基于RBF-CLNSGA-II算法的转向架构架多目标优化
Multi-objective optimization of bogie frame based on RBF-CLNSGA-II algorithm
- 铁道科学与工程学报 2023年20卷第11期 页码：4311-4320
- 作者机构：
1.大连交通大学 机车车辆工程学院，辽宁 大连 116028
2.大连交通大学 机械工程学院，辽宁 大连 116028
- 作者简介：
李永华(1971—)，女，黑龙江青冈人，教授，博士，从事轨道车辆现代化设计、机械数字产品仿真与优化设计研究；E-mail：yonghuali@163.com
- 基金信息：国家自然科学基金资助项目(51875073)
DOI：10.19713/j.cnki.43-1423/u.T20230030
中图分类号：
扫 描 看 全 文
张东旭,李永华,白肖宁等.基于RBF-CLNSGA-II算法的转向架构架多目标优化[J].铁道科学与工程学报,2023,20(11):4311-4320.
ZHANG Dongxu,LI Yonghua,BAI Xiaoning,et al.Multi-objective optimization of bogie frame based on RBF-CLNSGA-II algorithm[J].Journal of Railway Science and Engineering,2023,20(11):4311-4320.
张东旭,李永华,白肖宁等.基于RBF-CLNSGA-II算法的转向架构架多目标优化[J].铁道科学与工程学报,2023,20(11):4311-4320. DOI： 10.19713/j.cnki.43-1423/u.T20230030.
ZHANG Dongxu,LI Yonghua,BAI Xiaoning,et al.Multi-objective optimization of bogie frame based on RBF-CLNSGA-II algorithm[J].Journal of Railway Science and Engineering,2023,20(11):4311-4320. DOI： 10.19713/j.cnki.43-1423/u.T20230030.
摘要
转向架构架是高速动车组的重要承载部件，对其关键结构精确分析及优化能保障列车安全平稳运行。为提高转向架构架设计优化的精度和效率，提出一种子模型技术与径向基函数-改进快速非支配排序遗传算法(RBF-CLNSGA-II)相结合的多目标优化方法。首先，通过分析转向架构架的结构强度，确定等效应力最大的位置，利用子模型技术对该区域构建子模型并进行相对灵敏度分析，然后构建其RBF神经网络，提高计算和拟合效率。其次，提出CLNSGA-II算法，通过引入Circle混沌映射、自适应交叉变异概率、Levy飞行策略及动态更新拥挤度比较算子，提高NSGA-II算法Pareto解集分布的均匀性和稳定性，同时增强全局搜索以及局部开发能力。最后，构建以结构相关参数为设计变量、最大等效应力和质量最小为目标、变量区间及材料屈服极限为约束的多目标优化模型，利用CLNSGA-II算法对基于子模型技术的RBF神经网络进行多目标优化，得到Pareto最优解。研究结果表明：子模型技术和RBF-CLNSGA-II算法相结合，不仅能够解决大型复杂结构拟合困难、运算周期长的问题，而且研究过程相比传统方法，针对性更强，求解精度更高，结果稳定性更好。优化后的构架子模型最大等效应力降低了4.603%，质量减少了2.922%，该方法对大型复杂部件的设计优化具有重要工程实用价值。
Abstract
Bogie frame is an important load-bearing part of high-speed EMU, accurate analysis and optimization of its key structure will ensure the safe operation. To improve the accuracy and efficiency of bogie frame design optimization, a multi-objective optimization method combining sub-model technique and radial basis function-improved fast non-dominated sorting genetic algorithm (RBF-CLNSGA-II) was proposed. Firstly, the structural strength analysis of the bogie frame was made to determine the location of the largest equivalent force. The sub-model was constructed and analyzed the relative sensitivity by the sub-model technique. The RBF neural network was constructed to improve the calculation and fitting efficiency. Secondly, the CLNSGA-II algorithm was proposed to improve the uniformity and stability of the Pareto solution set distribution by introducing Circle chaotic mapping, adaptive cross-variance probability, Levy flight strategy and dynamic update congestion comparison operator, while enhancing the global search as well as local exploitation capability. Finally, an optimization model with the relevant parameters of the structure as design variables, the maximum equivalent force and mass minimization as objectives, the variable intervals and material yield limits as constraints was constructed. Multi-objective optimization of RBF neural networks based on sub-model technique using CLNSGA-II algorithm to obtain Pareto optimal solutions. The research results show that the combination of sub-model technology and RBF-CLNSGA-II algorithm can not only simplify the fitting of large complex structures and shorten the operation cycle, but also the research process has stronger focus, higher solution accuracy and more stable results than traditional method. The maximum equivalent force of the optimized sub-model is reduced by 4.603% and the mass is reduced by 2.922%, and the method has important engineering practical value for the design optimization of large complex components.
