运行工况下车辆动态载荷预测方法研究

doi:10.3901/JME.2025.04.249

机械工程学报 ›› 2025, Vol. 61 ›› Issue (4): 249-261.doi: 10.3901/JME.2025.04.249

• 运载工程 • 上一篇

扫码分享

运行工况下车辆动态载荷预测方法研究

赵礼辉^1,2,3, 陈沛⁴, 王震¹, 张东东¹, 翁硕¹, 朱一光⁵

1. 上海理工大学机械工程学院上海 200093;
2. 机械工业汽车机械零部件强度与可靠性评价重点实验室上海 200093;
3. 上海市新能源汽车可靠性评价专业技术平台上海 200093;
4. 泛亚汽车技术中心有限公司上海 201201;
5. 上海蔚来汽车有限公司上海 201800

收稿日期:2024-02-27 修回日期:2024-09-06 发布日期:2025-04-14
作者简介:赵礼辉(通信作者)，男，1985年出生，博士，副教授，硕士研究生导师。主要研究方向为车辆可靠性设计与评价、车辆寿命评估与健康监测。E-mail：Pheigoe@126.com
陈沛，男，1998年出生。主要研究方向为车辆载荷特征分析与建模。E-mail：Pei1_Chen@patac.com.cn
王震，男，1997年出生，博士研究生。主要研究方向为车辆载荷预测与可靠性评价。E-mail：wangzhenares@yeah.net
基金资助:
国家重点研发计划(2018YFB0104802)、国家自然科学基金(51705322，52005336)和上海市扬帆计划(19YF1434400)资助项目。

Research on Prediction Method of Vehicle Dynamic Load Under Operating Conditions

ZHAO Lihui^1,2,3, CHEN Pei⁴, WANG Zhen¹, ZHANG Dongdong¹, WENG Shuo¹, ZHU Yiguang⁵

1. School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai 200093;
2. CMIF Key Laboratory for Strength and Reliability Evaluation of Automotive Structures, Shanghai 200093;
3. Platform for Reliability Evaluation of New Energy Vehicles in Shanghai, Shanghai 200093;
4. Pan Asia Technical Automotive Center Co., Ltd., Shanghai 201201;
5. NIO Nextev Co., Ltd., Shanghai 201800

Received:2024-02-27 Revised:2024-09-06 Published:2025-04-14

摘要/Abstract

摘要： 对车辆结构进行实时损伤预测及寿命评估需要各部件的动态载荷信息，然而基于试验方法以及传统时频域内的动载荷识别方法在识别精度、稳定性等方面存在一定的局限。提出一种车辆动态载荷预测方法，通过少量的输入信号，预测后桥、车架、板簧等主要失效风险部件动态载荷，为实现低成本的车辆损伤动态监测和寿命智能管理奠定基础。首先将实采信号经具有自适应噪声的完全集成经验模态分解-排列熵(Complete EEMD with adaptive noise-permutation entropy，CEEMDAN-PE)方式进行降噪处理，以降噪后的轮心加速度信号及位移信号作为输入，基于训练数据和独立测试数据调整超参数以建立最优架构非线性有源自回归(Nonlinear autoregressive models with exogenous inputs，NARX)神经网络模型来实时预测各零部件的应变载荷，进而实现零部件损伤快速计算，并从时域、频域、损伤域等多方面对预测结果进行评价。在此基础上，结合不同路况下的输入输出数据建立NARX-S单路况模型和NARX-M多路况统一模型，通过不同路况下多种模型的对比，表明NARX-S单路况模型具有更高的预测精度，而NARX-M预测精度略低，但具有较好的普遍适应性。

