[1]朱宇清,白宝雪,陈鸿辉,等.基于神经网络的货运列车速度曲线实时规划算法[J].控制与信息技术(原大功率变流技术),2019,(03):7-12.[doi:10.13889/j.issn.2096-5427.2019.03.300]
 ZHU Yuqing,BAI Baoxue,CHEN Honghui,et al.A Real-time Speed Profile Planning Algorithm for Freight Trains Based on Neural Network[J].High Power Converter Technology,2019,(03):7-12.[doi:10.13889/j.issn.2096-5427.2019.03.300]
点击复制

基于神经网络的货运列车速度曲线实时规划算法()
分享到:

《控制与信息技术》(原《大功率变流技术》)[ISSN:2095-3631/CN:43-1486/U]

卷:
期数:
2019年03期
页码:
7-12
栏目:
控制理论与应用
出版日期:
2019-06-05

文章信息/Info

Title:
A Real-time Speed Profile Planning Algorithm for Freight Trains Based on Neural Network
文章编号:
2096-5427(2019)03-0007-06
作者:
朱宇清白宝雪陈鸿辉陈南匡王青元
(西南交通大学电气工程学院,四川 成都 611756)
Author(s):
ZHU Yuqing BAI Baoxue CHEN Honghui CHEN Nankuang WANG Qingyuan
( School of Electrical Engineering, Southwest Jiaotong University, Chengdu, Sichuan 611756, China )
关键词:
实时计算神经网络二次规划节能优化离线训练货运列车
Keywords:
real-time calculation neural network quadratic programming energy-saving optimization offline training freight train
分类号:
U268.4+3: U268.6
DOI:
10.13889/j.issn.2096-5427.2019.03.300
文献标志码:
A
摘要:
为降低司机操纵难度、提高运输效能,文章提出一种基于神经网络模型的实时速度曲线规划算法来优化列车操纵指导。该算法首先通过分析二次规划的优化结果,确定神经网络模型的输入与输出形式;并以大量优化结果作为样本数据对神经网络模型进行训练,确定模型的结构与权重;最后将训练出的模型与输入构造模块和牵引计算模块相结合,设计出整个算法流程。为验证该规划算法的正确性、实时性和节能性,分别在虚拟复杂线路和实际线路上进行仿真。结果表明,在保证实时计算的前提下,利用该算法所得的速度曲线与基于二次规划的离线全局规划算法的速度曲线相吻合,且相比于优秀司机的操纵结果节能5.98%。
Abstract:
In order to reduce driver’s operation difficulty and improve transportation efficiency, this paper proposed a real-time speed profile planning algorithm based on neural network to guide the freight train driver’s operation. Firstly, the algorithm determines the input and output forms of the neural network model by analyzing the optimization results of the quadratic programming, and then trains the neural network model with a large number of optimization results as sample data to determine the structure and weights of the model. Finally, the trained model is combined with the input construction module and the traction calculation module to design the entire algorithm flow. In order to verify the correctness, efficiency and energy-saving of the scheduling algorithm, the virtual complex line test and the actual line test were simulated respectively. The results show that the speed profile calculated by this algorithm is identical with the speed profile calculated by the offline global planning algorithm based on quadratic programming, meanwhile, the calculation time can meet real-time requirements. The energy-saving rate is 5.98% as compared to the operation results of experienced drivers.

参考文献/References:

[1] 杨成.列车操纵控制辅助系统[J].机车电传动,2017(1):55-60.
 [2] MILROY I. Aspect of automatic train control[D].London: Loughborough University, 1980.
 [3] LEE G, MILROY I, TYLER A. Application of pontryagin’s maximum principle to the semi-automatic control of rail vehicles[C]// Second Conference on Control Engineering. Newcastle, 1982: 233-236.
 [4] 梁志成. 货运列车辅助驾驶算法仿真研究[D].成都:西南交通大学, 2015.
[5] ZHANG L, ZHUAN X. Development of an Optimal Operation Approach in the MPC Framework for Heavy-Haul Trains[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(3):1391-1400.
 [6] 王新培. 基于多目标的重载列车优化操纵研究[D]. 成都:西南交通大学, 2016.
[7] 葛学超. 基于专家系统的货运列车优化操纵算法研究[D].成都:西南交通大学,2017.
[8] HUANG Y, TAN L, CHEN L , et al. A neural network driving curve generation method for the heavy-haul train[J]. Advances in Mechanical Engineering, 2016, 8(5):1-14.
 [9] 王悉. 基于机器学习的重载列车智能驾驶方法研究[D].北京:北京交通大学,2017.
 [10] CLEVERT D-A, UNTERTHINER T, HOCHREITER S. Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)[C/OL]//ICLR 2016. San Juan, Puerto Rico, 2016. https://arxiv.org/abs/1511.07289v5.
 [11] KINGMA D P, BA J. Adam: A Method for Stochastic Optimization [C/OL]//ICLR 2015. San Diego, CA, 2015. https://arxiv.org/abs/ 1412.6980v9.

