Application advances of artificial intelligence algorithms in dynamics simulation of railway vehicle
-
摘要: 梳理了人工智能算法在铁道车辆系统动力学仿真中的应用实例和国内外相关文献，概述了铁道车辆动力学仿真中常用的机器学习和深度学习算法，归纳和评述了2种学习算法在铁道车辆系统动力学建模与仿真中的应用分类；从铁道车辆系统动力学建模、动力学性能预测与动力学性能优化等方面入手，详细讨论了人工智能算法应用在力元建模和仿真、轨道不平顺预测、运行平稳性预测、噪声预测、侧风安全性预测、运行安全性预测、悬挂优化、轮轨匹配优化、结构优化以及主动与半主动控制等领域的优势和局限性，指出了现阶段人工智能算法在动力学仿真应用中主要面临的训练样本缺乏、泛化能力不够、可解释性欠缺等问题；展望了今后人工智能算法和车辆系统动力学交叉研究的发展方向和重点研究内容。研究结果表明：融合经典力学和人工智能算法结合的混合建模理论可作为之后的重点研究方向；人工智能算法对解决随机动力学中的随机不确定性，提高随机动力学的性能具有较大的应用潜力；通过人工智能算法与优化算法相结合来实现动力学性能优化，可充分发挥人工智能算法的优势。Abstract: The application examples and domestic and foreign literatures using artificial intelligence algorithm for railway vehicle system dynamics simulation were reviewed. The machine learning and deep learning algorithms commonly used in railway vehicle dynamics simulation were summarized, and the application classifications of the 2 algorithms in railway vehicle system dynamics modelling and simulation were concluded and interpreted. According to railway vehicle system dynamics modelling, dynamics performance prediction and dynamics performance optimization, the advantages and limitations of applying artificial intelligence algorithms in force-elements modelling and simulation, track irregularity prediction, running stability prediction, noise prediction, crosswind safety prediction, running safety prediction, suspension optimization, wheel-rail matching optimization, structure optimization, and active and semi-active control were discussed in detail. The problems of applications of artificial intelligence algorithms in railway dynamics simulation were lack of training samples, generalization ability and interpretability. The development directions and key research contents of the interdisciplinary research between artificial intelligence and vehicle system dynamics were given. Research result shows that the hybrid modelling theory combining classical mechanics and artificial intelligence algorithms can be as a key research direction in the future. There is great potential to use the artificial intelligence algorithms to solve the random uncertainty in stochastic dynamics and improve the performance of stochastic dynamics. The artificial intelligence algorithms combinated with optimization algorithms can exploit their advantages in the dynamics performance optimization. 5 tabs, 12 figs, 77 refs.
-
图 1 车辆系统动力学仿真的主要发展历程
Figure 1. Brief development history of vehicle system dynamics simulation
图 2 人工智能算法在动力学仿真中的应用
Figure 2. Applications of intelligent algorithms in vehicle dynamics simulation
表 1 车辆动力学仿真常用的人工智能算法
Table 1. Artificial intelligence algorithms used in vehicle dynamics simulation
算法 结构原理 优点 局限性 应用 文献 前向反馈神经网络 
具有较好的函数逼近能力 网络模型稳定性欠佳 复杂力元仿真、轮轨不平顺、动力学特性预测和主动控制 [54]、[75]、[76] 径向基神经网络 
优良的非线性逼近性能 结构庞大，复杂度增加，运算量增大 随机动力学仿真 [52] 支持向量基 
在小样本数据训练集上具有优势 对缺失数据较为敏感，参数调整复杂 轨道不平顺预测和评估 [60] 随机森林 
基于集成算法，精度高，支持并行 对噪声容忍度欠佳，强噪声条件下容易出现过拟合 数据驱动的力元建模 [48] Elman神经网络 
具有适应时变特性的能力 训练速度慢，易陷入局部最小点 脱轨系数的预测 [53] 循环神经网络 
较强的动态行为和计算能力 无法解决长时依赖的问题 脱轨系数的预测 [68] 非线性自回归神经网络 
具有序列学习能力 梯度消失或梯度爆炸 脱轨系数的预测，磨耗计算等 [61]、[64] 
下载: 导出CSV
表 2 人工智能算法在动力学建模中的应用
Table 2. Applications of artificial intelligence algorithms in dynamics modelling
