基于BP神经网络和遗传算法的简单链型悬挂接触网结构优化

doi:10.3901/JME.2024.12.313

机械工程学报 ›› 2024, Vol. 60 ›› Issue (12): 313-320.doi: 10.3901/JME.2024.12.313

扫码分享

基于BP神经网络和遗传算法的简单链型悬挂接触网结构优化

卢琪¹, 苏凯新¹, 张继旺¹, 闫涛², 杨冰¹, 张浩楠¹

1. 西南交通大学牵引动力国家重点实验室成都 610031;
2. 保德利电气设备有限责任公司宝鸡 721000

收稿日期:2023-07-17 修回日期:2023-10-25 出版日期:2024-06-20 发布日期:2024-08-23
作者简介:卢琪,男,1996年出生。主要研究方向为接触网结构服役可靠性。E-mail:luqi9668@foxmail.com;张继旺(通信作者),男,1983年出生,博士,研究员,博士研究生导师。主要研究方向为机械结构强度与可靠性。E-mail:zhangjiwang@swjtu.cn
基金资助:
国家自然科学基金资助项目(52075457)。

Structural Optimization of Simple Catenary Based on BP Neural Network and Genetic Algorithm

LU Qi¹, SU Kaixin¹, ZHANG Jiwang¹, YAN Tao², YANG Bing¹, ZHANG Haonan¹

1. State-key Laboratory of Traction Power, Southwest Jiaotong University, Chengdu 610031;
2. Bj-baodeli Electrical Equipment Co., Ltd., Baoji 721000

Received:2023-07-17 Revised:2023-10-25 Online:2024-06-20 Published:2024-08-23

摘要/Abstract

摘要： 受电弓和接触网之间的接触力标准差是评价弓网受流质量的重要指标。为了优化弓网受流质量，建立经EN 50318标准和已有文献仿真结果验证的弓网耦合仿真模型。采用中心复合设计方法设计输入-吊弦间距和接触线预弛度参数试验表，然后根据该试验表调整弓网耦合仿真模型，并进行仿真，提取输出-接触力标准差。采用BP神经网络(Back propagation neural network，BPNN)建立输入和输出之间的关系模型，模型预测精度达95.50%。然后，采用遗传算法(Genetic algorithm，GA)搜寻该BP神经网络模型的最小接触力标准差及所对应的最优输入参数组合。优化结果表明，BPNN-GA优化方法能显著降低弓网接触力标准差，从而提高弓网受流质量。最后，通过将优化后的接触网与原始接触网不同速度下接触力标准差进行比较，验证了优化接触网的弓网受流改善效果。经优化后的接触网可为实际接触网设计、施工、维修提供指导。

关键词: 弓网仿真, 受流质量, BP神经网络, 遗传算法

Abstract: The standard deviation of contact force(CFSD) between pantograph and catenary is an important index to evaluate the current collection quality of pantograph and catenary. In order to optimize the pantograph catenary current collection quality, a pantograph-catenary coupling simulation model verified by EN 50318 standard and the simulation results in the existing literature is established. The central composite design method is used to design the test table of input parameters (dropper spacing and contact wire pre-sag). The pantograph catenary coupling simulation model is carried out after modifying the model according to the test table. Based on this, the output parameter(CFSD) is obtained. Back propagation neural network(BPNN) is used to establish the relationship model between input and output parameter, and the prediction accuracy of the model is proved to be 95.50%. Then, genetic algorithm (GA) is used to search the minimum standard deviation of contact force and the corresponding optimal combination of input parameters of the BP neural network model. The optimization results show that BPNN-GA optimization method can significantly reduce the standard deviation of pantograph catenary contact force and improve the current collection quality of pantograph-catenary. Finally, by comparing the standard deviation of contact force between the optimized catenary and the original catenary at different speeds, the improvement effect of pantograph catenary current collection of the optimized catenary is verified. The optimized catenary can provide guidance for the design, construction and maintenance of the actual catenary.

Key words: pantograph-catenary simulation, current collection quality, BP neural network, genetic algorithm

中图分类号:

U225

卢琪, 苏凯新, 张继旺, 闫涛, 杨冰, 张浩楠. 基于BP神经网络和遗传算法的简单链型悬挂接触网结构优化[J]. 机械工程学报, 2024, 60(12): 313-320.

LU Qi, SU Kaixin, ZHANG Jiwang, YAN Tao, YANG Bing, ZHANG Haonan. Structural Optimization of Simple Catenary Based on BP Neural Network and Genetic Algorithm[J]. Journal of Mechanical Engineering, 2024, 60(12): 313-320.

