Optimal Preview Control of Rear Suspension Using Nonlinear Neural Networks

SUMMARY

The performance of neural networks to be used for identification and optimal control of nonlinear vehicle suspensions is analyzed. It is shown that neuro-vehicle models can be efficiently trained to identify the dynamical characteristics of actual vehicle suspensions. After trained, this neuro-vehicle is used to train both front and rear suspension neuro-controllers under a nonlinear rear preview control scheme. To do that, a neuro-observer is trained to identify the inverse dynamics of the front suspension so that front road disturbances can be identified and used to improve the response of the rear suspension. The performance of the vehicle with neuro-control and with LQ control are compared.     

Optimal Preview Control of Rear Suspension Using Nonlinear Neural Networks

The performance of neural networks to be used for identification and optimal control of nonlinear vehicle suspensions is analyzed. It is shown that neuro-vehicle models can be efficiently trained to identify the dynamical characteristics of actual vehicle suspensions. After trained, this neuro-vehicle is used to train both front and rear suspension neuro-controllers under a nonlinear rear preview control scheme. To do that, a neuro-observer is trained to identify the inverse dynamics of the front suspension so that front road disturbances can be identified and used to improve the response of the rear suspension. The performance of the vehicle with neuro-control and with LQ control are compared.     

驾驶员方向控制模型圆弧式预瞄算法的研究

在传统的预瞄算法中,预瞄位置的确定需要大量坐标变换,影响运算速度;且通过线性插值计算预瞄点坐标和路径方向,会使预期路径方向在路径点处不连续,导致人-车-路闭环系统仿真出现振荡.为此,本文中提出一种无需坐标变换的圆弧预瞄位置确定算法,并通过三次埃尔米特插值实现对局部路径的光滑处理.仿真结果表明:该算法效果良好,运算速度较快;且采用三次埃尔米特插值代替线性插值,可有效缓解闭环系统仿真振荡.     

基于横向预瞄偏差的驾驶员前视轨迹控制模型

文章给出了横向预瞄偏差的概念，提出了一种基于横向预瞄偏差的驾驶员前视轨迹控制模型。通过计算机仿真，验证了该控制模型的正确性。该模型与现行的预瞄驾驶员模型相比，具有理解容易，分析计算简单，实用性强的优点。     

A Mathematical Model for Driver Steering Control, with Design, Tuning and Performance Results

A mathematical model for the steering control of an automobile is described. The structure of the model derives from linear optimal discrete time preview control theory but it is non-linear. Its parameter values are obtained by heuristic methods, using insight gained from the linear optimal control theory. The driver model is joined to a vehicle dynamics model and the path tracking performance is demonstrated, using moderate manoeuvring and racing speeds. The model is shown to be capable of excellent path following and to be robust against changes in the vehicle dynamics. Application to the simulation of manoeuvres specified by an ideal vehicle path and further development of the model to formalise the derivation of its parameter values and to put it to other uses are discussed.     

A Mathematical Model for Driver Steering Control,with Design,Tuning and Performance Results

A mathematical model for the steering control of an automobile is described. The structure of the model derives from linear optimal discrete time preview control theory but it is non-linear. Its parameter values are obtained by heuristic methods, using insight gained from the linear optimal control theory. The driver model is joined to a vehicle dynamics model and the path tracking performance is demonstrated, using moderate manoeuvring and racing speeds. The model is shown to be capable of excellent path following and to be robust against changes in the vehicle dynamics. Application to the simulation of manoeuvres specified by an ideal vehicle path and further development of the model to formalise the derivation of its parameter values and to put it to other uses are discussed.     

BP神经网络技术在斜拉桥施工控制中的应用

介绍了传统方法在斜拉桥施工控制中的局限性,提出了以BP神经网络技术为基础的施工控制方法.研究表明,人工神经网络方法在解决多影响因子复杂非线性问题方面具有显著的优势,在施工控制中具有广阔的应用前景.通过具体实例验证了该方法具有较强的可行性及可靠性.     

BP神经网络技术在斜拉桥施工控制中的应用

介绍了传统方法在斜拉桥施工控制中的局限性,提出了以BP神经网络技术为基础的施工控制方法.研究表明,人工神经网络方法在解决多影响因子复杂非线性问题方面具有显著的优势,在施工控制中具有广阔的应用前景.通过具体实例验证了该方法具有较强的可行性及可靠性.     

基于驾驶人转向意图的双电机驱动电动汽车稳定性控制策略

为了使双电机驱动电动车在车辆稳定性控制过程中能够精确解读驾驶意图,使车辆实际行驶状态与驾驶意图期望的车辆行驶状态尽可能相符合,提出一种基于驾驶人意图辨识的稳定性控制策略.利用基于支持向量机递归特征消除(SVM-RFE)得到的特征参数构建基于长短期记忆(LSTM)模型的驾驶人转向意图辨识模型;基于转向意图识别结果,以方向...     