应用场景 网络结构 网络类型 训练方法 输入 输出 用途 参考文献 液压减振器 前向反馈神经网络 前馈神经网络 梯度下降法 减振器位移和速度 减振器阻尼力 提高建模精度 [52] 轮轨 Elman循环神经网络 递归神经网络 梯度下降法 轮轨的垂直和横向轨的相对位移 轮轨力与脱轨系数 轮轨智能检测 [53] 循环神经网络 循环神经网络 列文伯格-马夸尔特法 垂向和横向曲率不规则变化 轮轨力 脱轨、舒适度预测 [54] 前向反馈神经网络 前馈神经网络 列文伯格-马夸尔特法 不平顺检测数据 应变 轮轨横向力测量 [55] 多层感知机神经网络 前馈神经网络 列文伯格-马夸尔特法 轮轨相对位置(位移矢量和旋转矩阵) 接触点位置 在线实时仿真 [56]、[57] 垂向动力学 径向基神经网络 前馈神经网络 列文伯格-马夸尔特法 悬架相对位移和速度 悬架力总和 提高计算效率 [58] 纵向动力学 随机森林 随机森林 套袋法 仿真得到的力-位移曲线 其他工况下力-位移曲线 多体动力学建模 [49] 卷积长短记忆生成神经网络 循环神经网络 梯度下降法 列车碰撞非线性特征参数 关键部件的刚度和阻尼特性参数 多体动力学建模 [59]
下载: 导出CSV
表 3 人工智能算法在轨道不平顺预测中的应用
Table 3. Applications of artificial intelligence algorithms in track irregularity prediction
下载: 导出CSV
表 4 人工智能算法在运行安全性中的应用
Table 4. Applications of artificial intelligence algorithms in operational safety
应用场景 网络结构 网络类型 训练方法 输入 输出 用途 参考文献 轮轨接触力、脱轨系数预测 Elman循环神经网络 递归神经网络 梯度下降法 时间序列(轮轨的垂向和横向位移) 轮轨力以及脱轨系数 轮轨智能检测 [53] 循环神经网络 循环神经网络 列文伯格-马夸尔特法 垂向和横向曲率不规则变化 轮轨相互作用力 评估动力学特性 [54] 运行平稳性预测 非线性自回归神经网络 循环神经网络 梯度下降法 2个设计参数和4个轨道不平顺参数 垂向和横向加速度响应 轮轨几何检测及评价 [64] 循环神经网络 循环神经网络 梯度下降法 21个轨道几何图形 垂直力和侧向力 轮轨力实时预测 [68] 轮轨磨耗计算 非线性自回归神经网络 循环神经网络 列文伯格-马夸尔特法 载荷、速度、轮轨轮廓线等 轮轨磨耗程度 预测维护与降低成本 [69]
下载: 导出CSV
表 5 人工智能算法在动力学控制与性能优化中的应用
Table 5. Applications of artificial intelligence algorithms in dynamics control and performance optimization
应用场景 网络结构 训练方法 输入 输出 用途 参考文献 悬挂优化 遗传算法+差分进化 梯度下降法 悬挂参数等29个设计变量 平稳性、减载率等46个响应 优化动力学性能 [70] 轮轨匹配优化 人工神经网络+遗传算法 梯度下降法 需优化的点 磨损量 减少磨耗 [71] 结构优化 人工神经网络+遗传算法 梯度下降法 尺寸比和材料 破碎参数 性能优化 [72] 主动控制 BP神经网络 列文伯格-马夸尔特法 悬挂力 振动位移响应 提高动力学性能 [73] BP神经网络 列文伯格-马夸尔特法 悬挂控制力 振动加速度响应 提高稳定性 [74]、[75] 半主动控制 BP神经网络 梯度下降法 悬挂力 振动加速度响应 提高横向稳定性 [76] 非线性自回归模型 列文伯格-马夸尔特法 位移、速度 阻尼力 非线性仿真 [77]
下载: 导出CSV
-
[1] AHMED A K W, SANKAR S. Lateral stability behavior of railway freight car system with elasto-damper coupled wheelset: part 1—wheelset model[J]. Journal of Mechanisms, Transmissions, and Automation in Design, 1987, 109(4): 493-499. doi: 10.1115/1.3258827 [2] WICKENS A H. Static and dynamic stability of unsymmetric two-axle railway vehicles possessing perfect steering[J]. Vehicle System Dynamics, 1982, 11(2): 89-106. doi: 10.1080/00423118208968691 [3] LEE S, CHENG Y. Influences of the vertical and the roll motions of frames on the hunting stability of trucks moving on curved tracks[J]. Journal of Sound and Vibration, 2006, 294(3): 441-453. doi: 10.1016/j.jsv.2005.10.025 [4] LEE S, CHENG Y. Hunting stability analysis of high-speed railway vehicle trucks on tangent tracks[J]. Journal of Sound and Vibration, 2005, 282(3-5): 881-898. doi: 10.1016/j.jsv.2004.03.050 [5] LEE S Y, CHENG Y C. Nonlinear analysis on hunting stability for high-speed railway vehicle trucks on curved tracks[J]. Journal of Vibration and Acoustics, 2005, 127(4): 324-333. doi: 10.1115/1.1924640 [6] FAN Yang-tsai, WU Wen-fang. Stability analysis and derailment evaluation of rail vehicles[J]. International Journal of Heavy Vehicle Systems, 2006, 13(3): 194-211. doi: 10.1504/IJHVS.2006.010018 [7] KIM P, JUNG J, SEOK J. A parametric dynamic study on hunting stability of full dual-bogie railway vehicle[J]. International Journal of Precision Engineering and Manufacturing, 2011, 12(3): 505-519. doi: 10.1007/s12541-011-0064-1 [8] SEZER S, ATALAY A E. Application of fuzzy logic based control algorithms on a railway vehicle considering random track irregularities[J]. Journal of Vibration and Control, 2011, 18(8): 1177-1198. http://www.ingentaconnect.com/content/sageus/10775463/2012/00000018/00000008/art00010 [9] SAYYAADI H, SHOKOUHI N. A new model in rail-vehicles dynamics considering nonlinear suspension components behavior[J]. International Journal of Mechanical Sciences, 2009, 51(3): 222-232. doi: 10.1016/j.ijmecsci.2009.01.003 [10] 倪纯双, 贺启庸, 洪嘉振. 