参考文献

[1] LEE J H，PARK T W，OH H K，et al. Analysis of dynamic interaction between catenary and pantograph with experimental verification and performance evaluation in new high-speed line[J]. Vehicle System Dynamics International Journal of Vehicle Mechanics & Mobility，2015，53(8)：1117-1134.
[2] NVIK P，RNNQUIST A，STICHEL S. The use of dynamic response to evaluate and improve the optimization of existing soft railway catenary systems for higher speeds[J]. Proceedings of the Institution of Mechanical Engineers Part F Journal of Rail and Rapid Transit，2016，230(4)：1388-1396.
[3] BRUNI S，AMBROSIO J，CARNICERO A，et al. The results of the pantograph-catenary interaction benchmark[J]. Vehicle System Dynamics，2015，53(3)：412-435.
[4] POMBO J，JORGE A，PEREIRA M. Influence of pantograph suspension characteristics on the contact quality with the catenary for high speed trains[J]. Computers & Structures，2012，110：32-42.
[5] PARK T J，HAN C S，JANG J H. Dynamic sensitivity analysis for the pantograph of a high-speed rail vehicle[J]. Journal of Sound & Vibration，2003，266(2)：235-260.
[6] 吴孟臻，刘洋，许向红. 高速弓网系统动力学参数敏度分析及优化[J]. 力学学报，2021，53(1)：75-83. WU Mengzhen，LIU Yang，XU Xianghong. Sensitivity analysis and optimization on parameters of high speed pantograph-catenary system[J]. Chinese Journal of Theoretical and Applied Mechanics，2021，53(1)：75-83.
[7] LEE J H，KIM Y G，JIN-SUNG P，et al. Performance evaluation and design optimization using differential evolutionary algorithm of the pantograph for the high-speed train[J]. Journal of Mechanical Science & Technology，2012，26(10)：3253-3260.
[8] JORGE A，POMBO J，PEREIRA M，et al. Optimization of high-speed railway pantographs for improved pantograph-catenary contact[J]. Theoretical and Applied Mechanics Letters，2013，3(1)：013006.
[9] ZHOU N，ZHANG W. Investigation on dynamic performance and parameter optimization design of pantograph and catenary system[J]. Finite Elements in Analysis and Design，2011，47(3)：288-295.
[10] YONG H，Kl A，YP A，et al. Influence of contact wire pre-sag on the dynamics of pantograph-railway catenary[J]. International Journal of Mechanical Sciences，2010，52(11)：1471-1490.
[11] ZHANG W，MEI G，ZENG J. A study of pantograph/catenary system dynamics with influence of presag and irregularity of contact wire[J]. Vehicle System Dynamics，2016，37(sup1)：593-604.
[12] ZHANG W，LIU Y，MEI G. Evaluation of the coupled dynamical response of a pantograph-catenary system：Contact force and stresses[J]. Vehicle System Dynamics，2006，44(8)：645-658.
[13] GREGORI S，TUR M，NADAL E，et al. An approach to geometric optimisation of railway catenaries[J]. Vehicle System Dynamics，2018，56(8)：1162-1186.
[14] ZHAO H，WANG Y，SONG J，et al. The pollutant concentration prediction model of NNP-BPNN based on the INI algorithm，AW method and neighbor-PCA[J]. Journal of Ambient Intelligence and Humanized Computing，2019，10(8)：3059-3065.
[15] 关金发. 预弛度接触网三维静态形状计算[J]. 铁道标准设计，2013(10)：116-120. GUAN Jinfa. Calculation of three-dimensional static shape of pre-sag catenary[J]. Railway Standard Design，2013(10)：116-120.
[16] 周宁，李瑞平，张卫华. 基于负弛度法的接触网建模与仿真[J]. 交通运输工程学报，2009，9(4)：28-32. ZHOU Ning，LI Ruiping，ZHANG Weihua. Modeling and simulation of catenary based on negative sag method [J]. Journal of Traffic and Transportation Engineering，2009，9(4)：28-32.
[17] 关金发，吴积钦. 受电弓与接触网动态仿真模型建立及其确认[J]. 铁道科学与工程学报，2017，14(11)：2444-2451. GUAN Jinfa，WU Jiqin. Building and confirmation for dynamic simulation model of pantograph and catenary [J]. Journal of Railway Science and Engineering，2017，14(11)：2444-2451.
[18] YONG H C. Numerical simulation of the dynamic responses of railway overhead contact lines to a moving pantograph，considering a nonlinear dropper[J]. Journal of Sound & Vibration，2008，315(3)：433-454.
[19] European Committee for Electrotechnical Standardization. Railway applications-current collection systems-technical criteria for the interaction between pantograph and overhead line，BS EN 50367-2012[S]. Brussels：British Standards Institution，2012.
[20] European Committee for Electrotechnical Standardization. Railway applications-current collection system-validation of simulation of the dynamic interaction between pantograph and overhead contact line，BS EN 50318-2002[S]. Brussels：British Standards Institution，2002.
[21] 胡艳，黄盼盼，马然. 京津线弓网动态仿真模型的建立及验证[J]. 机械设计，2020，37(1)：84-88. HU Yan，HUANG Panpan，MA Ran. Building and validation of the dynamic simulation model for the pantograph-catenary system of the Beijing-Tianjin high-speed railway[J]. Journal of Machine Design，2020，37(1)：84-88.
[22] 吉鹏霄. 接触网[M]. 北京：化学工业出版社，2006. JI Pengxiao. Catenary[M]. Beijing：Chemical Industry Press，2006.
[23] MING T，HE G，LI X，et al. Prediction of the effects of preparation conditions on pervaporation performances of polydimethylsiloxane(PDMS)/ceramic composite membranes by backpropagation neural network and genetic algorithm[J]. Separation & Purification Technology，2012，89：142-146.
[24] PARK D，CHA J，KIM M，et al. Multi-objective optimization and comparison of surrogate models for separation performances of cyclone separaror based on CFD，RSM，GMDH-neural network，back propagation- ANN and genetic algorithm[J]. Engineering applications of computational fluid mechanics，2020，14(1)：180-201.

