The objective of this paper is to investigate the safe speed of SUV on curved sections of rural road in China. The effects of various geometric design characteristics and adverse weather conditions were introduced in Carsim multi-body simulation packages. Based on vehicle dynamic characteristics on horizontal curve alignment, this research selected the maximum side friction factor of axle, lateral load transfer ratio, the ratio of the lateral distance of tracking trajectory to the lane width as the indicators for skidding, rollover and transient lane-departure respectively. The RBF neural network was used to analyze the data and establish the prediction model for maximum speed . Results of the research found that, with the increase of horizontal curve radius, the effect of the crosswind has more pronounced effect on the maximum security speed. The safe speed prediction model based on RBF neural network has high accuracy and can be used to provide technical support for formulating reasonable speed limit strategies for rural roads designed by Chinese design criteria.

CICTP