铁路车辆多体动力学综述[J]. 中国铁道科学, 1996, 17(4): 1-11. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTK604.000.htmNI Chun-shuang, HE Qi-yong, HONG Jia-zhen. Review of railway multibody dynamic systems[J]. China Railway Science, 1996, 17(4): 1-11. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTK604.000.htm [11] 翟婉明. 车辆-轨道垂向系统的统一模型及其耦合动力学原理[J]. 铁道学报, 1992, 14(3): 10-21. doi: 10.3321/j.issn:1001-8360.1992.03.002ZHAI Wan-ming. The vertical model of vehicle-track system and its coupling dynamics[J]. Journal of the China Railway Society, 1992, 14(3): 10-21. (in Chinese) doi: 10.3321/j.issn:1001-8360.1992.03.002 [12] 梁波, 蔡英, 朱东生. 车-路垂向耦合系统的动力分析[J]. 铁道学报, 2000, 22(5): 65-71. doi: 10.3321/j.issn:1001-8360.2000.05.015LIANG Bo, CAI Ying, ZHU Dong-sheng. Dynamic analysis on vehicle-subgrade model of vertical coupled system[J]. Journal of the China Railway Society, 2000, 22(5): 65-71. (in Chinese) doi: 10.3321/j.issn:1001-8360.2000.05.015 [13] 陈果, 翟婉明, 左洪福. 车辆-轨道耦合系统随机振动响应特性分析[J]. 交通运输工程学报, 2001, 1(1): 13-16. doi: 10.3321/j.issn:1671-1637.2001.01.003CHEN Guo, ZHAI Wan-ming, ZUO Hong-fu. Analysis of the random vibration responses characteristics of the vehicle-track coupling system[J]. Journal of Traffic and Transportation Engineering, 2001, 1(1): 13-16. (in Chinese) doi: 10.3321/j.issn:1671-1637.2001.01.003 [14] 苏谦, 蔡英. 高速铁路路基结构空间时变系统耦合动力分析[J]. 西南交通大学学报, 2001, 36(5): 509-513. doi: 10.3969/j.issn.0258-2724.2001.05.014SU Qian, CAI Ying. A spatial time-varying coupling model for dynamic analysis of high speed railway subgrade[J]. The Journal of Social Sciences of Southwest Jiaotong University, 2001, 36(5): 509-513. (in Chinese) doi: 10.3969/j.issn.0258-2724.2001.05.014 [15] 翟婉明, 任尊松. 提速列车与道岔的垂向相互作用研究[J]. 铁道学报, 1998, 20(3): 33-38. doi: 10.3321/j.issn:1001-8360.1998.03.006ZHAI Wan-ming, REN Zun-song. An investigation on vertical interactions between speed-raising trains and turnouts[J]. Journal of the China Railway Society, 1998, 20(3): 33-38. (in Chinese) doi: 10.3321/j.issn:1001-8360.1998.03.006 [16] 翟婉明, 韩卫军, 蔡成标, 等. 高速铁路板式轨道动力特性研究[J]. 铁道学报, 1999, 21(6): 65-69. doi: 10.3321/j.issn:1001-8360.1999.06.016ZHAI Wan-ming, HAN Wei-dong, CAI Cheng-biao, et al. Dynamic properties of high speed railway slab tracks[J], Journal of the China Railway Society, 1999, 21(6): 65-69. (in Chinese) doi: 10.3321/j.issn:1001-8360.1999.06.016 [17] 蔡成标, 翟婉明, 王其昌. 高速列车与高架桥上无碴轨道相互作用研究[J]. 铁道工程学报, 2000(3): 29-32. doi: 10.3969/j.issn.1006-2106.2000.03.008CAI Cheng-biao, ZHAI Wan-ming, WANG Qi-chang. Research on vertical interactions between high-speed train and ballastless track on bridge[J]. Journal of Railway Engineering Society, 2000(3): 29-32. (in Chinese) doi: 10.3969/j.issn.1006-2106.2000.03.008 [18] 张敏, 范屹立, 马卫华, 等. 滑差频率对磁浮车辆运行性能的影响[J]. 交通运输工程学报, 2019, 19(5): 64-73. doi: 10.3969/j.issn.1671-1637.2019.05.008ZHANG Min, FAN Yi-li, MA Wei-hua, et al. Influence of slip frequency on running performance of maglev vehicle[J]. Journal of Traffic and Transportation Engineering, 2019, 19(5): 64-73. (in Chinese) doi: 10.3969/j.issn.1671-1637.2019.05.008 [19] 翟婉明. 车辆-轨道耦合动力学[M]. 