目 次
液力缓速器恒速控制策略的仿真研究
陆中华 程秀生
(吉林大学)
【摘要】简述了液力缓速器工作原理,并给出了所研究液力缓速器台架试验得到的转子转速与制动扭矩之间关系曲线.利用Matlab软件建立了车辆恒速下坡制动模型,通过仿真对比了控制周期,充液量初始值和每个控制周期内充液量变化值等参数对恒速控制效果的影响.根据液力缓速器控制参数的仿真结果,选定各参数最佳值进行了实车道路试验.结果表明,仿真得到的恒速控制策略应用到实际控制中是有效的.
主题词:液力缓速器 恒速控制策略 仿真
Simulation Research on Constant Speed Control Strategy of Hydraulic Retarder
Lu Zhonghua, Cheng Xiusheng
(Jilin University)
【Abstract】Operating principle of hydraulic retarder is briefed in the paper, and the relationship curve is given between rotor speed and braking torque obtained from bench test of the hydraulic retarder. A braking model of the vehicle driving downgrade with constant speed is established with Matlab software, and then the effect of parameters like control cycle, initial liquid charge and variation of liquid charge in each control cycle, etc. on constant speed control effect is analyzed with simulation. Road test is carried out with the optimal parameters selected in accordance with the simulation results of the control parameters of the hydraulic retarder. The test results show that the constant speed control strategy is effective in actual control operation.
Key words: Hydraulic retarder;Constant speed control strategy;Simulation
基于支持向量机的夹紧力控制阀质量分类
高帅1 周云山2 安颖1 刘金刚2
(1. 吉林大学;2. 湖南大学 汽车车身先进制造国家重点实验室)
【摘要】提出了采用支持向量机对CVT夹紧力控制阀进行质量分类的方法,并设计了相应的提取夹紧力控制阀性能特征参数的试验方案与夹紧力控制阀SVM多类分类器.利用试验得到的性能参数对SVM分类器进行训练,然后分别使用训练成熟的SVM分类器与RBF神经网络分类器对夹紧力控制阀进行质量分类.结果表明,采用SVM分类器的分类准确率明显高于RBF神经网络分类器.
主题词:CVT 支持向量机 夹紧力控制阀 质量
Quality Classification of Clamping Force Control Valve based on Support Vector Machine
Gao Shuai1 Zhou Yunshan2 An Ying1 Liu Jingang2
(1. Jilin University; 2. State Key Laboratory of Advanced Design and Manufacture for Vehicle Body, Hunan University)
【Abstract】A method of quality classification on CVT clamping force control valve with support vector machine (SVM) was proposed. Firstly corresponding test plan for feature parameters extraction from clamping force control valve and the clamping force control valve SVM multi-class classifier were designed. Secondly, based on the feature parameters acquired from test, the SVM classifier was trained to maturity. Lastly, clamping force control valves were classified based on quality with SVM classifier and RBF neural network classifier respectively. Results showed that the accuracy of SVM classifier was better than RBF neural network classifier.

下一页