轮毂电动汽车电子差速控制器设计研究
|
摘要
研究电动汽车的电子差速控制器,可有效的提高电动汽车行驶的稳定性,难点在于如何改进电动汽车的电子差速控制算法。针对经典的电子差速控制算法——BP神经网络算法收敛速度慢和易陷入局部最优解的缺陷,提出了PSO-BP神经网络的电子差速控制算法,并设计了基于该算法的电子差速控制模型。通过将采用BP神经网络算法和PSO-BP神经网络算法的电子差速控制结果进行比较,结果表明,利用PSO-BP神经网络算法解决了BP神经网络算法的固有缺陷,算法的收敛速度更快,电子差速模型的训练验证样本均方误差和转速的预测误差更小,优化了电动汽车的差速控制。
The study on electronic differential controller of electric vehicle can effectively improve the stability of electric vehicle. The difficulty is how to improve the electronic differential control algorithm of electric vehicle. Aiming at,the defects of the convergence speed and the local optimum solution of BP neural network algorithm,an electronic differential control algorithm for PSO-BP neural networks was proposed,and the electronic differential control model based on the algorithm was designed. The results of electronic differential control were compared with BP neural network algorithm and PSO-BP Neural network algorithm. The results show that the inherent defects of BP neural network algorithm are solved by using PSO-BP neural network algorithm,and the convergence speed of the algorithm is faster,the training of electronic differential model validates that the mean square error and the prediction error of rotational speed of sample are smaller. The differential control of EV is optimized.
The study on electronic differential controller of electric vehicle can effectively improve the stability of electric vehicle. The difficulty is how to improve the electronic differential control algorithm of electric vehicle. Aiming at,the defects of the convergence speed and the local optimum solution of BP neural network algorithm,an electronic differential control algorithm for PSO-BP neural networks was proposed,and the electronic differential control model based on the algorithm was designed. The results of electronic differential control were compared with BP neural network algorithm and PSO-BP Neural network algorithm. The results show that the inherent defects of BP neural network algorithm are solved by using PSO-BP neural network algorithm,and the convergence speed of the algorithm is faster,the training of electronic differential model validates that the mean square error and the prediction error of rotational speed of sample are smaller. The differential control of EV is optimized.
引文
[1]严运兵,彭思仑.后驱电动轮汽车电子差速控制影响因素分析[J].汽车工程,2014,36(2):210-215.
[2]段敏,等.后轮轮毂电机驱动电动汽车电子差速控制器研究[J].辽宁工业大学学报(自然科学版),2016,36(3):184-190.
[3] C G Lu,M S Xu,C Q Li. Research on the Electronic Differential Control Strategy of Electric Vehicle[J]. Advanced Materials Research,2013,712-715:2109-2112.
[4]朱绍鹏,等.两轮独立驱动电动汽车的驱动力控制策略研究[C]. 2013中国汽车工程学会年会论文集,2013,CN-EV105:299-303.
[5] Zhu C Q,Wu S,Yang Y Z. Research on Electronic Differential Speed Control for In-Wheel Motor Drive Electric Vehicle[J]. Applied Mechanics&Materials,2014,525:337-341.
[6]李绍杰.基于轮毂电机的电动车电子差速转向控制系统的研究[D].武汉理工大学,2009.
[7] H Pan,R S Song. The Control Strategy and Experimental Analysis of Electronic Differential Steering for Four Independent Drive Hub Motor Electric Vehicle[J]. Advanced Materials Research,2014,1030-1032:1550-1553.
[8] R Rajamani. Vehicle Dynamics and Control[M]. Springer US,2006.
[9] Y Zhong,B Ai,Z Y han. A PSO algorithm for multi-objective hull assembly line balancing using the stratified optimization strategy[J]. Computers&Industrial Engineering,2016,98:53-62.
[10] A Boucheham,M Batouche. Hybrid Wrapper/Filter Gene Selection Using an Ensemble of Classifiers and PSO Algorithm[J]. International Journal of Applied Metaheuristic Computing,2017-8.
[11] A Azimifar,S Payan. Optimization of characteristics of an array of thin fins using PSO algorithm in confined cavities heated from a side with free convection[J]. Applied Thermal Engineering,2016,110:1371-1388.
[12]魏津瑜,张玮,李欣.基于PSO-BP神经网络的高炉煤气柜位预测模型及应用[J].中南大学学报(自然科学版),2013,(s1):266-270.
[13]陈军. MSC. ADAMS技术与工程分析实例[M].北京:中国水利水电出版社,2008.
[14]张兴宇.轮毂式电动汽车电子差速系统的研究[D].武汉理工大学,2008.
[2]段敏,等.后轮轮毂电机驱动电动汽车电子差速控制器研究[J].辽宁工业大学学报(自然科学版),2016,36(3):184-190.
[3] C G Lu,M S Xu,C Q Li. Research on the Electronic Differential Control Strategy of Electric Vehicle[J]. Advanced Materials Research,2013,712-715:2109-2112.
[4]朱绍鹏,等.两轮独立驱动电动汽车的驱动力控制策略研究[C]. 2013中国汽车工程学会年会论文集,2013,CN-EV105:299-303.
[5] Zhu C Q,Wu S,Yang Y Z. Research on Electronic Differential Speed Control for In-Wheel Motor Drive Electric Vehicle[J]. Applied Mechanics&Materials,2014,525:337-341.
[6]李绍杰.基于轮毂电机的电动车电子差速转向控制系统的研究[D].武汉理工大学,2009.
[7] H Pan,R S Song. The Control Strategy and Experimental Analysis of Electronic Differential Steering for Four Independent Drive Hub Motor Electric Vehicle[J]. Advanced Materials Research,2014,1030-1032:1550-1553.
[8] R Rajamani. Vehicle Dynamics and Control[M]. Springer US,2006.
[9] Y Zhong,B Ai,Z Y han. A PSO algorithm for multi-objective hull assembly line balancing using the stratified optimization strategy[J]. Computers&Industrial Engineering,2016,98:53-62.
[10] A Boucheham,M Batouche. Hybrid Wrapper/Filter Gene Selection Using an Ensemble of Classifiers and PSO Algorithm[J]. International Journal of Applied Metaheuristic Computing,2017-8.
[11] A Azimifar,S Payan. Optimization of characteristics of an array of thin fins using PSO algorithm in confined cavities heated from a side with free convection[J]. Applied Thermal Engineering,2016,110:1371-1388.
[12]魏津瑜,张玮,李欣.基于PSO-BP神经网络的高炉煤气柜位预测模型及应用[J].中南大学学报(自然科学版),2013,(s1):266-270.
[13]陈军. MSC. ADAMS技术与工程分析实例[M].北京:中国水利水电出版社,2008.
[14]张兴宇.轮毂式电动汽车电子差速系统的研究[D].武汉理工大学,2008.