基于BP神经网络电动轮汽车行驶状态监测分析
|
摘要
行驶状态监测是电动轮汽车整车控制的基础,也是整车网略技术发展的基础。针对电动轮车辆行驶状态监测评估分析,设计分析系统,在此系统中实现了对总线数据的实时监控研究,总线的时间特性与占用率的评估,总线通信数据的存储。通过分析判定车辆行驶状态所需要的数据以及数据的测量方法,并且利用Matlab使用BP算法建立了BP神经元三层网络模型,预测出判定车辆行驶状态的参数,并与实际理论公式判定参数进行比较,结果表明相对误差在范围内,由此可见用BP神经元网络来实现判定车辆行驶状态参数的方法是可行的,可以作为设计使用的参考。
Driving condition monitoring is the basis of vehicle control of electric wheel car,and also the basis for the development of a slightly technical vehicle network. Aiming at evaluation and analysis of driving condition monitoring of electric wheel vehicles,the analysis system is designed. In this system to achieve a real-time monitoring of bus data,the time characteristics and occupancy of the bus,the storage of the bus communication data. By analyzing and judging the data required to determine the running status of the vehicle and the data measurement method,a BP neural network three-layer network model is established by using BP algorithm by Matlab,to predict the parameters for determining the running state of the vehicle and compared with the actual theoretical formula to determine parameters. The results show that the relative error in the range,we can see from the BP neural network to determine the vehicle driving state parameters of the method is feasible,can be used as a reference design.
Driving condition monitoring is the basis of vehicle control of electric wheel car,and also the basis for the development of a slightly technical vehicle network. Aiming at evaluation and analysis of driving condition monitoring of electric wheel vehicles,the analysis system is designed. In this system to achieve a real-time monitoring of bus data,the time characteristics and occupancy of the bus,the storage of the bus communication data. By analyzing and judging the data required to determine the running status of the vehicle and the data measurement method,a BP neural network three-layer network model is established by using BP algorithm by Matlab,to predict the parameters for determining the running state of the vehicle and compared with the actual theoretical formula to determine parameters. The results show that the relative error in the range,we can see from the BP neural network to determine the vehicle driving state parameters of the method is feasible,can be used as a reference design.
引文
[1]刘树伟,秦笃赫.基于BP神经网络的电动轮汽车驱动控制系统仿真研究[J].机械设计与制造,2016(12):31-34.(Liu Shu-wei,Qin Du-he.Electric wheel motor torque control system simulation research based on the BP neural network[J].Machinery Design&Manufacture,2016(12):31-34.)
[2]Rong Y J,Yang W,Niu H.Accurate estimation of SOC value of electric vehicle battery based on EKF algorithm optimized by BP neural network[J].Advanced Technology of Electrical Engineering&Energy,2015,66(7):1108-1121.
[3]Feng J P,Hang W X,Zhao L.Endurance mileage estimation of the state of charge for electric vehiclesm based on the fuzzy inference of artificial Neural network[J].International Journal of Advancements in Computing Technology,2013,5(1):540-548.
[4]Rimal B P,Shin H,Choi E.Simulation of nonlinear identification and control of unmanned aerial vehicle:an artificial neural network approach[J].Communications&Information Technology.iscit.international Symposium on,2009:442-447.
[5]Xie C,Zhao C,Dong D.Electric vehicle industry development environment evaluation in China based on BP neural network[J].International Journal of Simulation&Process Modelling,2014,9(4):234.
[6]李寿涛,田微,郭鹏程.基于模糊自适应的BP神经网络动态行驶车辆车长测算[J].吉林大学学报:工学版,2015,45(6):1881-1886.(Li Shou-tao,Tian Wei,Guo Peng-cheng.Dynamic traveling vehicle length measurement based on fuzzy adaptive of BP neural network[J].Journal of Jilin University:Engineering and Technology Edition,2015,45(6):1881-1886.)
[7]宁梓呈,郑玉航,王爱亮.基于PCA-GA-BP神经网络的状态评估算法[J].兵工自动化,2014(9):27-30.(Ning Zi-cheng,Zheng Yu-hang,Wang Ai-liang.Condition estimating algorithm based on PCA-GA-BP neural network[J].Ordnance Industry Automation,2014(9):27-30.)
[8]周帆,徐斌,杨世春.基于神经网络PID的电动汽车轮毂电机调速设计与仿真[J].车辆与动力技术,2015(2):53-57.(Zhou Fan,Xu Bin,Yang Shichun.Design and simulation of electric vehicle in-hub motor speed control based on neural network PID[J].Vehicle&Power Technology,2015(2):53-57.)
