scholarly journals Road Performance Prediction Model of AC-25 Asphalt Mixture

Author(s):  
Zhaohui Sun ◽  
Zhiqi Song ◽  
Guangqiang Zhu ◽  
Mengmeng Li
Author(s):  
Pengzhen Lu ◽  
Chenhao Zhou ◽  
Simin Huang ◽  
Yang Shen ◽  
Yilong Pan

Expansion joints are a weak and fragile part of bridge superstructure. The damage or failure of the expansion joint will lead to the decline of bridge durability and endanger the bridge structure and traffic safety. To improve the service life and performance of bridge expansion joints, the ideal method is to use seamless expansion joints. In this study, starting from the commonly used asphalt mixture gradation of seamless expansion joint, and taking into account the actual situation of bridge expansion joint structure and environment in China, the gradation and asphalt-aggregate ratio are preliminarily designed. Through a Marshall test, the corresponding asphalt mixture is evaluated and analyzed according to the stability, flow value, and void ratio, and the optimal gradation and asphalt-aggregate ratio are determined. Finally, the asphalt mixture is prepared with the mixture ratio design, and the test results of an immersion Marshall test, fatigue performance test, and full-scale test verify that the asphalt mixture meets the road performance requirements of seamless expansion joints. On the basis of the experimental data, the performance of large sample asphalt mixture is continuously tested, compared, and optimized. The results show that the asphalt mixture ratio designed is true and reliable, which can provide reference for the optimal design of seamless expansion joint filler.


2021 ◽  
Author(s):  
Marco Aurélio Oliveira ◽  
Luiz V. O. Dalla Valentina ◽  
André Hideto Futami ◽  
Osmar Possamai ◽  
Carlos Alberto Flesch

2021 ◽  
Vol 30 (1) ◽  
pp. 511-523
Author(s):  
Ephrem Admasu Yekun ◽  
Abrahaley Teklay Haile

Abstract One of the important measures of quality of education is the performance of students in academic settings. Nowadays, abundant data is stored in educational institutions about students which can help to discover insight on how students are learning and to improve their performance ahead of time using data mining techniques. In this paper, we developed a student performance prediction model that predicts the performance of high school students for the next semester for five courses. We modeled our prediction system as a multi-label classification task and used support vector machine (SVM), Random Forest (RF), K-nearest Neighbors (KNN), and Multi-layer perceptron (MLP) as base-classifiers to train our model. We further improved the performance of the prediction model using a state-of-the-art partitioning scheme to divide the label space into smaller spaces and used Label Powerset (LP) transformation method to transform each labelset into a multi-class classification task. The proposed model achieved better performance in terms of different evaluation metrics when compared to other multi-label learning tasks such as binary relevance and classifier chains.


Sign in / Sign up

Export Citation Format

Share Document