论文部分内容阅读
为提高跟车预警系统给出的结果的准确性和可靠性,利用毫米波雷达开展实际驾驶试验,获取驾驶人在跟车过程中的稳定、加速和减速状态表征数据。以自车速度、自车与前车相对速度、自车与前车相对距离等3类参数的不同组合为输入变量,以自车的加减速特性为输出变量,建立BP神经网络模型。用遗传算法(GA)优化该模型。结果表明,单纯的BP神经网络模型预测准确率较低,利用GA优化模型后可有效提高模型的准确率。当输入参数为自车速度、相对距离与相对速度时,模型的有效率达到94.17%。
In order to improve the accuracy and reliability of the results given by the car early warning system, an actual driving test was carried out by using millimeter-wave radar to obtain the steady state, acceleration and deceleration state characterization data of the driver following the car. Taking the different combinations of three kinds of parameters, such as the speed of the vehicle, the relative speed of the vehicle and the vehicle in front of the vehicle, the relative distance between the vehicle and the vehicle in front of the vehicle, as input variables, the BP neural network model is established by taking the acceleration and deceleration characteristics of the vehicle as output variables. The genetic algorithm (GA) to optimize the model. The results show that the prediction accuracy of the BP neural network model is lower than that of the BP neural network model alone. The GA model can effectively improve the accuracy of the model. When the input parameters are vehicle speed, relative distance and relative speed, the efficiency of the model reaches 94.17%.