高速公路进出流量差异的BP神经网络预测模型

进出高速公路收费站车流量的差异和变化给营运管理带来一定难度。分析了造成流量差异的部分因素，建立了BP神经网络预测模型，并运用Matlab工具进行仿真及误差分析。结果显示，采用本模型可缩短训练时间，避免训练陷入局部极小值，并可对近期4d的车流量差值进行可靠预测。     

Multiple models direct adaptive controller for a stochastic non-minimum phase system

For a stochastic non-minimum phase multivariable system, a multiple models direct adaptive controller is presented. It is composed of multiple fixed models with two adaptive models. The fixed models are used to cover the region where the system parameters jump and improve the transient response, while another two adaptive models are used to guarantee the stability. Utilizing generalized minimum variance design method, it adopts the stochastic system estimation algorithm with optimal controller design method to identify the controller parameter directly. Finally, the global convergence is given. The simulation proves the effectives of the controller proposed.