基于GA-LSTM自适应卡尔曼滤波的路面不平度识别

摘要
图/表
参考文献(21)
相关文章 (0)

全文: PDF (4433 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要准确、快速地识别出车辆当前行驶的路面激励信息，是实现智能底盘控制进而保证车辆平顺性的关键。针对传统路面不平度识别算法准确率低、自适应性差等问题，提出了基于遗传算法(genetic algorithm，GA)优化长短期记忆神经网络(long short-term memory networks,LSTM)自适应卡尔曼滤波的路面不平度识别算法。基于2自由度车辆悬架模型，通过灰色关联法选择LSTM神经网络的特征输入变量，并采用GA优化LSTM神经网络的模型参数以准确识别路面等级，并据此实时更新卡尔曼滤波器算法中的噪声矩阵，实现了在复杂路况下对路面不平度的自适应识别。仿真和实验研究表明，所提出的基于GA-LSTM自适应卡尔曼滤波算法能够快速准确的识别路面不平度与路面等级，与传统卡尔曼滤波算法相比，相关系数、均方根误差和最大绝对误差分别提高3.11%、37.5%和51.2%，表明所提算法对复杂工况具有很好的自适应能力。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	李韶华1
	李健玮1
	2
	冯桂珍2

关键词 ：路面不平度识别, 自适应卡尔曼滤波器, GA-LSTM, 灰色关联法

Abstract：Accurately and rapidly identifying the current road excitation information of the vehicle is the key to realize the intelligent chassis control and ensure the ride comfort of the vehicle. Aiming at the problems of low accuracy and poor adaptability of traditional road roughness recognition algorithms, a road roughness recognition algorithm based on genetic algorithm(GA)optimized long short-term memory neural network(LSTM)adaptive Kalman filtering was proposed. Based on the two-degree-of-freedom vehicle suspension model, the feature input variables of the LSTM neural network were selected by the grey correlation method, and the model parameters of the LSTM neural network were optimized by GA to accurately identify the road grade. Based on this, the noise matrix in the Kalman filtering algorithm is updated in real time, and the adaptive recognition of road roughness under complex road conditions is realized. Simulation and experimental results show that the proposed adaptive Kalman filtering algorithm with GA-LSTM can quickly and accurately identify road roughness and road grade. Compared with the traditional Kalman filtering algorithm, The correlation coefficient, root mean square error and maximum absolute error are increased by 3.11 %, 37.5 % and 51.2 %, respectively, indicating that the proposed algorithm has good adaptability to complex working conditions.

Key words： road roughness identification adaptive Kalman filtering GA-LSTM grey relational analysis

收稿日期: 2023-07-04 出版日期: 2024-05-15

引用本文:

李韶华1，李健玮1,2，冯桂珍2. 基于GA-LSTM自适应卡尔曼滤波的路面不平度识别[J]. 振动与冲击, 2024, 43(9): 121-130.
LI Shaohua1, LI Jianwei1,2, FENG Guizhen2. Road roughness recognition based on GA-LSTM adaptive Kalman filtering. JOURNAL OF VIBRATION AND SHOCK, 2024, 43(9): 121-130.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2024/V43/I9/121