关键词: 动态载荷, 神经网络, 降噪处理, 载荷预测, 损伤计算

Abstract: Real-time damage prediction and life assessment of vehicle structures require dynamic load information of each component. However, the dynamic load identification method based on the test method and the traditional time-frequency domain has certain limitations in terms of identification accuracy and stability. A vehicle dynamic load prediction method is proposed. Through a small amount of input signals, the dynamic load of the main failure risk components such as rear axle, frame and leaf spring is predicted, which lays the foundation for the realization of low-cost dynamic monitoring of vehicle damage and intelligent life management. Firstly, the actual collected signal is subjected to noise reduction processing by CEEMDAN-PE method, and the denoised wheel center acceleration signal and displacement signal are used as input, and hyperparameters are adjusted based on training data and independent test data to establish the optimal architecture NARX neural network model. The strain load of each component is predicted in real time, and the component damage is calculated in real time, and the prediction results are evaluated from the time domain, frequency domain, damage domain and other aspects. On this basis, combining the input and output data under different road conditions to build the NARX-S single road condition model and the NARX-M multi-road condition unified model, the comparison of multiple models under different road conditions shows that the NARX-S single road condition model has higher prediction accuracy, while the NARX-M prediction accuracy is relatively lower, but has better general adaptability.

Key words: dynamic load, neural network, noise reduction processing, load prediction, damage calculation

中图分类号:

U461

赵礼辉, 陈沛, 王震, 张东东, 翁硕, 朱一光. 运行工况下车辆动态载荷预测方法研究[J]. 机械工程学报, 2025, 61(4): 249-261.

ZHAO Lihui, CHEN Pei, WANG Zhen, ZHANG Dongdong, WENG Shuo, ZHU Yiguang. Research on Prediction Method of Vehicle Dynamic Load Under Operating Conditions[J]. Journal of Mechanical Engineering, 2025, 61(4): 249-261.

