采用神经网络与模糊控制的制动需求识别

doi:10.3969/j.issn.1004-132X.2020.23.009

摘要/Abstract

摘要： 以保证车辆的制动安全性为最终目的，基于制动推杆行程传感器信号，利用神经网络算法与模糊控制算法提出了对制动需求进行识别的方法。首先采用神经网络算法与模糊控制算法完成对驾驶员制动需求的初步判断，然后通过主缸压力反馈信号对制动系统的制动动作完成程度进行预测，进而对制动需求识别结果进行持续反馈跟踪修正，以保证车辆的制动系统能够实现预期的制动效能。通过MATLAB/Simulink仿真试验与台架试验对控制算法进行了对比与验证，结果表明该方法能迅速准确地识别驾驶员的制动需求，从而为车辆的制动安全性提供保障。

关键词: 安全制动, 神经网络, 模糊控制, 制动力

Abstract: Aiming at ensuring the brake safety of vehicles, approaches for detecting driver brake requests weres investigated by applying neural network and fuzzy control. Firstly, neural network algorithm and fuzzy control algorithm were used to complete preliminary judgment of drivers braking demands. And then, completion degree of braking actions of the braking systems was predicted by feedback signals of the master cylinder pressure. Then the recognition results of braking demands were continuously fed back to track and modify in order to ensure the braking system of vehicles to achieve expected braking efficiency. The control algorithms were compared and validated by MATLAB/Simulink simulation tests and bench tests. The results show that the method may quickly and accurately identify the drivers braking demands and provide guarantee for vehicle braking safety.

Key words: safety braking, neural network, fuzzy control, braking force

中图分类号:

TH133.3

刘晏宇;喻凡;宋娟娟;庞纪苏;KAKU Chuyo. 采用神经网络与模糊控制的制动需求识别[J]. 中国机械工程, DOI: 10.3969/j.issn.1004-132X.2020.23.009.

LIU Yanyu;YU Fan;SONG Juanjuan;PANG Jisu;KAKU Chuyo. Detection of Brake Requests Using Neural Network and Fuzzy Control[J]. China Mechanical Engineering, DOI: 10.3969/j.issn.1004-132X.2020.23.009.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.cmemo.org.cn/CN/10.3969/j.issn.1004-132X.2020.23.009

http://www.cmemo.org.cn/CN/Y2020/V31/I23/2847

参考文献

［1］刘剑开，张向文.电动汽车再生制动过程制动踏板位移与制动意图及制动强度之间的关系［J］.科学技术与工程, 2018, 18(12):317-325.

LIU Jiankai, ZHANG Xiangwen. The Relationship between Bake Pedal Displacement and Braking Intention and Braking Strength in Regenerative Braking Process of Electric Vehicles［J］. Science and Technology and Engineering, 2018, 18(12):317-325.

［2］潘宁，于良耀，宋健. 考虑舒适性的电动汽车制动意图分类与识别方法［J］. 清华大学学报(自然科版), 2016, 56(10):1097- 1103.

PAN Ning, YU Liangyao, SONG Jian. Classification and Identification Method of Braking Intention for Electric Vehicles Considering Comfort［J］. Journal of Tsinghua University (Natural Science Edition), 2016, 56(10):1097-1103.

［3］朱昊，张豫南，张舒阳，等. 基于模糊控制的履带车辆分布式制动系统性能仿真［J］. 火力与指挥控制, 2018, 43(7):47-53.

ZHU Hao, ZHANG Yunan, ZHANG Shuyang, et al. Performance Simulation of Distributed Braking System for Tracked Vehicle Based on Fuzzy Control［J］. Firepower and Command Control, 2018, 43(7):47-53.

［4］张亚桥，程广伟，周志立，等. 基于驾驶员意图识别的微型纯电动货车控制策略［J］. 河南科技大学学报(自然科学版), 2018,39(5):21-27.

ZHANG Yaqiao, CHENG Guangwei, ZHOU Zhili, et al. Control Strategy of Miniature Pure Electric Truck Based on Driver Intention Recognition［J］. Journal of Henan University of Science and Technology(Natural Science Edition), 2018, 39(5):21-27.

［5］GAJRE M N, JEGADEESHWARAN R, SUGUMARAN V, et al. Vibration Based Fault Diagnosis of Automobile Hydraulic Brake System Using Fuzzy Logic with Best First Tree Rules［J］. International Journal of Vehicle Structures & Systems, 2016,8(4):214-218.