北京: 科学出版社, 2015.ZHAI Wan-ming. Vehicle-Track Coupling Dynamics[M]. Beijing: Science Press, 2015. (in Chinese) [20] RIPKE B, KNOTHE K. Simulation of high frequency vehicle-track interactions[J]. Vehicle System Dynamics, 1995, 24(S1): 72-85. [21] OSCARSSON J, DAHLBERG T. Dynamic train/track/ballast interaction-computer models and full-scale experiments[J]. Vehicle System Dynamics, 1998, 29(S1): 73-84. doi: 10.1080/00423119808969553 [22] 于梦阁, 李海庆, 刘加利, 等. 强风雨环境下高速列车空气动力学性能研究[J]. 机械工程学报, 2020, 56(4): 185-192. https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB202004023.htmYU Meng-ge, LI Hai-qing, LIU Jia-li, et al. Study on the aerodynamic performance of the high-speed train under strong wind and railfall environment[J]. Chinese Journal of Mechanical Engineering, 2020, 56(4): 185-192. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB202004023.htm [23] 于梦阁, 李田, 张骞, 等. 强降雨环境下高速列车空气动力学性能[J]. 交通运输工程学报, 2019, 19(5): 96-105. doi: 10.3969/j.issn.1671-1637.2019.05.011YU Meng-ge, LI Tian, ZHANG Qian, et al. Aerodynamic performance of high-speed train under heavy rain condition[J]. Journal of Traffic and Transportation Engineering, 2019, 19(5): 96-105. (in Chinese) doi: 10.3969/j.issn.1671-1637.2019.05.011 [24] 于梦阁, 张继业, 张卫华. 侧风下高速列车车体与轮对的运行姿态[J]. 交通运输工程学报, 2011, 11(4): 48-55. http://transport.chd.edu.cn/oa/DArticle.aspx?type=view&id=201104008YU Meng-ge, ZHANG Ji-ye, ZHANG Wei-hua. Running attitudes of car body and wheelset for high-speed train under cross wind[J]. Journal of Traffic and Transportation Engineering, 2011, 11(4): 48-55. (in Chinese) http://transport.chd.edu.cn/oa/DArticle.aspx?type=view&id=201104008 [25] 成楠. 侧风作用下的高速列车空气动力学研究[D]. 成都: 西南交通大学, 2017.CHENG Nan. Study on aerodynamic characteristics of a high speed train under cross wind[D]. Chengdu: Southwest Jiaotong University, 2017. (in Chinese) [26] 李雪冰, 侯传伦, 张曙光, 等. 高速列车交会时的风致振动研究[J]. 振动与冲击, 2009, 28(7): 81-84. doi: 10.3969/j.issn.1000-3835.2009.07.017LI Xue-bing, HOU Chuan-lun, ZHANG Shu-guang, et al. Flow-induced vibration of high-speed trains in passing events[J]. Journal of Vibration and Shock, 2009, 28(7): 81-84. (in Chinese) doi: 10.3969/j.issn.1000-3835.2009.07.017 [27] 李雪冰, 张继业, 张卫华. 高速列车交会时气流诱发振动的仿真研究[J]. 铁道车辆, 2009, 47(12): 9-12. doi: 10.3969/j.issn.1002-7602.2009.12.003LI Xue-bing, ZHANG Ji-ye, ZHANG Wei-hua. Simulation research on vibration caused by airflow while high speed trains passing each other[J]. Rolling Stock, 2009, 47(12): 9-12. (in Chinese) doi: 10.3969/j.issn.1002-7602.2009.12.003 [28] 田红旗. 列车交会空气压力波研究及应用[J]. 铁道科学与工程学报, 2004, 1(1): 83-89. doi: 10.3969/j.issn.1672-7029.2004.01.015TIAN Hong-qi. Research and applications of air pressure pulse from trains passing each other[J]. Journal of Railway Science and Engineering, 2004, 1(1): 83-89. (in Chinese) doi: 10.3969/j.issn.1672-7029.2004.01.015 [29] 田红旗, 许平, 梁习锋, 等. 列车交会压力波与运行速度的关系[J]. 中国铁道科学, 2006, 27(6): 64-67. doi: 10.3321/j.issn:1001-4632.2006.06.013TIAN Hong-qi, XU Ping, LIANG Xi-feng, et al. Correlation between pressure wave of train passing and running speed[J]. Journal of Railway Science and Engineering, 2006, 27(6): 64-67. (in Chinese) doi: 10.3321/j.issn:1001-4632.2006.06.013 [30] 王英学, 高波, 骆建军, 等. 高速列车进入隧道空气动力学模型实验分析[J]. 