相似文献/References:

[1]樊京路,易韵岚.基于小波分析的光伏并网逆变器故障诊断[J].控制与信息技术(原大功率变流技术),2014,(05):12.[doi:10.13889/j.issn.2095-3631.2014.05.003]
 FAN Jinglu,YI Yunlan.Fault Diagnosis of Photovoltaic Grid-connected Inverter Based on Wavelet Analysis[J].High Power Converter Technology,2014,(03):12.[doi:10.13889/j.issn.2095-3631.2014.05.003]
[2]王智弘,李东辉.变流器故障诊断技术综述[J].控制与信息技术(原大功率变流技术),2014,(05):1.[doi:10.13889/j.issn.2095-3631.2014.05.001]
 WANG Zhihong,LI Donghui.A Survey of Fault Diagnosis Technology for Converter[J].High Power Converter Technology,2014,(03):1.[doi:10.13889/j.issn.2095-3631.2014.05.001]
[3]丁惜瀛,王晶晶,张泽宇,等.基于神经网络的4WD电动汽车AFS/DYC解耦控制研究[J].控制与信息技术(原大功率变流技术),2013,(04):48.[doi:10.13889/j.issn.2095-3631.2013.04.005]
 DING Xi-ying,WANG Jing-jing,ZHANG Ze-yu,et al.Research on AFS/DYC Decoupling Control of 4WD EV Based on Neutral Network[J].High Power Converter Technology,2013,(03):48.[doi:10.13889/j.issn.2095-3631.2013.04.005]
[4]李彦涌,忻 力,赖 伟,等.基于现场数据的IGBT 结温实时计算[J].控制与信息技术(原大功率变流技术),2017,(01):24.[doi:10.13889/j.issn.2095-3631.2017.01.005]
 LI Yanyong,XIN Li,LAI Wei,et al.IGBT Real-time Junction Temperature Calculation Based on Converter Operation Data[J].High Power Converter Technology,2017,(03):24.[doi:10.13889/j.issn.2095-3631.2017.01.005]
[5]张全明,邓亚波.基于神经网络的机车牵引系统故障诊断研究[J].控制与信息技术(原大功率变流技术),2018,(03):74.[doi:10.13889/j.issn.2096-5427.2018.03.016]
 ZHANG Quanming,DENG Yabo.Locomotive Traction Malfunction Diagnosing System with Neural Network[J].High Power Converter Technology,2018,(03):74.[doi:10.13889/j.issn.2096-5427.2018.03.016]
[6]刘敬,高志建.应用神经网络法预测光伏系统发电功率[J].控制与信息技术(原大功率变流技术),2010,(03):28.[doi:10.13889/j.issn.2095-3631.2010.03.007]
[7]朱宇清,白宝雪,陈鸿辉,等. 基于神经网络的货运列车速度曲线实时规划算法[J].控制与信息技术(原大功率变流技术),2019,(03):1.[doi:10.13889/j.issn.2096-5427.2019.03.300]
 ZHU Yuqing,BAI Baoxue,CHEN Honghui,et al. A Real-time Speed Profile Planning Algorithm for Freight Trains Based on Neural Network[J].High Power Converter Technology,2019,(03):1.[doi:10.13889/j.issn.2096-5427.2019.03.300]

备注/Memo

备注/Memo:
收稿日期:2019-03-01
作者简介:朱宇清(1994—),男,硕士研究生,主要研究方向为列车运行控制。
基金项目:国家重点研发计划(2017YFB1201302)
更新日期/Last Update: 2019-06-14