基于BP神经网络和遗传算法的简单链型悬挂接触网结构优化

Structural Optimization of Simple Catenary Based on BP Neural Network and Genetic Algorithm

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	石琴, 蒋正信, 刘翼闻, 魏宇江, 胡晓松, 贺林. 基于分数阶模型的锂离子电池荷电状态估计[J]. 机械工程学报, 2024, 60(8): 224-232,244.
[2]	王跃飞, 王超, 许于涛, 孙睿, 肖锴, 王凯林. 边-云协同下智能制造单元作业的数字孪生任务调度方法[J]. 机械工程学报, 2024, 60(6): 137-152.
[3]	王俊玖, 刘金玉, 侯秀娟, 齐振国, 李志敏, 刘涛. 列车车体柔性装配精度预测的力学-数据混合建模方法[J]. 机械工程学报, 2024, 60(6): 177-186.
[4]	秦涛, 李运华, 范茹军. 强力摇臂矿用液压挖掘机自主挖掘轨迹优化[J]. 机械工程学报, 2024, 60(18): 374-384.
[5]	刘承尚, 陈锐, 李芳, 王萌, 徐戊矫. 基于改进遗传算法的超高强钢硬化模型参数确定及折弯回弹预测[J]. 机械工程学报, 2024, 60(12): 240-249.
[6]	田志强, 姜兴宇, 杨国哲, 刘伟军, 索英祁, 陈克强, 邢飞. 一种面向航天复杂构件的柔性作业车间能耗优化调度问题研究[J]. 机械工程学报, 2023, 59(8): 273-287.
[7]	刘浩, 陈正颖, 沈楷, 熊旭辉. 基于AC转角变化最小的五轴FDM熔覆路径的法矢量优化技术[J]. 机械工程学报, 2023, 59(6): 272-284.
[8]	苏进展, 李旭东, 尹逊民, 贾海涛, 郭芳. 人字齿轮直线型对角修形设计及成形磨原理[J]. 机械工程学报, 2023, 59(5): 121-129.
[9]	吴宏宇, 牛文栋, 张玉玲, 王树新, 阎绍泽. 水下滑翔机多点探测能耗最低路径的规划方法[J]. 机械工程学报, 2023, 59(5): 156-166.
[10]	董海江, 郑婷婷, 于进涛, 付正家, 刘秀成, 邢智翔, 闫正祥, 何存富. 汽车B柱加强板软硬部过渡特性的磁巴克豪森噪声检测方法[J]. 机械工程学报, 2023, 59(4): 10-17.
[11]	李昆鹏, 刘腾博, 李文莉. 改进自适应遗传算法求解“货到人”拣选系统订单分批问题[J]. 机械工程学报, 2023, 59(4): 308-317.
[12]	李贝贝, 孙深圳, 刘秀梅, 刘启航, 刘申, 赵巧, 贺杰. 基于改进SVM算法的调节阀空化状态识别[J]. 机械工程学报, 2023, 59(24): 312-322.
[13]	娄维达, 秦国华, 王华敏, 吴竹溪. 基于复化Cotes积分和神经网络的稳定铣削工艺参数多目标优化方法[J]. 机械工程学报, 2023, 59(17): 279-290.
[14]	郭鑫, 王海涵, 王杰, 张凯, 赵武. 韧性产品交互式概念设计与知识推理方法研究[J]. 机械工程学报, 2023, 59(11): 74-83.
[15]	孙树栋, 周新民, 常昇博. 含私有信息的多代理作业车间协商调度算法[J]. 机械工程学报, 2022, 58(9): 210-217.