[9]谢娟烘.微型电动车新型行驶状态监控系统设计分析[J].机械设计与制造,2017(1):213-217.(Xie Juan-hong.Design and analysis of a new type of traveling information monitoring system in micro-electric vehicle[J].Machinery Design&Manufacture,2017(1):213-217.)
[10]张健伟,刘桂雄,潘梦鹞.基于智能传感的车轮运动状态监测系统设计[J].科学技术与工程,2011(18):4268-4272.(Zhang Jian-wei,Liu Gui-xiong,Pan Meng-ya.Design of movement state monitoring system of wheel based on intelligent sensor[J].Science Technology and Engineering,2011(18):4268-4272.)
[11]徐观,潘洪达,苏建.汽车曲线行驶状态轴距差检测及校准方法[J].吉林大学学报:工学版,2011(s2):118-121.(Xu Guan,Pan Hong-da,Su Jian.Research on wheelbase difference detection and calibration method for vehicle with curve driving status[J].Journal of Jilin University:Engineering and Technology Edition,2011(s2):118-121.)
[12]郭建龙,陈世元.电动车用多电机独立轮式驱动的协调运行分析[J].微特电机,2007,35(1):13-16.(Guo Jian-long,Chen Shi-yuan.Harmonious performing analysis for multiple-motors respective wheel-driving used electric vehicle[J].Small&Special Electrical Machines,2007,35(1):13-16.)
[2]Rong Y J,Yang W,Niu H.Accurate estimation of SOC value of electric vehicle battery based on EKF algorithm optimized by BP neural network[J].Advanced Technology of Electrical Engineering&Energy,2015,66(7):1108-1121.
[3]Feng J P,Hang W X,Zhao L.Endurance mileage estimation of the state of charge for electric vehiclesm based on the fuzzy inference of artificial Neural network[J].International Journal of Advancements in Computing Technology,2013,5(1):540-548.
[4]Rimal B P,Shin H,Choi E.Simulation of nonlinear identification and control of unmanned aerial vehicle:an artificial neural network approach[J].Communications&Information Technology.iscit.international Symposium on,2009:442-447.
[5]Xie C,Zhao C,Dong D.Electric vehicle industry development environment evaluation in China based on BP neural network[J].International Journal of Simulation&Process Modelling,2014,9(4):234.
[6]李寿涛,田微,郭鹏程.基于模糊自适应的BP神经网络动态行驶车辆车长测算[J].吉林大学学报:工学版,2015,45(6):1881-1886.(Li Shou-tao,Tian Wei,Guo Peng-cheng.Dynamic traveling vehicle length measurement based on fuzzy adaptive of BP neural network[J].Journal of Jilin University:Engineering and Technology Edition,2015,45(6):1881-1886.)
[7]宁梓呈,郑玉航,王爱亮.基于PCA-GA-BP神经网络的状态评估算法[J].兵工自动化,2014(9):27-30.(Ning Zi-cheng,Zheng Yu-hang,Wang Ai-liang.Condition estimating algorithm based on PCA-GA-BP neural network[J].Ordnance Industry Automation,2014(9):27-30.)
[8]周帆,徐斌,杨世春.基于神经网络PID的电动汽车轮毂电机调速设计与仿真[J].车辆与动力技术,2015(2):53-57.(Zhou Fan,Xu Bin,Yang Shichun.Design and simulation of electric vehicle in-hub motor speed control based on neural network PID[J].Vehicle&Power Technology,2015(2):53-57.)
[9]谢娟烘.微型电动车新型行驶状态监控系统设计分析[J].机械设计与制造,2017(1):213-217.(Xie Juan-hong.Design and analysis of a new type of traveling information monitoring system in micro-electric vehicle[J].Machinery Design&Manufacture,2017(1):213-217.)
[10]张健伟,刘桂雄,潘梦鹞.基于智能传感的车轮运动状态监测系统设计[J].科学技术与工程,2011(18):4268-4272.(Zhang Jian-wei,Liu Gui-xiong,Pan Meng-ya.Design of movement state monitoring system of wheel based on intelligent sensor[J].Science Technology and Engineering,2011(18):4268-4272.)
[11]徐观,潘洪达,苏建.汽车曲线行驶状态轴距差检测及校准方法[J].吉林大学学报:工学版,2011(s2):118-121.(Xu Guan,Pan Hong-da,Su Jian.Research on wheelbase difference detection and calibration method for vehicle with curve driving status[J].Journal of Jilin University:Engineering and Technology Edition,2011(s2):118-121.)
[12]郭建龙,陈世元.电动车用多电机独立轮式驱动的协调运行分析[J].微特电机,2007,35(1):13-16.(Guo Jian-long,Chen Shi-yuan.Harmonious performing analysis for multiple-motors respective wheel-driving used electric vehicle[J].Small&Special Electrical Machines,2007,35(1):13-16.)