空气动力学学报, 2004, 22(3): 346-351. doi: 10.3969/j.issn.0258-1825.2004.03.019WANG Ying-xue, GAO Bo, LUO Jian-jun, et al. Model experiment and numeral simulation of the aerodynamics character of high-speed train entering tunnel[J]. Acta Aerodynamica Sinica, 2004, 22(3): 346-351. (in Chinese) doi: 10.3969/j.issn.0258-1825.2004.03.019 [31] 万晓燕, 吴剑. 时速200 km动车组通过隧道时空气动力学效应现场试验与研究[J]. 现代隧道技术, 2006, 43(1): 43-48. doi: 10.3969/j.issn.1009-6582.2006.01.008WAN Xiao-yan, WU Jian. In-situ test and study on the aerodynamic effect of the rolling stock passing through tunnels with a speed of 200 km/h[J]. Modern Tunnelling Technology, 2006, 43(1): 43-48. (in Chinese) doi: 10.3969/j.issn.1009-6582.2006.01.008 [32] 骆建军, 姬海东. 高速列车进入有缓冲结构隧道的压力变化研究[J]. 铁道学报, 2011, 33(9): 114-118. doi: 10.3969/j.issn.1001-8360.2011.09.020LUO Jian-jun, JI Hai-dong. Study on changes of pressure waves induced by a high-speed train entering into a tunnel with hood[J]. Journal of the China Railway Society, 2011, 33(9): 114-118. (in Chinese) doi: 10.3969/j.issn.1001-8360.2011.09.020 [33] 赵晶, 李人宪. 高速列车进入隧道的气动作用数值模拟[J]. 西南交通大学学报, 2009, 44(1): 96-100. doi: 10.3969/j.issn.0258-2724.2009.01.018ZHAO Jing, LI Ren-xian. Numerical analysis of aerodynamics of high-speed trains running into tunnels[J]. Journal of Southwest Jiaotong University, 2009, 44(1): 96-100. (in Chinese) doi: 10.3969/j.issn.0258-2724.2009.01.018 [34] 刘凤华, 余以正. 地铁列车隧道气动力学试验与仿真[J]. 大连交通大学学报, 2013, 34(4): 7-11. doi: 10.3969/j.issn.1673-9590.2013.04.002LIU Feng-hua, YU Yi-zheng. Comparison of subway train tunnel aerodynamic test and simulation analysis[J]. Journal of Dalian Jiaotong University, 2013, 34(4): 7-11. (in Chinese) doi: 10.3969/j.issn.1673-9590.2013.04.002 [35] 田红旗, 梁习锋, 许平. 列车空气动力性能研究及外形、结构设计方法[J]. 中国铁道科学, 2002, 23(5): 138-141. doi: 10.3321/j.issn:1001-4632.2002.05.027TIAN Hong-qi, LIANG Xi-feng, XU Ping. Research on the aerodynamic performance of train and its configuration and structure design method[J]. China Railway Science, 2002, 23(5): 138-141. (in Chinese) doi: 10.3321/j.issn:1001-4632.2002.05.027 [36] 梁习锋, 张健. 工业造型和空气动力学在流线型列车外形设计中的应用[J]. 铁道车辆, 2002, 40(7): 5-7. doi: 10.3969/j.issn.1002-7602.2002.07.002LIANG Xi-feng, ZHANG Jian. Application of industrial visual design and aerodynamics in streamlined train contour design[J]. Rolling Stock, 2002, 40(7): 5-7. (in Chinese) doi: 10.3969/j.issn.1002-7602.2002.07.002 [37] 罗洁, 张继业. 高速列车气动性能研究及结构优化设计[C]//中国力学学会. 第十届全国动力学与控制学术会议. 北京: 中国力学学会, 2016: 224-225.LUO Jie, ZHANG Ji-ye. High-speed train aerodynamic performance research and structural optimization design[C]//Chinese Society of Theoretical and Applied Mechanics. 10th National Symposium on Dynamics and Control. Beijing: Chinese Society of Theoretical and Applied Mechanics, 2016: 224-225. (in Chinese) [38] SHEN Z Y, HEDRICK J K, ELKINS J A. A comparison of alternative creep force models for rail vehicle dynamic analysis[J]. Vehicle System Dynamics, 1983, 12(1-3): 79-83. doi: 10.1080/00423118308968725 [39] 张卫华, 张曙光. 高速列车耦合大系统动力学及服役模拟[J]. 西南交通大学学报, 2008, 43(2): 147-152. doi: 10.3969/j.issn.0258-2724.2008.02.001ZHANG Wei-hua, ZHANG Shu-guang. Dynamics and service simulation for general coupling system of high-speed trains[J]. Journal of Southwest Jiaotong University, 2008, 43(2): 147-152. (in Chinese) doi: 10.3969/j.issn.0258-2724.2008.02.001 [40] 沈志云. 论我国高速铁路技术创新发展的优势[J]. 中国科学, 2012, 57(8): 594-599. https://www.cnki.com.cn/Article/CJFDTOTAL-KXTB201208002.htmSHEN Zhi-yun. The superiorities in innovatively developing high-speed train technology in China[J]. Science China, 2012, 57(8): 594-599. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-KXTB201208002.htm [41] 聂宁, 官科, 钟章队. 德国铁路4.0战略[J]. 中国铁路, 2017(5): 86-90. https://www.cnki.com.cn/Article/CJFDTOTAL-TLZG201705018.htmNIE Ning, GUAN Ke, ZHONG Zhang-dui. German railway 4.0 strategy[J]. China Railway, 2017(5): 86-90. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-TLZG201705018.htm [42] 王同军. 中国智能高铁发展战略研究[J]. 中国铁路, 2019(1): 9-14. https://www.cnki.com.cn/Article/CJFDTOTAL-TLZG201901002.htmWANG Tong-jun. Study on the development strategy of China intelligent high speed railway[J]. China Railway, 2019(1): 9-14. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-TLZG201901002.htm [43] 王燕鹏, 韩涛, 王学昭. G20国家人工智能科技发展态势分析[J]. 科学观察, 2019, 14(1): 20-32. https://www.cnki.com.cn/Article/CJFDTOTAL-KCGC201901002.htmWANG Yan-peng, HAN Tao, WANG Xue-zhao. The development trend of artificial intelligence in the Group 20[J]. Science Focus, 2019, 14(1): 20-32. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-KCGC201901002.htm [44] 王万森. 人工智能原理及其应用(第4版)[M]. 北京: 电子工业出版社, 2018.WANG Wan-sen. Artificial Intelligence (AI) and Applications[M]. Beijing: Electronics Industry Publishing House, 2018. (in Chinese) [45] HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554. doi: 10.1162/neco.2006.18.7.1527 [46] ALPAYDIN E. Introduction to Machine Learning[M]. London: MIT Press, 2014. [47] HENNING H O, CHRISTOPH H, ROLF I. Vehicle dynamics based on hybrid simulation modeling[C]//IEEE. International Conference on Advanced Intelligent Mechatronics. New York: IEEE, 1999, 1014-1019. [48] NIE Yin-yu, TANG Zhao, LIU Feng-jia, et al. Data-driven dynamics simulation for railway vehicles[J]. Vehicle System Dynamics, 2018, 56(3): 406-427. doi: 10.1080/00423114.2017.1381981 [49] TANG Zhao, ZHU Yun-rui, NIE Yin-yu, et al. Data-driven train set crash dynamics simulation[J]. Vehicle System Dynamics, 2017, 55(2): 149-167. doi: 10.1080/00423114.2016.1249377 [50] YIM Y U, OH S Y. Modeling of vehicle dynamics from real vehicle measurements using a neural network with two-stage hybrid learning for accurate long-term prediction[J]. IEEE Transactions on Vehicular Technology, 2004, 53(4): 1076-1084. doi: 10.1109/TVT.2004.830145 [51] CHELI F, ROCCHI D, SCHITO P, et al. Neural network algorithm for evaluating wind velocity from pressure measurements performed on a train's surface[J]. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 2015, 230(3): 961-970. [52] KOGANEI R, SASAKI K, WATANABE N. Characteristic identification of oil dampers for railway vehicles using Neural Networks[J]. WIT Transactions on the Built Environment, 2008, 103: 725-733. http://www.researchgate.net/publication/271436134_Characteristic_identification_of_oil_dampers_for_railway_vehicles_using_Neural_Networks [53] IWNICKI S D, STOW J, PARKINSON H. Assessing railway vehicle derailment potential using neural networks[J]. Rail Technology Unit, 1999: 1-11. http://www.researchgate.net/publication/27398318_Assessing_railway_vehicle_derailment_potential_using_neural_networks [54] GUALANO L, IWNICKI S D, PONNAPALLI P V S, et al. Prediction of wheel-rail forces, derailment and passenger comfort using artificial neural networks[C]//ASER. EURNEX-ŽEL 2006, 14th International Symposium. Bratislava: ASER, 2006: 1-10. [55] URDA P, ACEITUNO J F, MUÑOZ S, et al. Artificial neural networks applied to the measurement of lateral wheel-rail contact force: A comparison with a harmonic cancellation method[J]. Mechanism and Machine Theory, 2020, 153: 1-18. [56] FALOMI S, MALVEZZI M, MELI E, et al. Determination of wheel-rail contact points: comparison between classical and neural network based procedures[J]. Meccanica, 2009, 44(6): 661-686. doi: 10.1007/s11012-009-9202-6 [57] FALOMI S, MALVEZZI M, MELI E. Multibody modeling of railway vehicles: innovative algorithms for the detection of wheel-rail contact points[J]. Wear, 2011, 271(1/2): 453-461. http://www.sciencedirect.com/science/article/pii/S004316481000373X [58] TAHERI M, AHMADIAN M. Machine learning from computer simulations with applications in rail vehicle dynamics[J]. Vehicle System Dynamics, 2016, 54(5): 653-666. doi: 10.1080/00423114.2016.1150497 [59] DONG Shao-di, TANG Zhao, YANG Xiao-song, et al. Nonlinear spring-mass-damper modeling and parameter estimation of train frontal crash using CLGAN model[J]. Shock and Vibration, 2020, 2020: 1-19. http://www.researchgate.net/publication/344006292_Nonlinear_Spring-Mass-Damper_Modeling_and_Parameter_Estimation_of_Train_Frontal_Crash_Using_CLGAN_Model [60] 彭丽宇, 张进川, 苟娟琼, 等. 基于BP神经网络的铁路轨道几何不平顺预测方法[J]. 铁道学报, 2018, 40(9): 154-158. doi: 10.3969/j.issn.1001-8360.2018.09.021PENG Li-yu, ZHANG Jin-chuan, GOU Juan-qiong, et al. Prediction method of railway track geometric irregularity based on bp neural network[J]. Journal of the China Railway Society, 2018, 40(9): 154-158. (in Chinese) doi: 10.3969/j.issn.1001-8360.2018.09.021 [61] LIU Song, PANG Xue-miao, JI Hai-yan, et al. Prediction of track irregularities using NARX neural network[C]//IEEE. 2010 Second Pacific-Asia Conference on Circuits, Communications and System (PACCS). New York: IEEE, 2010: 109-112. [62] 于瑶, 刘仍奎, 王福田. 基于支持向量机的轨道不平顺预测研究[J]. 铁道科学与工程学报, 2018, 15(7): 1671-1677. https://www.cnki.com.cn/Article/CJFDTOTAL-CSTD201807006.htmYU Yao, LIU Reng-kui, WANG Fu-tian. Prediction for track irregularity based on support vector machine[J]. Journal of Railway Science and Engineering, 2018, 15(7): 1671-1677. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-CSTD201807006.htm [63] 韩晋, 杨岳, 陈峰, 等. 基于非等时距加权灰色模型与神经网络的轨道不平顺预测[J]. 铁道学报, 2014, 36(1): 81-87. https://www.cnki.com.cn/Article/CJFDTOTAL-TDXB201401016.htmHAN Jin, YANG Xue, CHEN Feng, et al. Prediction of track irregularity based on non-equal interval weighted grey model and neural network[J]. Journal of the China Railway Society, 2014, 36(1): 81-87. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-TDXB201401016.htm [64] KRAFT S, CAUSSE J, MARTINEZ A. Black-box modelling of nonlinear railway vehicle dynamics for track geometry assessment using neural networks[J]. Vehicle System Dynamics, 2018, 57(9): 1241-1270. doi: 10.1080/00423114.2018.1497186 [65] ZHENG Shu-bin, ZHONG Qian-wen, CHAI Xiao-dong, et al. A novel prediction model for car body vibration acceleration based on correlation analysis and neural networks[J]. Journal of Advanced Transportation, 2018, 2018: 1-13. http://www.researchgate.net/publication/329969104_A_Novel_Prediction_Model_for_Car_Body_Vibration_Acceleration_Based_on_Correlation_Analysis_and_Neural_Networks [66] SHAFIULLAH G M, ALI A B M S, THOMPSON