轮胎载荷是车辆设计和安全性评估的基础数据，对轮胎进行高精度的载荷识别具有重要意义。针对轮胎载荷直接测量昂贵，复杂的现状以及基于纯物理驱动与纯数据驱动的载荷识别方法的局限性，提出一种物理-数据联合驱动的载荷识别模型。该模型由卡尔曼滤波器与神经网络修正模型串行组成，卡尔曼滤波器对载荷进行初步识别，修正模型通过卷积神经网络和长短期记忆网络提取信号的空间和时间特征，预测卡尔曼滤波器的偏差并对识别结果予以修正。以APM300胶轮车辆为例进行载荷识别，结果表明，该串行模式载荷识别模型通过将物理驱动与数据驱动方法有机结合，综合整个系统的规则与经验，有效地克制了参数扰动的影响，提升了载荷识别精度，具有较强的泛化性能，具备一定的工程应用价值。
Abstract
Tire load is the basic data of vehicle design and safety evaluation. It is of great significance to identify tire load with high precision. In order to avoid the cost and complexity of direct measurement of tire load and the Limitations of load identification methods based on pure physical drive and pure data drive, A physical - data - driven load identification model is proposed. The model is composed of kalman filter and neural network correction model in series. Kalman filter is used to preliminarily identify the load，The modified model extracts the spatial and temporal characteristics of signals through the convolutional neural network and long and short term memory network, predicts the errors of kalman filter and corrects the recognition results. APM300 rubber wheel vehicle is taken as an example for load identification. The results show that the serial model can effectively restrain the influence of parameter perturbation and improve the identification accuracy of the model by organically combining physical drive and data drive methods and integrating the rules and experience of the whole system, and it has strong generalization performance and has certain engineering application value.
关键词
卡尔曼滤波器 /
卷积神经网络 /
长短期记忆网络 /
物理-数据联合驱动 /
轮胎载荷识别
{{custom_keyword}} /
Key words
Kalman filter /
Convolutional neural network /
Long Short-Term Memory /
Combined data-driven and physical-driven method /
Tire load identification
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 丁奕.车轮六分力计的测量原理与结构分析[J].时代汽车,2020(03):60-63.
DING Yi. Measuring principle and structure analysis of wheel six component dynamometer[J]. Auto Time, 2020(03):60-63.
[2] Law S S, Chan T H T, Zeng Q H. Moving force identification: a time domain method[J]. Journal of Sound and Vibration, 1997, 201(1): 1-22.
[3] Law S S, Fang Y L. Moving force identification: optimal state estimation approach[J]. Journal of Sound and Vibration, 2001, 239(2): 233-254.
[4] Yu L, Chan T H T. Moving force identification based on the frequency–time domain method[J]. Journal of Sound and Vibration, 2003, 261(2): 329-349.
[5] Baffet G, Charara A, D Herbomez G . An Observer of Tire–Road Forces and Friction for Active Security Vehicle Systems[J]. IEEE/ASME Transactions on Mechatronics, 2007, 12(6):651-661.
[6] Dakhlallah J, Glaser S, Mammar S, et al. Tire-road forces estimation using extended Kalman Filter and sideslip angle evaluation[C]// American Control Conference. IEEE, 2008.
[7] Li Y, Liu J, Wang K, et al. Continuous Measurement Method of Wheel/Rail Contact Force Based on Neural Network[C]// International Conference on Transportation Engineering. 2011.
[8] 张冉佳. 基于改进的BP神经网络对轮轨力测量技术的研究[D].北京交通大学,2015.
ZHANG Ranjia. Research on Measurement Technique of Wheel/rail Force Based on Improved BP Neural Network[D]. Beijing Jiaotong University, 2015.
[9] 罗金屯,滕飞,周亚波,池茂儒,张海波.数据驱动的高速铁路轮轨作用力反演模型[J]. 南京大学学报(自然科学),2021,57(02):299-308.
Luo Jintun, Teng Fei, ZHOU Yabo, et al. A wheel⁃rail force inversion model for high⁃speed railway[J]. Journal of Nanjing University(Natural Science), 2021,57(02):299-308.
[10] 胡健雄,汤奕,李峰,王琦,赵璇.电力系统中数据-物理融合模型的并联模式性能分析[J]. 电力系统自动化,2022,46(01):15-24.
HU Jianxiong, TANG Yi, LI Feng. Performance Analysis on Parallel Mode of Data- Physical Fusion Model in Power System. Automation of Electric Power Systems, 2022,46(01):15-24.
[11] 李峰,王琦,胡健雄,汤奕.数据与知识联合驱动方法研究进展及其在电力系统中应用展望[J]. 中国电机工程学报,2021,41(13):4377-4390.DOI:10.13334/j.0258-8013.pcsee.202468.
LI Feng, WANG Qi, HU Jianxiong. Combined Data-driven and Knowledge-driven Methodology Research Advances and its Applied Prospect in Power Systems[J]. Proceedings of the CSEE, 2021,41(13):4377-4390.DOI:10.13334/j.0258-8013.pcsee.202468.
[12] 任利惠,季元进,薛蔚. 单轴轮胎走行部APM车辆的动力学性能[J].同济大学学报(自然科学版),2015,43(02):280-285.
REN Lihui, JI Yuanjin, XUE Wei. Dynamics of Automatic Passenger Mover Vehicle with Single-axle Tire Running Gear[J]. Journal of Tongji University(Natural Science) , 2015,43(02):280-285.
[13] 刘豹, 唐万生. 现代控制理论(第三版)[M]. 北京: 机械工业出版社, 2006. LIU Bao, TANG Wansheng. Modern Control Theory (3rd edition)[M]. Beijing: China Machine Press, 2006.文
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(3355 KB)