参考文献

[1] 邱雨晴，王磊，王晓宇，等. 基于改进函数拟合法的冲击载荷识别研究[J]. 机械工程学报，2022，58(3):157-166. QIU Yuqing，WANG Lei，WANG Xiaoyu，et al. Research on impact force reconstruction based on improved function fitting method[J]. Journal of Mechanical Engineering，2022，58(3):157-166.
[2] 于佳伟，郑松林，冯金芝，等. 某轿车前副车架服役载荷模拟试验加速方法研究[J]. 机械工程学报，2016，52(22):112-120. YU Jiawei，ZHENG Songlin，FENG Jinzhi，et al. Research on accelerated testing method for the service-simulation fatigue test of automotive front sub-frame[J]. Journal of Mechanical Engineering，2016，52(22):112-120.
[3] 赵礼辉，王震，冯金芝，等. 基于用户大数据的电动汽车驱动系统可靠性试验循环工况构建方法[J]. 机械工程学报，2021，57(14):129-140. ZHAO Lihui，WANG Zhen，FENG Jinzhi，et al. Construction method for reliability test driving cycle of electric vehicle drive system based on users’ big data[J]. Journal of Mechanical Engineering，2021，57(14):129-140.
[4] 郑松林，郭正翔，冯金芝，等. 基于轴头垂向加速度响应的车轮载荷推断方法研究[J]. 机械强度，2016，38(6):1300-1305. ZHENG Songlin，GUO Zhengxiang，FENG Jinzhi，et al. The inference method of wheel load based on the acceleration of axle head[J]. Journal of Mechanical Strength，2016，38(6):1300-1305.
[5] 葛文韬，黄晖，刘洲，等. 一种加速多体动力学模型虚拟迭代的载荷谱编制方法[J]. 中国机械工程，2020，31(12):1504-1511. GE Wentao，HUANG Hui，LIU Zhou，et al. Load spectrum development methodology for accelerating dynamics model virtual iteration[J]. China Mechanical Engineering，2020，31(12):1504-1511.
[6] 董国疆，颜峰，韩杰，等. 车辆悬架零部件载荷谱提取方法研究[J]. 振动与冲击，2021，40(2):103-110. DONG Guojiang，YAN Feng，HAN Jie，et al. Load spectrum extraction method for automobile suspension components[J]. Journal of Vibration and Shock，2021，40(2):103-110.
[7] 葛文韬，刘洲，段龙杨，等. 四驱SUV车架动态载荷仿真及疲劳分析[J]. 机械强度，2019，41(6):1466-1472. GE Wentao，LIU Zhou，DUAN Longyang，et al. Dynamic load simulation of 4WD SUV and fatigue life analysis of frame[J]. Journal of Mechanical Strength，2019，41(6):1466-1472.
[8] DOYLE J F. A wavelet deconvolution method for impact force identification[J]. Experimental Mechanics，1997，37(4):403-408.
[9] KHOO S Y，ISMAIL Z，KONG K K，et al. Impact force identification with pseudo-inverse method on a lightweight structure for under-determined，even-determined and over-determined cases[J]. International Journal of Impact Engineering，2014，63:52-62.
[10] RIASAT A M，MUSTAFA G. Development of a novel damage detection framework for truss railway bridges using operational acceleration and strain response[J]. Vibration，2021，4(2):422-443.
[11] BUDERATH M，MCFEAT J，AZZAM H. The need for guidance on integrating structural health monitoring within military aircraft systems[J]. Structural Health Monitoring，2014，13(6):581-590.
[12] SUN Q，CHEN C，KEMP A H，et al. An on-board detection framework for polygon wear of railway wheel based on vibration acceleration of axle-box[J]. Mechanical Systems and Signal Processing，2021，153:107540.
[13] LIU H，SONG W，NIU Y，et al. A generalized Cauchy method for remaining useful life prediction of wind turbine gearboxes[J]. Mechanical Systems and Signal Processing，2021，153(6):107471.
[14] MOVSESSIAN A，GARCÍA CAVA D，TCHERNIAK D. An artificial neural network methodology for damage detection:Demonstration on an operating wind turbine blade[J]. Mechanical Systems and Signal Processing，2021，159:107766.
[15] WEIFANG S，BIN Y，NIANYIN Z，et al. An intelligent gear fault diagnosis methodology using a complex wavelet enhanced convolutional neural network[J]. Materials，2017，10(7):1-18.
[16] MOUSAVI M，GANDOMI A H. Prediction error of Johansen cointegration residuals for structural health monitoring[J]. Mechanical Systems and Signal Processing，2021，160:107847.
[17] ZHI C，TIE W，FENGSHOU G，et al. Characterizing the dynamic response of a chassis frame in a heavy-duty dump vehicle based on an improved stochastic system identification[J]. Shock and Vibration，2015，2015:1-15.
[18] 楼梦瑶，王旭阳，陈瑞，等. 基于NARX神经网络的船舶升沉运动实时预测方法[J]. 中国舰船研究，2020，15(1):48-55，67. LOU Mengyao，WANG Xuyang，CHEN Rui，et al. A real-time prediction method for ship heave motion using NARX neural network[J]. Chinese Journal of Ship Research，2020，15(1):48-55，67.
[19] YU B，SHU W，CAO C. A novel modeling method for aircraft engine using nonlinear autoregressive exogenous (NARX) models based on wavelet neural networks[J]. International Journal of Turbo & Jet-Engines，2018，35(2):161-169.
[20] 林聪，时岩. 基于非线性有源自回归神经网络的路面不平度识别[J]. 南京理工大学学报(自然科学版)，2020，44(3):296-302. LIN Cong，SHI Yan. Road roughness recognition based on NARX neural network[J]. Journal of Nanjing University of Science and Technology，2020，44(3):296-302.
[21] KLEINER J，STUCKENBERGER M，KOMSIYSKA L，et al. Real-time core temperature prediction of prismatic automotive lithium-ion battery cells based on artificial neural networks[J]. Journal of Energy Storage，2021，39:102588.
[22] 赵礼辉，李佳欣，井清，等. 关联用户的汽车试验场耐久性评价路况循环确定方法研究[J]. 汽车工程，2020，42(1):127-133. ZHAO Lihui，LI Jiaxin，JING Qing，et al. Research on the method of determining road condition cycles of durability test of correlated user automobile test field[J]. Automotive Engineering，2020，42(1):127-133.
[23] 于佳伟，钱春雷，郑松林，等. 基于小波变换理论的车辆实测载荷谱优化处理方法研究[J]. 汽车工程，2020，42(7):965-971. YU Jiawei，QIAN Chunlei，ZHENG Songlin，et al. Research on optimized processing method for vehicle load spectra measured based on wavelet transform theory[J]. Automotive Engineering，2020，42(7):965-971.
[24] BANDT C，POMPE B. Permutation entropy:A natural complexity measure for time series[J]. Physical Review Letters，2002，88(17):174102.
[25] 郑近德，程军圣，杨宇. 改进的EEMD算法及其应用研究[J]. 振动与冲击，2013，32(21):21-26. ZHENG Jinde，CHENG Junsheng，YANG Yu. Modified EEMD algorithm and its applications[J]. Journal of Vibration and Shock，2013，32(21):21-26.
[26] UGRAS R C，ALKAN O K，ORHAN S，et al. Real time high cycle fatigue estimation algorithm and load history monitoring for vehicles by the use of frequency domain methods[J]. Mechanical Systems and Signal Processing，2019，118:290-304.
[27] 李永利. 疲劳试验测试分析理论与实践[M]. 北京:国防工业出版社，2011. LI Yongli. Fatigue testing and analysis theory and practice[M]. Beijing:Defense Industry Press，2011.
[28] JOHANNESSON P，SPECKERT M. Guide to load analysis for durability in vehicle engineering[M]. New Jersey:John. Wiley & Sons. Inc.，2013.