A, et al. Predicting vertical acceleration of railway wagons using regression algorithms[J]. IEEE Transactions on Intelligent Transportation Systems, 2010, 11(2): 290-299. doi: 10.1109/TITS.2010.2041057 [67] KUN Qian, JIE Liang, GAO Yin-han. The prediction of vibration and noise for the high-speed train based on neural network and boundary element method[J]. Journal of Vibroengineering, 2015, 17(8): 1-13. http://www.researchgate.net/publication/292816535_The_prediction_of_vibration_and_noise_for_the_high-speed_train_based_on_neural_network_and_boundary_element_method/download [68] TIMOTHY P, MARTIN K, ALI T. Using a multibody dynamic simulation code with neural network technology to predict railroad vehicle-track interaction performance in real time[C]//IEEE. 6th International Conference on Multibody Systems, Nonlinear Dynamics and Control. New York: IEEE, 2007: 1881-1891. [69] SHEBANI A, IWNICKI S. Prediction of wheel and rail wear under different contact conditions using artificial neural networks[J]. Wear, 2018, 406/407: 173-184. doi: 10.1016/j.wear.2018.01.007 [70] ZENG Yuan-chen, ZHANG Wei-hua, SONG Dong-li, et al. Response prediction of stochastic dynamics by neural networks: theory and application on railway vehicles[J]. Computing in Science and Engineering, 2019, 21(3): 18-30. doi: 10.1109/MCSE.2018.2882328 [71] KIM Y, PARK C, HWANG H. Design optimization for suspension system of high speed train using neural network[J]. JSME International Journal, 2003, 46(2): 727-734. doi: 10.1299/jsmec.46.727 [72] JIANG Han-wen, GAO Liang. Optimizing the rail profile for high-speed railways based on artificial neural network and genetic algorithm coupled method[J]. Sustainability, 2020, 12(2): 1-23. http://www.researchgate.net/publication/338652874_Optimizing_the_Rail_Profile_for_High-Speed_Railways_Based_on_Artificial_Neural_Network_and_Genetic_Algorithm_Coupled_Method [73] MARZBANRAD J, EBRAHIMI M R. Multi-objective optimization of aluminum hollow tubes for vehicle crash energy absorption using a genetic algorithm and neural networks[J]. Thin-Walled Structures, 2011, 49(12): 1605-1615. doi: 10.1016/j.tws.2011.08.009 [74] KUMAR P S, SIVAKUMAR K, KANAGARAJAN R, et al. Adaptive neuro fuzzy inference system control of active suspension system with actuator dynamics[J]. Journal of Vibroengineering, 2018, 20(1): 541-549. doi: 10.21595/jve.2017.18379 [75] CHOROMAŃSKI W. Application of neural network for intelligent wheelset and railway vehicle suspension designs[J]. Vehicle System Dynamics, 1996, 25(1): 87-98. doi: 10.1080/00423119608969189 [76] 丁问司, 卜继玲. 基于非线性神经网络的列车半主动悬挂系统[J]. 华南理工大学学报(自然科学版), 2005, 33(12): 75-77, 91. doi: 10.3321/j.issn:1000-565X.2005.12.017DING Wen-si, BU Ji-ling. Semi-active suspension system of train based on nonlinear neural networks[J]. Journal of South China University of Technology (Natural Science Edition), 2005, 33(12): 75-77, 91. (in Chinese) doi: 10.3321/j.issn:1000-565X.2005.12.017 [77] TUDÓN-MARTÍNEZ J C, LOZOYA-SANTOS J J, MORALES-MENENDEZ R, et al. An experimental artificial-neural-network-based modeling of magneto-rheological fluid dampers[J]. Smart Materials and Structures, 2012, 21(8): 1-16. http://www.ingentaconnect.com/content/iop/sms/2012/00000021/00000008/art085007 -
点击查看大图
图(12) / 表(5)
计量
- 文章访问数: 892
- HTML全文浏览量: 208
- PDF下载量: 423
- 被引次数: 0
