The “white hole effect” alters the driving environment during a tunnel’s exit phase, making it more difficult and uncertain for drivers to access information and control their behavior, thereby endangering traffic safety. Consequently, the driving risk at the exit of a long spiral tunnel served as the subject of this study, and the Jinjiazhuang spiral tunnel served as the object of the natural vehicle driving experiment. Following the theory of a non-linear autoregressive dynamic neural network, a vehicle speed prediction model based on driver characteristics was developed for the exit phase of the tunnel, taking driver expectations and behavioral changes into account. It also classifies the driver’s behavior during the tunnel’s exit phase to assess the risk posed by the driver’s behavior during the tunnel’s exit phase and determine a dynamic and safe comfort speed. The study’s results indicate that the driver’s behavioral load changed significantly as the vehicle approached the tunnel exit. At the exit of the spiral tunnel, the vehicle’s actual speed was 71 km/h, which is below the speed limit of 80 km/h. This demonstrates that the expected change in the driver’s behavior in the tunnel exit phase was substantial. Therefore, setting the emotional safety and comfort speed so that the driver maintains a smooth comfort level in the tunnel exit phase can reduce the tunnel exit driving risk. The results of this study provide a benchmark for tunnel traffic safety and lay the groundwork for further development of vehicle risk warning settings for the tunnel’s exit phase.
24 March 2021 in Journal of Advanced Transportation
The accurate evaluation and prediction of highway network traffic state can provide effective information for travelers and traffic managers. Based on the deep learning theory, this paper proposes an evaluation and prediction model of highway network traffic state, which consists of a Fuzzy C-means (FCM) algorithm-based traffic state partition model, a Long Short-Term Memory (LSTM) algorithm-based traffic state prediction model, and a K-Means algorithm-based traffic state discriminant model. The highway network in Hebei Province is employed as a case study to validate the model, where the traffic state of highway network is analyzed using both predicted data and real data. The dataset contains 536,823 pieces of data collected by 233 continuous observation stations in Hebei Province from September 5, 2016, to September 12, 2016. The analysis results show that the model proposed in this paper has a good performance on the evaluation and prediction of the traffic state of the highway network, which is consistent with the discriminant result using the real data.
30 March 2025 in Tunnelling and Underground Space Technology
Road geometry (curve radius and curve direction) must be optimized and perfected based on scientific design and accident analysis in order to ensure traffic safety. This study simulated vehicle maneuvering and operational behavior of drivers using simulated driving experiments. The experimental procedure was divided into two scenes, and there were five types of curves with radiuses of 500 m, 1,000 m, 1,500 m, 2,000 m, and 2,500 m. Each curve radius was divided into two cases: the left curve and the right curve. Twenty-eight participants took part in the experiment, each with different personal characteristics. During the experiment, driver visual information and electroencephalogram (EEG) information were recorded through Face-LAB and an EEG recorder. EEG information was processed according to frequency, and divided into different bands: workload, relaxation, comfort, nervousness, attention, thinking, consciousness, and fatigue. According to the averages and standard deviations of the different EEG curves, the principle of Kansei engineering can be used to determine the level of a driver’s subjective Kansei factors. As a result, it was found that the emotional information of the driver gradually became stable with increased curve radius, and the degree of subjective emotional change decreased.
The larger the proportion of truck traffic volume, the greater the impact on traffic efficiency, and overtaking behavior will also have an impact. Therefore, in order to clarify the truck traffic volume of the freight two-lane highway due to the difficulty of overtaking, an actual vehicle test is carried out. This involves selecting the appropriate two-lane test section, recording each moment and speed in the driver’s overtaking behavior, performing multiple regression analysis to examine the relationship between the overtaking conflict time and design speed and traffic volume, determining a reasonable evaluation series of two-lane road overtaking risk and the corresponding overtaking conflict time threshold by the Fisher optimal segmentation method, and giving an overtaking behavior risk evaluation method based on conflict time. Finally, according to the overtaking conflict time model, different truck traffic conditions are obtained. The research results show that overtaking conflict time is negatively correlated with the traffic volume and design speed of the lane. Through the risk assessment of the corresponding overtaking behavior, the three levels of serious conflict, general conflict and non-conflict are determined, and the freight traffic volume corresponding to different conflict levels at different speeds is calculated, which provides a reference for setting auxiliary lanes for the two-lane freight highway.