[1] 段虎明，石锋，赵永杰，等.道路路面的剖面曲线测量研究与实践[J]. 振动与冲击，2011, 30(03): 155-160. DUAN Hu-ming, SHI Feng, ZHAO Yong-jie, et al. Research and practice of road surface profile measurement [J]. Journal of Vibration and Shock, 2011, 30(3): 155-160. [2] Doumiati M, Martinez J, Sename O, et al. Road profile estimation using an adaptive Youla–Kučera parametric observer: Comparison to real profilers[J]. Control Engineering Practice, 2017, 61: 270-278. [3] Yang Z, Shi C, Zheng Y, et al. A study on a vehicle semi-active suspension control system based on road elevation identification[J]. PLoS one, 2022, 17(6): e0269406. [4] Ni T, Li W, Zhao D, et al. Road profile estimation using a 3D sensor and intelligent vehicle[J]. Sensors, 2020, 20(13): 3676. [5] 陈双，王丽佳.基于车辆振动响应反向分析的路面等级辨识方法[J]. 振动与冲击，2022, 41(17): 145-151+169. CHEN Shuang, WANG Li-jia. Pavement grade identification method based on reverse analysis of vehicle vibration response [J]. Journal of Vibration and Shock, 2022, 41(17): 145-151+169. [6] Wang R, Liu W, Ding R, et al. Switching control of semi-active suspension based on road profile estimation[J]. Vehicle system dynamics, 2022, 60(6): 1972-1992. [7] 李杰，郭文翠，赵旗，等.基于4种典型神经网络识别路面不平度的研究[J]. 汽车工程，2020, 42(01): 100-107. LI Jie, GUO Wen-cui, ZHAO Qi, et al. Study on road roughness identification based on four typical neural networks [J]. Automotive Engineering, 2020, 42(1): 100-107. [8] 梁冠群,赵通,王岩,等. 基于LSTM网络的路面不平度辨识方法[J]. 汽车工程，2021, 43(4): 509-517, +628. LIANG Guan-qun, ZHAO Tong, WANG Yan, et al. Road unevenness identification based on LSTM network [J]. Automotive Engineering, 2021, 43(4): 509-517, +628. [9] Liang G, Zhao T, Shangguan Z, et al. Experimental study of road identification by LSTM with application to adaptive suspension damping control[J]. Mechanical Systems and Signal Processing, 2022, 177: 109197. [10] 李以农，朱哲葳，郑玲，等. 基于路面识别的主动馈能悬架多目标控制与优化[J]. 交通运输工程学报，2021, 21(2): 129-137. LI Yi-nong, ZHU Zhe-wei, ZHENG Ling, et al. Multi-objective control and optimization of active energy-regenerative suspension based on road recognition [J]. Journal of Traffic and Transportation Engineering, 2021, 21(2): 129-137. [11] 寇发荣，贺嘉杰，李孟欣，等.基于路面识别的电磁混合式悬架自适应模糊控制[J]. 振动与冲击，2023, 42(02): 303-311. KOU Fa-rong, HE Jia-jie, LI Meng-xin, et al. Adaptive fuzzy control of an electromagnetic hybrid suspension based on road recognition [J]. Journal of Vibration and Shock, 2023, 42(02): 303-311. [12] Chen S, Xue J. Road Roughness Level Identification Based on BiGRU Network[J]. IEEE Access, 2022, 10: 32696-32705. [13] Im S J, Oh J S, Kim G W. Simultaneous Estimation of Unknown Road Roughness Input and Tire Normal Forces Based on a Long Short-Term Memory Model[J]. IEEE Access, 2022, 10: 16655-16669. [14] Yu W , Zhang X , Guo K ,et al. Adaptive Real-Time Estimation on Road Disturbances Properties Considering Load Variation via Vehicle Vertical Dynamics[J].Mathematical Problems in Engineering, 2013, 2013(4). [15] Yang H, Kim B G, Oh J S, et al. Simultaneous Estimation of Vehicle Mass and Unknown Road Roughness Based on Adaptive Extended Kalman Filtering of Suspension Systems[J]. Electronics, 2022, 11(16): 2544. [16] 刘浪，张志飞，鲁红伟，等.基于增广卡尔曼滤波并考虑车辆加速度的路面不平度识别[J]. 汽车工程，2022, 44(2): 247-255, +297. LIU Lang, ZHANG Zhi-fei, LU Hong-wei, et al. Road roughness identification based on augmented Kalman filtering with consideration of vehicle acceleration [J]. Automotive Engineering, 2022, 44(2): 247-255, +297. [17] Hamersma H A, Els P S. Vehicle suspension force and road profile prediction on undulating roads[J]. Vehicle system dynamics, 2021, 59(10): 1616-1642. [18] Xue K, Nagayama T, Zhao B. Road profile estimation and half-car model identification through the automated processing of smartphone data[J]. Mechanical Systems and Signal Processing, 2020, 142: 106722. [19] 殷珺，陈辛波，吴利鑫，等.滤波白噪声路面时域模拟方法与悬架性能仿真[J].同济大学学报(自然科学版)，2017, 45(03): 398-407. YIN Jun, CHEN Xin-bo, Wu Li-xin, et al. Simulation method of road excitation in time domain using filtered white noise and dynamic analysis of suspension [J]. Journal of Tongji University, 2017, 45(3): 399-406. [20] 刘豹,唐万生.现代控制理论[M].3版.北京：机械工业出版社，2006 LIU Bao, TANG Wansheng. Modern control theory[M]. 3rd ed. Beijing: China Machine Press, 2006 [21] Fauriat W, Mattrand C, Gayton N, et al. Estimation of road profile variability from measured vehicle responses[J]. Vehicle System Dynamics, 2016, 54(5): 585-605.