［6］RADHIKA R, APOORVA S, VIGNESH R, et al. Artificial Neural Network Approach for Air Brake Pushrod Stroke Prediction in Heavy Commercial Road Vehicles［J］. Proceedings of the Institution of Mechanical Engineers, 2019, 233(10):2467-2478.

［7］ALY A A. Intelligent Fuzzy Control for Antilock Brake System with Road-surfaces Identifier［C］//2010 International Conference on Mechatronics and Automation (ICMA). Xi’an,2010:699-705.

［8］王波，唐先智，王连东，等.基于EEMD和熵理论的电动汽车制动意图识别方法［J］. 汽车工程, 2018, 40(8):935-941.

WANG Bo, TANG Xianzhi, WANG Liandong, et al. Braking Intention Recognition Method for Electric Vehicles Based on EEMD and Entropy Theory［J］. Automotive Engineering, 2018, 40(8):935-941.

［9］曹佳, 徐潇源, 严正, 等. 几种高阶收敛的Levenberg- Marquardt方法在潮流计算中的应用［J］.电网技术, 2017, 41(4):1181-1187.

CAO Jia, XU Xiaoyuan, YAN Zheng, et al. Application of Several High-order Convergent Levenberg-Marquardt Methods in Power Flow Calculation［J］. Power Grid Technology, 2017, 41(4):1181-1187.

［10］王猛，孙泽昌，卓桂荣，等. 电动汽车制动能量回收系统研究［J］. 农业机械学报, 2012, 43(2):6-10.

WANG Meng, SUN Zechang, ZHUO Guirong, et al. Research on Braking Energy Recovery System for Electric Vehicles［J］. Journal of Agricultural Machinery, 2012, 43(2):6-10.

［11］吴志新，石金蓬，李亚伦，等. 基于制动边界与意图识别的再生制动策略［J］. 北京航空航天大学报, 2017, 43(8):1531-1540.

WU Zhixin, SHI Jinpeng, LI Yalun, et al. Regenerative Braking Strategy Based on Braking Boundary and Intention Recognition［J］. Journal of Beijing University of Aeronautics and Astronautics, 2017, 43(8):1531-1540.

［12］许世维，马建，汪贵平，等. 基于制动意图识别的增程式重型商用车复合制动控制策略［J］. 中国公路学报, 2017, 30(4):140-151.

XU Shiwei, MA Jian, WANG Guiping, et al. Compound Braking Control Strategy for Heavy Commercial Vehicles Based on Braking Intention Recognition［J］. Chinese Journal of Highway, 2017, 30(4):140-151.

［13］杨阳，邹佳航，杨洋，等. 混合动力汽车再生制动压力协调控制系统［J］. 机械工程学报, 2014, 50(22):127-135.

YANG Yang, ZOU Jiahang, YANG Yang, et al. Hybrid Electric Vehicle Regenerative Braking Pressure Coordination Control System［J］. Journal of Mechanical Engineering, 2014, 50(22):127-135.

［14］张俊智，吕辰，李禹橦，等. 电驱动乘用车制动能量回收技术发展现状与展望［J］. 汽车工程, 2014, 36(8):911-918.

ZHANG Junzhi, LYU Chen, LI Yutong, et al. Current Status and Prospects of Braking Energy Recovery Technology for Electrically Driven Passenger Cars［J］. Automotive Engineering, 2014, 36(8):911-918.

［15］刘杨，孙泽昌，邹小琼，等. 一体式电液复合制动系统制动意图解析及评价［J］. 华中科技大学学报(自然科学版), 2015, 43(12):32-36.

LIU Yang, SUN Zechang, ZOU Xiaoqiong, et al. Analysis and Evaluation of Braking Intention of Integrated Electro-hydraulic Composite Braking System［J］. Journal of Huazhong University of Science and Technology (Natural Science Edition), 2015, 43(12):32-36.

［16］初亮，杨毅，张世桐，等. 基于制动感觉的制动能量回收系统的设计与匹配［J］. 吉林大学学报(工学版), 2015, 45(4):1029- 1035.

CHU Liang, YANG Yi, ZHANG Shitong, et al. Design and Matching of Braking Energy Recovery System Based on Braking Sensation［J］. Journal of Jilin University (Engineering Edition), 2015, 45(4):1029-1035.

［17］王庆年，孙磊，唐先智，等. HEV制动意图识别的研究［J］. 汽车工程, 2013, 35(9):769-774.

WANG Qingnian, SUN Lei, TANG Xianzhi, et al. Research on HEV Braking Intention Recognition［J］. Automotive Engineering, 2013, 35(9):769-774.

