论文部分内容阅读
针对驾驶员建模中不确定因素的影响,采用操纵逆动力学方法,反求出驾驶员的操纵输入来避开驾驶员建模.神经网络作为一种较好的识别驾驶员输入的方法,其学习速度和收敛精度会影响识别精度.为了提高汽车操纵逆动力模型识别时神经网络的学习速度和收敛精度,基于Elman网络,采用一种新的动态神经网络结构——状态延迟输入动态递归神经网络(SDIDRNN).首先,建立三自由度人—车闭环模型并以实车试验数据验证了模型的正确性.然后,通过建立SDIDRNN网络模型,取闭环模型的仿真结果做为训练样本,对汽车操纵逆动力模型进行了识别,所得结果及误差分析说明了该神经网络在学习能力上的优越性及识别模型的有效性.
In order to avoid the influence of the uncertainties in the driver modeling, a reverse maneuvering method is used to find out the driver’s manipulation input to avoid the driver modeling.As a better method of identifying the driver’s input, Its learning speed and convergence accuracy will affect the recognition accuracy.In order to improve the learning speed and convergence accuracy of the neural network in recognition of vehicle maneuvering inverse dynamic model, based on Elman network, a new dynamic neural network structure-state delay input dynamic recursive neural Network (SDIDRNN) .Firstly, a three-DOF human-vehicle closed-loop model is established and the correctness of the model is verified by real vehicle test data.Then, the SDIDRNN network model is established and the simulation results of closed-loop model are taken as training samples, The manipulated inverse dynamic model was identified, the results obtained and the error analysis demonstrated the superiority of the neural network in learning ability and the effectiveness of the recognition model.