关键词
转向架构架子模型技术径向基神经网络改进快速非支配排序遗传算法多目标优化
Keywords
bogie framesub-model techniqueradial basis function(RBF) neural networkcircle levy non-dominated sorting genetic algorithm-II(CLNSGA-II) algorithmmulti-objective robust optimization
references
智鹏鹏, 王悦东, 汪忠来, 等. 基于IDEPSO-SS的多工况转向架构架可靠性分析[J]. 中国铁道科学, 2021, 42(2): 134-143.
ZHI Pengpeng, WANG Yuedong, WANG Zhonglai, et al. IDEPSO-SS based reliability analysis of bogie frame under multiple load cases[J]. China Railway Science, 2021, 42(2): 134-143.
GAO Yuehua, LIU Qipeng, ZHAO Dan. Kriging surrogate model based optimisation of welded bogie frame for fatigue improvement[J]. International Journal of Vehicle Structures and Systems, 2020, 11(4): 349-354.
XING Bangsheng, ZHANG Jialu, XU Yongjie. Simulation and optimization design of CRH380A EMU bogie frame[J]. IOP Conference Series: Materials Science and Engineering, 2020, 790(1): 012117.
BAEK S, SONG Xueguan, KIM M, et al. Multiobjective optimization of beam structure for bogie frame considering fatigue-life extension[J]. Journal of Electrical Engineering & Technology, 2021, 16(3): 1709-1719.
SHAO Qing, XU Tao, YOSHINO T, et al. Optimization of the welding sequence and direction for the side beam of a bogie frame based on the discrete particle swarm algorithm[J]. Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 2018, 232(8): 1423-1435.
CETIN M H, ALVALI G T, KORKMAZ S. Parameter optimization with multi-criteria decision-making methods in rail transport: a case study of freight wagon bogie[J]. Arabian Journal for Science and Engineering, 2021, 46(10): 10059-10076.
ZHI Pengpeng, LI Yonghua, CHEN Bingzhi, et al. Bounds-based structure reliability analysis of bogie frame under variable load cases[J]. Engineering Failure Analysis, 2020, 114: 104541.
ZHANG Zifan, RU Changle, LI Qiang. Study on a novel field-measured load calibration method for the life assessment of the metro bogie frame[J]. Engineering Failure Analysis, 2022, 136: 106209.
卜康正, 赵勇, 郑先昌. 基于NSGA2遗传算法的地铁隧道上方基坑工程优化设计[J]. 铁道科学与工程学报, 2021, 18(2): 459-467.
BU Kangzheng, ZHAO Yong, ZHENG Xianchang. Optimization design for foundation pit above metro tunnel based on NSGA2 genetic algorithm[J]. Journal of Railway Science and Engineering, 2021, 18(2): 459-467.
ZHENG Xueqin, YAO Yiping. Multi-objective capacity allocation optimization method of photovoltaic EV charging station considering V2G[J]. Journal of Central South University, 2021, 28(2): 481-493.
杨红波, 史文库, 陈志勇, 等. 基于NSGA-Ⅱ的斜齿轮宏观参数多目标优化[J]. 吉林大学学报(工学版), 2023, 53(4): 1007-1018.
YANG Hongbo, SHI Wenku, CHEN Zhiyong, et al. Multi-objective optimization of macro parameters of helical gear based on NSGA-Ⅱ[J]. Journal of Jilin University (Engineering and Technology Edition), 2023, 53(4): 1007-1018.
HU Hongzhou, ZHONG Zhihua. Explicit-implicit co-simulation techniques for dynamic responses of a passenger car on arbitrary road surfaces[J]. Engineering, 2019, 5(6): 1171-1178.
SUN Yuantao, ZHAI Jinjin, ZHANG Qing, et al. Research of large scale mechanical structure crack growth method based on finite element parametric submodel[J]. Engineering Failure Analysis, 2019, 102: 226-236.