［18］张元才，余卓平，徐乐，等. 基于制动意图的电动汽车复合制动系统制动力分配策略研究［J］. 汽车工程, 2009, 31(3):244- 249.

ZHANG Yuancai, YU Zhuoping, XU Le, et al. Research on Braking Force Distribution Strategy of Electric Vehicle Composite Braking System Based on Braking Intention［J］. Automotive Engineering, 2009, 31(3):244-249.

［19］王英范，宁国宝，余卓平. 乘用车驾驶员制动意图识别参数的选择［J］. 汽车工程, 2011, 33(3):213-216.

WANG Yingfan, NING Guobao, YU Zhuoping. Selection of Parameters for Identifying Braking Intention of Passenger Drivers［J］. Automotive Engineering, 2011, 33(3):213-216.

［20］汪震.电动货车驾驶意图识别及控制策略研究［D］.长春：吉林大学, 2015.

WANG Zhen. Research on Driving Intention Recognition and Control Strategy of Electric Truck［D］. Changchun:Jilin University, 2015.

［21］刘晏宇，喻凡，郭中陽.汽车制动助力系统研究进展综述［J］.汽车文摘，2019（4）:35-43.

[1]	李小力, 陈威, 闫蓉. 基于BP神经网络的空间轮廓误差自适应补偿 [J]. J4, 201016, 21(16): 1902-1906.
[2]	赵伟, 王志远, 周志立. 载重汽车连续下坡弯道路段制动稳定性仿真研究 [J]. J4, 201016, 21(16): 2010-2015.
[3]	谢阳, 戴逸群, 张超勇, 刘金锋. 融合集成模型与深度学习的机床能耗识别与预测方法[J]. 中国机械工程, 2023, 34(24): 2963-2974.
[4]	刘孝保, 严清秀, 易斌, 姚廷强, 顾文娟. 基于集成学习和改进粒子群优化算法的流程制造工艺参数优化[J]. 中国机械工程, 2023, 34(23): 2842-2853.
[5]	陈剑, 许畅, 徐庭亮, . 基于位错叠加法和改进概率神经网络的离心泵故障诊断方法[J]. 中国机械工程, 2023, 34(23): 2854-2861.
[6]	屈小章, 张加贝, 翟方志. 高速列车散热离心风机性能灵敏性分析及优化[J]. 中国机械工程, 2023, 34(20): 2504-2512.
[7]	徐美姣, 薛善良, 张惠, 周国庆, 卢红根. 基于BP-AdaBoost算法的复杂产品装配制造成熟度等级评估方法[J]. 中国机械工程, 2023, 34(20): 2513-2519.
[8]	张东, 刘啸奔, 孔天威, 杨悦, 武学健, 吴锴, 张宏. 高钢级管道焊缝材料应力应变本构关系确定方法[J]. 中国机械工程, 2023, 34(17): 2106-2114.
[9]	阴艳超, 施成娟, 邹朝普, 刘孝保. 基于深度时间卷积神经网络与迁移学习的流程制造工艺过程质量时序关联预测[J]. 中国机械工程, 2023, 34(14): 1659-1671.
[10]	贺青川, 刘慧, 潘骏, 陈文华. 基于电机运行状态的电静压伺服机构内泄漏检测方法[J]. 中国机械工程, 2023, 34(12): 1407-1414.
[11]	古玉锋, 杜雨洁, 王育阳, 李昆鹏, 黎程山. 基于神经网络与自调节卡尔曼滤波的超宽带定位算法研究[J]. 中国机械工程, 2023, 34(12): 1504-1511.
[12]	付翔, 王玉新, 刘道远, 王纪杰, . 基于越野工况辨识的轮毂电机车辆驱动力控制[J]. 中国机械工程, 2023, 34(08): 955-965.
[13]	郭文光, 王飞. 考虑热影响的永磁液冷缓速器制动力矩模型[J]. 中国机械工程, 2023, 34(06): 685-693.
[14]	张俊鑫, 陈威, 黄斯凯, 吴海彬. 基于力位混合导向的工业机器人顺槽运动控制策略[J]. 中国机械工程, 2023, 34(06): 712-719，726.
[15]	曾俊玮, 季元进, 任利惠, 葛方顺, 孙泽良, 黄章行. 融合一维卷积神经网络和双向门控循环单元的APM车辆轮胎径向载荷识别方法[J]. 中国机械工程, 2023, 34(03): 359-368.