An artificial neural network model for virtual Superpave asphalt mixture design

Date

2014-02-07

Author

Ozturk, Hande I.
Öztürk, Hande Işık

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

210
views

0
downloads

This study presents an artificial neural network (ANN) model to predict the asphalt mixture volumetrics at Superpave gyration levels. The input data-set needed by the algorithm is composed of gradation of the mix, bulk specific gravity of aggregates, low- and high-performance grade of the binder, binder content of the mix and the target number of gyrations (i.e. N-ini, N-des and N-max). The proposed ANN model uses a three-layer scaled conjugate gradient back-propagation (feed-forward) network. The ANN was trained using data obtained from numerous roads with a total of 1817 different mix designs. Results revealed that the ANN was able to predict V-a within V-a (measured) +/- 1.0% range 85-93% of the time and within V-a (measured) +/- 0.5% range 60-70% of the time. Currently with the developed ANN model, Superpave mix design can take approximately between 1.5 and 4.5 days, which corresponds to 3-6 days of savings.

Subject Keywords

Mechanics of Materials, Civil and Structural Engineering

URI

https://hdl.handle.net/11511/48076

Journal

INTERNATIONAL JOURNAL OF PAVEMENT ENGINEERING

DOI

https://doi.org/10.1080/10298436.2013.808341

Collections

Department of Civil Engineering, Article

Suggestions

OpenMETU
Core

Predicting the shear strength of reinforced concrete beams using artificial neural networks Mansour, MY; Dicleli, Murat; Lee, JY; Zhang, J (Elsevier BV, 2004-05-01) The application of artificial neural networks (ANNs) to predict the ultimate shear strengths of reinforced concrete (RC) beams with transverse reinforcements is investigated in this paper. An ANN model is built, trained and tested using the available test data of 176 RC beams collected from the technical literature. The data used in the ANN model are arranged in a format of nine input parameters that cover the cylinder concrete compressive strength, yield strength of the longitudinal and transverse reinforc...
Quantification and localisation of damage in beam-like structures by using artificial neural networks with experimental validation Şahin, Melin (Elsevier BV, 2003-12-01) This paper presents a damage detection algorithm using a combination of global (changes in natural frequencies) and local (curvature mode shapes) vibration-based analysis data as input in artificial neural networks (ANNs) for location and severity prediction of damage in beam-like structures. A finite element analysis tool has been used to obtain the dynamic characteristics of intact and damaged cantilever steel beams for the first three natural modes. Different damage scenarios have been introduced by redu...
A Methodology for Optimal Layout Design of Pressure Cells for Concrete Faced Rockfill Dams Arı, Onur; Yanmaz, Ali Melih (Springer Science and Business Media LLC, 2018-08-01) In this study, a methodology for optimal layout design of pressure cells for concrete faced rockfill dams is developed. A representative dimensionless stress distribution model was formed for obtaining the magnitudes and location of different stress zones as a function of dam height. This information enabled development of a procedure for proper location and the number of pressure cells throughout the dam body. A vertical placement algorithm based on error minimization was first developed, which is followed...
Testing and analysis of different hold down devices for CFS construction Pehlivan, Barış Mert; Baran, Eray; Topkaya, Cem (Elsevier BV, 2018-06-01) This paper summarizes the findings of a two-phase study on hold down devices used in cold formed steel (CFS) structural systems. The first phase consisted of component testing and numerical analysis of hold down devices while the second phase was based on testing of CFS framed sheathed wall panels under cyclic lateral loading. Eleven monotonic and three cyclic tensile load tests were performed on seven different types of hold down devices to assess the performance of readily available hold downs and propose...
Upgrading of slab-column connections using fiber reinforced polymers Binici, Barış (Elsevier BV, 2005-01-01) The results of an experimental program on upgrading of reinforced concrete slab-column connections subjected to monotonic shear and unbalanced moment transfer are presented in this study. Externally installed carbon fiber reinforced polymer (CFRP) stirrups acting as shear reinforcement around the slab-column connection area were used with two patterns of CFRP arrangements. It was found that the proposed method resulted in punching shear capacity increases up to 60% relative to the specimen without any stren...

Citation Formats

H. I. Ozturk and H. I. Öztürk, “An artificial neural network model for virtual Superpave asphalt mixture design,” INTERNATIONAL JOURNAL OF PAVEMENT ENGINEERING, pp. 151–162, 2014, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/48076.