驾驶员稳态预瞄动态校正假说

针对汽车运动学和动力学自身的特点及驾驶员对其的理解和认识，基于预瞄跟随理论和预测控制理论，在驾驶员行为建模中作出了汽车运动学和动力学特性的分隔处理，提出了驾驶员稳态预瞄动态校正假说，并结合仿真计算和驾驶模拟器实验论证了假说的合理性和有效性。     

基于轴距预瞄的半主动悬架模糊神经网络控制

应用模糊控制和神经网络控制理论,构建了1/2车辆的半主动悬架模型,设计了基于轴距预瞄的半主动悬架模糊神经网络控制系统.对前轮半主动悬架采用以对应处车身垂向加速度为目标的模糊控制,对后轮半主动悬架采用轴距预瞄模糊控制,并利用神经网络来调整模糊控制器的控制规则和隶属度函数.在不同车速下对所建的控制系统分别进行了白噪声和路面脉冲输入的仿真.结果表明,与传统的被动系统相比,轴距预瞄模糊神经网络控制的半主动悬架系统能有效降低车辆振动;与模糊控制的半主动悬架系统相比,质心垂向加速度和后轮对应处车身加速度均有显著减小,较好地改善了车辆的行驶平顺性.     

BP神经网络技术在斜拉桥施工控制中的应用

神经网络是一种模拟人脑结构和功能的信息处理系统。通过一工程实例,以BP神经网络技术为基础,对影响斜拉桥线形的各种参数（主梁混凝土弹性模量和容重）进行参数识别及主梁标高的预测。     

车辆转弯制动横向轨迹控制驾驶员模型研究

为了较为真实地反映车辆转弯制动工况,建立了含Pacejka"魔术公式"非线性联合工况轮胎模型的4轮8自由度车辆系统模型,并基于预瞄跟随理论、加速度反馈控制和模糊PID控制技术建立了车辆转弯制动横向轨迹控制驾驶员模型。针对不同初始速度和制动强度,利用MATLAB/Simulink进行了横向轨迹控制仿真分析。分析结果表明,驾驶员控制模型能很好地跟踪横向轨迹,模型的可行性和有效性得到验证,同时不同仿真条件下结果的一致性也说明该控制方法具有较强的自适应能力和鲁棒性,为进一步研究复杂工况下的驾驶员模型及横向轨迹控制提供了一条可行的途径。     

转向路感控制系统在汽车上的应用

本文介绍一种汽车电液主动转向路感控制系统,提出一种控制策略,通过估算车辆状态信息,分别在执行或不执行主动转向干预时,进行路感控制,保证行驶稳定性。     

自抗扰控制在前轮主动转向控制中的应用

为进一步提高前轮主动转向的性能,采用自抗扰控制算法来实现前轮主动转向控制.在对车辆动力学方程进行规范化的基础上,设计了二阶自抗扰控制算法.在双移线工况和对开路面加速工况下,对该算法的控制效果进行了硬件在环的仿真试验研究.结果表明,自抗扰控制算法能够有效地实现前轮主动转向控制,控制效果优于P1D控制,具有更高的抗扰动能力...     

三自由度四轮转向系统的神经网络模型研究

车辆四轮转向的数学模型随着自由度的增加其非线性迅速增加。对于多自由度车辆模型而言,准确而迅速地求解出目标变量的值是研究的难点。针对车辆的三自由度模型,建立了带反馈的神经网络模型,通过有导师训练改变网络的权值和阈值,在输入参数后可以准确而迅速地求解出目标值。仿真结果表明,该神经网络能够很好地逼近该三自由度数学模型。     

多层前向神经网络在电动转向系统中的应用

针对电动转向系统助力特性存在非线性的特点,应用多层前向神经网络,对电动转向系统全车速下的助力特性进行拟合。文中设计了多层前向神经网络结构,并采用基于综合目标函数的二阶学习算法对其进行离线学习,最后在电动转向综合试验台上实现在线控制。系统实现了全车速范围的非线性转向助力,克服了转向助力盲区。     

Preview of This Issue on “Driver Behavior and Traffic S fety”

This special issue is designed to deal with the researches on ＇kiriver behavior and traffic safety＂. Initiated by Journal of Transport Information and Safety, it is of significance in far reaching discussion about different driver characteristics, and management measures of driving behavior characteristics and their influence on traffic safety under different traffic environments. Scholars from famous academic organizations have been invited to submit papers and provide reviewing task for this special issue. A total of 33 papers have been recommended to publish in this issue, and the authors come from Tsinghua University, Tongji Univeristy, Beijing Jiaotong University, Beijing University of Technology, Wuhan University of Technology, Southeast University, Jilin Univeristy, Central South University, Beihang University, Chang＇an University, Shandong University of Technology, Tianjin University, Southwest Jiaotong University, Wuhan University of Science and Technology, Traffic Management Research Institute of the Ministry of Public Security, Research Institute of Highway of Ministry of Transport, etc. In the content reprinted below, this special issue consists of five main columns, including “Review of Driver Behavior and Traffic Safety”, “Individual Characteristic of Driver and Traffic Safety”, “ Driving Fatigue and Traffic Safety”, “Traffic System and Driving Behavior”,“Traffic Management and Driving Behavior”.     

变频调速系统在船闸电气控制系统中的应用

介绍以变频器-PLC为核心构成的变频调速系统的控制原理、系统硬件、接口组成及系统优点。分析变频器干扰产生的原因及抗干扰的一些措施。通过实例介绍变频调速技术在船闸电气控制系统中的应用。