高磊, 刘振奎, 张昊宇. 基于混合PSO-RBF神经网络的铁路隧道岩爆分级预测[J]. 铁道科学与工程学报, 2021, 18(2): 450-458.
GAO Lei, LIU Zhenkui, ZHANG Haoyu. Prediction of rockburst classification of railway tunnel based on hybrid PSO-RBF neural network[J]. Journal of Railway Science and Engineering, 2021, 18(2): 450-458.
李永华, 盛自强, 宫琦. 基于GAPSO-RBFNN的动车组电机吊架多目标稳健优化设计[J]. 中国铁道科学, 2020, 41(3): 103-110.
LI Yonghua, SHENG Ziqiang, GONG Qi. GAPSO-RBFNN-based multi-objective robust optimal design for motor hanger of EMU[J]. China Railway Science, 2020, 41(3): 103-110.
李萌, 初建宇, 李印凤, 等. 基于航迹运行模式的航空器航迹优化模型[J]. 铁道科学与工程学报, 2022, 19(9): 2583-2591.
LI Meng, CHU Jianyu, LI Yinfeng, et al. Aircraft track optimization model based on track operation mode[J]. Journal of Railway Science and Engineering, 2022, 19(9): 2583-2591.
HERBADJI D, DEROUICHE N, BELMEGUENAI A, et al. A tweakable image encryption algorithm using an improved logistic chaotic map[J]. Traitement Du Signal, 2019, 36(5): 407-417.
BELAZI A, KHARBECH S, ASLAM M N, et al. Improved Sine-Tangent chaotic map with application in medical images encryption[J]. Journal of Information Security and Applications, 2022, 66: 103131.
张达敏, 徐航, 王依柔, 等. 嵌入Circle映射和逐维小孔成像反向学习的鲸鱼优化算法[J]. 控制与决策, 2021, 36(5): 1173-1180.
ZHANG Damin, XU Hang, WANG Yirou, et al. Whale optimization algorithm for embedded Circle mapping and onedimensional oppositional learning based small hole imaging[J]. Control and Decision, 2021, 36(5): 1173-1180.
章红梅, 胡帆, 段元锋. Bouc-Wen模型参数识别的非线性自适应遗传算法和试验验证[J]. 工程力学, 2022, 39(6): 191-201.
ZHANG Hongmei, HU Fan, DUAN Yuanfeng. A nonlinear adaptive genetic algorithm for parameter identification of the bouc-Wen model and its experimental verification[J]. Engineering Mechanics, 2022, 39(6): 191-201.
徐凯, 涂永超, 徐文轩, 等. 自适应多智能体算法优化深度网络的列车智能驾驶[J]. 铁道科学与工程学报, 2022, 19(10): 2820-2832.
XU Kai, TU Yongchao, XU Wenxuan, et al. Intelligent train operation based on adaptive multi-agent algorithm optimization for deep network[J]. Journal of Railway Science and Engineering, 2022, 19(10): 2820-2832.
邢致恺, 贾鹤鸣, 宋文龙. 基于莱维飞行樽海鞘群优化算法的多阈值图像分割[J]. 自动化学报, 2021, 47(2): 363-377.
XING Zhikai, JIA Heming, SONG Wenlong. Levy flight trajectory-based salp swarm algorithm for multilevel thresholding image segmentation[J]. Acta Automatica Sinica, 2021, 47(2): 363-377.
李文桦, 明梦君, 张涛, 等. 考虑全局和局部帕累托前沿的多模态多目标优化算法[J]. 自动化学报, 2023, 49(1): 148-160.
LI Wenhua, MING Mengjun, ZHANG Tao, et al. Multi-modal multi-objective optimization algorithm considering global and local Pareto frontier[J]. Acta Automatica Sinica, 2023, 49(1): 148-160.
JOO K H, KANG Y J. Relative sensitivity analysis of responses using transmissibility[J]. Journal of Sound and Vibration, 2017, 410: 87-102.
0
浏览量
1
下载量
0
CSCD
- 网络PDF下载
- XML下载
- Meta-XML下载
- BibTeX下载
- Endnote下载
- RefMan 下载
- NoteExpress下载
- NoteFirst下载
关联资源
相关文章
相关作者
相关机构
- 地址：长沙市韶山南路22号 邮编：410075
- 联系电话：0731-82656536 Email：jrse@csu.edu.cn
- 技术支持由北京北大方正电子有限公司提供 湘ICP备09001153号-13
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies