智能车辆巡航建模与硬件在环试验

采用软计算方法设计了智能车辆巡航的神经网络-模糊控制模型。模型采用两输入、单输出方式，两输入分别为车间距离和两车相对车速，单输出为油门量或者刹车量。为了获取模型训练和仿真的数据，设计了车辆跟随试验，试验采用GPS和蓝牙无线通信模块来实时获得两车间的相对距离和相对车速。利用试验数据对CANFIS（collective adaptive neuro-fuzzy inference system）模型进行离线训练，建立了巡航车间距离模型。根据建立的模型设计了控制器，并基于实时仿真平台DSPACE1103进行了硬件在环试验。仿真结果和试验结果对比表明，建立的模型具有一定的合理性，较好地体现了车辆系统的非线性特性。

Model of Intelligent Vehicle Cruise and Hardware-in-the-loop Test

Neuro-Fuzzy model of intelligent vehicle cruise was built in the way of soft computation. The model included two inputs and one output . The inputs were relative velocity and relative distance between the leading car and the following one, the output was the journey of gas pedal or brake pedal. To acquire data of training and simulaton, test of inter-vehicle following was carried out. Inter-vehicle distance and relative velocity were obtained by GPS and wireless bluetooth module. The CANFIS model was trained by experimental data and the vehicle- to- vehicle distance controller was designed. Fianally the hardware- in- the- loop test was made to validate the model. It makes it clear that the built model is rational between the simulation and test and indicates nonlinear feature of vehicle.