运行工况下车辆动态载荷预测方法研究

Research on Prediction Method of Vehicle Dynamic Load Under Operating Conditions

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]	程英豪, 刘长青, 庄其扬, 李光旭, 郝小忠. 基于循环神经网络的切削力无传感器监测[J]. 机械工程学报, 2025, 61(6): 14-23.
[2]	程军, 朱煜龙, 汪步云, 梁艺, 许德章, 刘蒙蒙, 刘有余. 基于改进迁移学习的CFRP缺陷涡流检测与识别[J]. 机械工程学报, 2025, 61(6): 53-65.
[3]	邵东, 尹思维, 李亮, 王翔宇, 魏凌涛, 周道林. 基于神经网络的ESC线控制动压力估计与控制[J]. 机械工程学报, 2025, 61(4): 219-228.
[4]	陈国强, 申正义, 杨宇驰, 李腾, 徐丽. FCN优化GA的飞行模拟座舱意象仿生视觉焦点预测模型[J]. 机械工程学报, 2025, 61(3): 154-166.
[5]	刘翰儒, 陈桂映, 许泽林, 彭世通, 郭嘉楠, 刘伟嵬, 王奉涛. 基于SERepVGG-A2的轻量化卷积神经网络在熔池状态识别中的应用[J]. 机械工程学报, 2025, 61(3): 440-448.
[6]	杜冰, 万宇凡, 陈星池, 王绪辰. 基于ANN的不同材料统一起皱判定线的高效建立方法[J]. 机械工程学报, 2025, 61(2): 106-119.
[7]	徐向阳, 任博, 黄开胜, 贾涵杰, 朱才朝. 基于动态啮合力-油膜压力迭代耦合的人字行星齿轮接触疲劳寿命计算方法[J]. 机械工程学报, 2025, 61(1): 199-208.
[8]	郑杰, 权伟, 刘洋, 卢学民, 刘晓红, 岳雅楠, 周腾, 蔡振兵. Cr/Zr涂层环向压缩表面裂纹识别研究[J]. 机械工程学报, 2024, 60(8): 1-10.
[9]	刘占广, 张云, 刘晴雨. 基于差分融合长短期记忆神经网络数控机床热误差建模[J]. 机械工程学报, 2024, 60(7): 249-257.
[10]	狄子钧, 袁东风, 李东阳, 梁道君, 周晓天, 信苗苗, 曹凤, 雷腾飞. 基于多尺度-高效通道注意力网络的刀具故障诊断方法[J]. 机械工程学报, 2024, 60(6): 82-90.
[11]	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.
[12]	李春凯, 王嘉昕, 石玗, 代悦. GTAW熔池激光条纹动态行为与熔透预测方法研究[J]. 机械工程学报, 2024, 60(6): 236-244.
[13]	周宁, 姚建勇, 邓文翔. 基于神经网络的比例伺服阀阀芯液动力补偿鲁棒智能控制[J]. 机械工程学报, 2024, 60(4): 126-133.
[14]	王丹丹, 黄伟迪, 张军辉, 赵守军, 于斌, 刘施镐, 吕飞, 苏琦, 徐兵. 基于边缘计算的轴向柱塞泵磨损状态辨识方法研究[J]. 机械工程学报, 2024, 60(4): 189-199.
[15]	史丽晨, 史炜椿, 王海涛, 李金阳, 刘亚雄. 基于DRSN-BiLSTM模型的刀具磨损预测方法研究[J]. 机械工程学报, 2024, 60(24): 66-74.