The correlation and Hausdroff dimensions of traffic flow and speed series are analyzed based on the Fractal theory. Using the traffic flow data of four typical expressways in China as input sample, the data statistical results indicates that both synchronized and free flow state are fractal and chaotic. In addition, traffic flow rate and speed time series are determined by different intervals and then G-P arithmetic is applied to estimate their correlation dimensions and the Hausdroff dimension. The results also illustrates that Fractal dimension could by clearly identified, which provides a useful tool for expressway operation management and facilities provision.
Mountainous freeway goes through complex geographic and geological regions and causes safety problem. Making clear of the inner relationship of the crash occurrence and the geometric factors is the most fundamental prerequisite to solve the problem. This paper reveals the contributing geometric factors through analyzing the crash data from Changjin Freeway, a typical mountainous freeway located in Jiangxi Province, China. Based on crash records and designed alignment data, contributing geometric factors are generally classified into three categories: vertical alignment, horizontal alignment, and cross section. And then detailed effects of geometric variables are separately discussed and quantified through the relation with crash rate (CR).
PAC(programmable automation controller) is a new trend of the industrial controller, but for now, most IDEs(integrated development environment) are still providing the PLC mode for users, which can not take full advantage of the PAC. Further more, in China, there is still not such IDE with complete intellectual properties for PACs designed by Chinese companies. For above purposes, the CHD-PACIDE was implemented which supported the ARM cortex-Mx series microcontrollers. This IDE consists of three layers, interface layer, data management layer and kernel layer, which managed functional modules respectively. Based on a C-like language Engineer C defined by our research team, the interface layer provided the structural graphical input mode and the text input mode for users to edit their code. The data management layer used the XML with specified format manage the flow of data. The kernel layer had two parts which were implemented in the IDE and the debug microcontroller stm8s, this layer can be used to debug user’s code through the Jtag port under the Coresight debugging structure of ARM. This IDE could be updated easily by adding the specific XML file for the new microcontroller used by the specific PAC.
Accurately obtaining the distribution of the open-channel velocity field in hydraulic engineering is extremely important, which is helpful for better calculation of open-channel flow and analysis of open-channel water flow characteristics. In recent years, machine learning has been used for open-channel velocity field prediction. However, effective training of data-driven models in machine learning heavily depends on the diversity and quantity of data. In this paper, a CFD-based pre-training neural network model (CFD–PNN) is proposed for accurate open-channel velocity field prediction, allowing the adaption to the task with small sample data. Also, a cross-sectional velocity field prediction method combining the computational fluid dynamics (CFD) and machine learning is established. By comparing CFD–PNN with six other neural network algorithm models and the CFD model, the results show that, in the case of small sample data, the CFD–PNN model can predict a more reasonable open-channel velocity field with higher prediction accuracy than other models. The average error of the velocity calculation for the trapezoidal open-channel cross-section is about 3.62%. Compared with other models, the accuracy is improved by 0.3–2.8%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.