基于前车速度预测的信号交叉口汽车生态驾驶控制策略

Vehicle eco-driving control strategy based on speed prediction of the front vehicle at the signalized intersection

为降低车辆通过信号交叉口的油耗和排放,研究车路协同环境下基于前车速度预测的信号交叉口汽车生态驾驶控制策略。通过转鼓试验修正目标车辆的VT-CPFM油耗模型和VSP排放模型,构建RBF神经网络模型对前车速度轨迹进行预测。以油耗为目标函数,排放为约束,创建基于动态规划的目标车辆速度优化算法,在MATLAB仿真得到目标车辆通过信号交叉口的优化速度诱导轨迹及油耗排放。仿真结果表明:加速优化诱导策略使得油耗、NO_(x)、CO、THC分别降低了27.3%、27.7%、32.9%、32.1%,减速优化诱导策略使得油耗、NO_(x)、CO、THC分别降低了25.1%、26.3%、32.6%、23.1%。在转鼓试验台进行实车试验,依据仿真计算得到的优化速度诱导轨迹测试目标车辆的油耗和排放。试验结果表明:加速优化诱导策略使得油耗、NO_(x)、CO、THC分别降低了21.4%、20.7%、22.4%、20.4%,减速优化诱导策略使得油耗、NO_(x)、CO、THC分别降低了20.1%、23.4%、30.9%、22.6%。

At signalized intersections,vehicles often stop and idle,accelerate and decelerate violently,which leads to the increase in fuel consumption and emissions.To reduce the fuel consumption and emissions of vehicles,this paper studies the vehicle ecological driving control strategy at the signalized intersection based on the speed prediction of the vehicles in front in the vehicle road collaborative environment.The VT-CPFM fuel consumption model and VSP emission model of the target vehicle are modified through the drum test,and the RBF neural network model is constructed to predict the speed trajectory of the front vehicles.Taking the fuel consumption as the objective function and the emission as the constraint,the target vehicle speed optimization algorithm based on dynamic programming is established.The optimal speed guidance trajectory and fuel consumption emission of the target vehicle passing through the signalized intersection are obtained by MATLAB simulation.The simulation results show that the acceleration optimization guidance strategy reduces fuel consumption,NO_(x),CO,THC by 27.3%,27.7%,32.9%,and 32.1% respectively,and the deceleration optimization guidance strategy reduces the fuel consumption,NO_(x),CO,THC by 25.1%,26.3%,32.6% and 23.1% respectively.Finally,a real vehicle test is carried out on the drum,and the fuel consumption and emission of the target vehicle are tested according to the optimized speed guidance trajectory obtained by simulation.The test results show that the acceleration optimization guidance strategy reduces fuel consumption,NO_(x),CO,THC by 21.4%,20.7%,22.4%,and 20.4% respectively,the deceleration optimization guidance strategy reduces the fuel consumption,NO_(x),CO,THC by 16.4%,23.4%,30.9%,and 16.1% respectively.Therefore,the vehicle ecological driving control strategy based on vehicle speed prediction at the signalized intersection in the vehicle-road collaborative environment can guide the target vehicle to pass through the signalized intersection,obviously reducing the energy-consumption and emissions.