.1049/ip-epa:19970797 [5] 卢启衡, 冯晓云, 王青元. 基于遗传算法的追踪列车节能优化 [J]. 西南交通大学学报,2012,47(2):265-270. [6] 雷 明, 孟学雷. 基于协同进化遗传算法的高速铁路运行调整研究 [J]. 铁道科学与工程学报,2017,14(6):1137-1145. doi: 10.3969/j.issn.1672-7029.2017.06.004 [7] 宋文婷, 谭 觅, 蔡文川, 等. 高速列车的节能操纵策略研究 [J]. 铁道科学与工程学报,2016,13(3):423-429. doi: 10.3969/j.issn.1672-7029.2016.03.003 [8] 刘 炜, 李群湛, 郭 蕾, 等. 基于多种群遗传算法的城轨列车节能运行优化研究 [J]. 系统仿真学报,2010,22(4):921-925. [9] 纪云霞, 孙鹏飞, 毛畅海, 等. 基于改进遗传算法的列车运行曲线优化 [J]. 计算机与现代化,2018(8):1-7. doi: 10.3969/j.issn.1006-2475.2018.08.001 [10] 张 刚, 潘金山, 倪少权, 等. 列车牵引计算仿真的研究 [J]. 铁路计算机应用,2007,16(8):18-20. doi: 10.3969/j.issn.1005-8451.2007.08.006 [11] 王自力. 列车节能运行优化操纵的研究 [J]. 西南交通大学学报,1994(3):275-280. [12] 梁志成, 王青元, 何 坤, 等. 基于极大值原理的电动车组节能操纵 [J]. 铁道学报,2015,37(10):16-25. doi: 10.3969/j.issn.1001-8360.2015.10.003 [13] 马超云, 丁 勇, 杜 鹏, 等. 基于遗传算法的列车节能运行惰行控制研究 [J]. 铁路计算机应用,2010,19(6):4-8. doi: 10.3969/j.issn.1005-8451.2010.06.002 [14] 张凯举, 彭先涛. 基于进化逆转操作算子的遗传算法对步进式加热炉炉温优化 [J]. 江南大学学报(自然科学版),2013,12(6):677-681.