矿用自卸车行驶路况恶劣，路面激励是平顺性研究中的重要因素。结合整车刚柔耦合模型，提出一种利用遗传算法优化的BP神经网络(GA-BP)辨识矿山路面不平度的方法，与标准BP网络相比预测能力得到极大提高，并通过整车道路试验验证了该方法辨识路面的准确性。通过与矿用自卸车常用C级、D级路面平顺性仿真结果对比显示，基于辨识路面的模型仿真精度提高了12.3%。在此基础上，以座椅垂直方向加速度均方根值为目标，将簧载质量和轮胎刚度阻尼作为不确定量，通过建立Kriging近似模型，运用多岛遗传算法对油气悬架和座椅结构参数进行不确定性优化，优化后目标值下降了37.4%，从而达到提高矿用自卸车平顺性能的目的。
Abstract
Aiming at harsh driving mining road,road surface excitation is an important factor in the research of mining dump truck ride comfort. Combined with rigid-flexible vehicle model ,this paper proposes that using BP neural network which is optimized by genetic algorithm to identify the mining road, prediction ability are improved greatly compared with standard BP network.The accuracy of the method is verified through vehicle road test. Compared with simulation results of ride comfort under common C-class and D-class roads, the model simulation accuracy based on identification road is increased by 12.3%. Through the establishment of Kriging approximation model,the structure parameters of hydro-pneumatic suspension and seat are optimized by multi-island genetic algorithm, which makes the root mean square value of the seat acceleration as optimization objective and makes the sprung mass and tire stiffness damping as uncertainties. After optimizing, the value is descended by 37.4%, which achieves the purpose of improving the ride comfort.
关键词
矿山路面 /
辨识 /
GA-BP神经网络 /
刚柔耦合模型 /
平顺性
{{custom_keyword}} /
Key words
Mining road /
Identification /
GA-BP neural network /
Rigid-flexible vehicle model /
Ride comfort
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 段虎明, 石峰, 谢飞, 等. 路面不平度研究综述[J]. 振动与冲击, 2009, 28(9): 95-101.
DUAN Hu-ming, SHI Feng, XIE fei, et al. A survey of road roughness study[J]. Journal of Vibration and Shock, 2009, 28(9): 95-101.
[2] Castelnovi M, Arkin R, Collins T R. Reactive speed control system based on terrain roughness detection[C]//Robotics and Automation, 2005. ICRA 2005. Proceedings of the 2005 IEEE International Conference on. IEEE, 2005: 891-896.
[3] 王 亚,陈思忠,郑凯锋.时空相关路面不平度时域模型仿真研究[J].振动与冲击,2013,32(5):70-74.
WANG Ya,CHEN Si-zhong,ZHENG Kai-feng.Simulation research on time domain model of road roughness with time-space correlation[J].Journal of Vibration and Shock,2013,32(5):70-74.
[4] 高建, 殷承良, 张勇, 等. 基于路面自动识别的 ABS 自适应神经模糊控制器仿真研究[J]. 汽车技术, 2006, 6: 4-7.
GAO Jian, YIN Cheng-liang, ZHANG Yong, et al.The simulation research of ABS self-adapting nerve fuzzy control unit base on road automatic identification[J]. Automobile Technology, 2006, 6: 4-7.
[5] Wang Q, McDaniel J G, Sun N X, et al. Road profile estimation of city roads using DTPS[C]//SPIE Smart Structures and Materials+ Nondestructive Evaluation and Health Monitoring. International Society for Optics and Photonics, 2013: 86923C-86923C-8.
[6] 韩建保, 张鲁滨, 李邦国. 轮胎路面附着系数实时感应识别系统[J]. 车辆与动力技术, 2005, 2: 62-64.
HAN Jian-bao, ZHANG Lu-bin, LI Bang-guo. Electronic sensing system for realTime identification of the tire-road adhesion[J]. Vehicle & Power Technology, 2005, 2: 62-64.
[7] Ngwangwa H M, Heyns P S, Labuschagne F J J, et al. Reconstruction of road defects and road roughness classification using vehicle responses with artificial neural networks simulation[J]. Journal of Terramechanics, 2010, 47(2): 97-111.
[8] Swart P L, Lacquet B M, Blom C. An acoustic sensor system for determination of macroscopic surface roughness[J]. Instrumentation and Measurement, IEEE Transactions on, 1996, 45(5): 879-884.
[9] 杨明亮, 徐格宁. 基于约束刚柔耦合系统的叉车振动研究[J]. 机械工程学报, 2011, 47(20): 89-94.
YANG Ming-liang, XU Ge-ning. Vibration study of fork-lift truck based on the constraint-rigid-flexible coupling System[J]. Journal of Mechanical Engineering, 2011, 47(20): 89-94.
[10] 宋桂霞. 汽车钢板弹簧柔性体建模与仿真研究[J]. 农业装备与车辆工程, 2011, 6: 008.
SONG Gui-xia. Flexible body modeling and simulation study on automobile leaf spring[J]. Agricultural Equipment & Vehicle Engineering, 2011, 6: 008.
[11] 陈建政, 林建辉. 在线连续测量轮轨接触点的神经网络方法[J]. 振动与冲击, 2007, 26(5): 90-92.
CHEN Jian-zheng, LIN Jian-hui.Online continuous measurement of rail wheel contact point based on neuro network method[J]. Journal of Vibration and Shock, 2007, 26(5): 90-92.
[12] 韩利芬, 高晖, 李光耀, 等. 神经网络与遗传算法在拉延筋参数反求中的应用[J]. 机械工程学报, 2005, 41(5): 171-176.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(2653 KB)
