Backcalculation of pavement layer properties using artificial neural network based gravitational search algorithm /

Download
index.pdf
2014
Öcal, Arda
Show full item record
384
views
238
downloads
Transportation agencies need to make accurate decisions about maintenance strategies to provide sustainability of pavements. Non-destructive pavement evaluation means play a crucial role when making such assessments. A commonly used method is to use Falling Weight Deflectometer (FWD) device which measures the surface deflections under imposed loadings. Determination of layer properties through the use of FWD deflections is known as pavement layer backcalculation. This process requires the use of mathematical pavement model to simulate the deflections, which is called forward response model. Calculated deflections from this model are then compared with the field deflections measured through FWD in an iterative manner, which requires intelligent schemes as this process is time-consuming and sometimes produces erroneous results. In this study, an artificial intelligence based inversion algorithm is presented to backcalculate the flexible pavement layer properties. A hybrid approach is proposed using the combination of Artificial Neural Networks (ANN) and a recently developed metaheuristic optimization technique Gravitational Search Algorithm (GSA). The forward calculation engine is based on the finite element analysis of flexible pavements and its surrogate ANN model, which is used to eliminate the time- consuming stages for computing the deflections. GSA is utilized as an efficient search algorithm to seed the ANN model to obtain the deflections in a quick way. The performance of the proposed algorithm is then validated using both synthetically created FWD data and the ones obtained from actual field FWD data. The proposed method is also validated by comparing two well-accepted backcalculation software, EVERCALC and MODULUS. To present the effectiveness of the GSA method, Simple Genetic Algorithm (SGA) is also utilized for comparison purposes. The findings show that the proposed algorithm can predict layer moduli with high accuracy for various types of flexible pavements.
Pavements, Pavements, Pavements, Pavements, Asphalt concrete., Computer algorithms., Neural networks (Computer science).
http://etd.lib.metu.edu.tr/upload/12618019/index.pdf
https://hdl.handle.net/11511/24098
Graduate School of Natural and Applied Sciences, Thesis

Suggestions

Predicted impact of design parameters in asphalt concrete layers on pavement performance
Shakhan, Mohammad Razeq; TOPAL, ALİ; ŞENGÖZ, BURAK; Öztürk, Hande Işık (2021-01-01)
© 2021 ICE Publishing: All rights reserved.The scope of this study was to assess the predicted impact of design factors (voids percentage (Va), effective binder content (Vbe) and aggregate gradation) in each asphalt concrete (AC) layer on pavement performance for conditions in Izmir, Turkey. Research was conducted on three flexible pavement structures for three traffic levels and three subgrade types using AashtoWare Pavement ME Design software. The results indicated that increasing Vbe (from 8% to 15%) and...
Freight villages: A literature review from the sustainability and societal equity perspective
Baydar, A. Mete; Süral, Haldun; ÇELİK, MELİH (2017-11-20)
The purpose of this study is to present a state-of-the-art literature review on Freight Villages from the sustainability and equity perspective, and discuss their impacts and place in the supply chain and logistics networks while focusing on the core concepts of freight transportation. With an understanding of the structure of freight villages, it is clear that they have potential for a number of merits with the increase in freight transportation activities. However, our review shows that current literature...
Investigation of low temperature cracking in asphalt concrete pavement
Qadir, Adnan; Güler, Murat; Department of Civil Engineering (2010)
In this study, low temperature cracking of asphalt concrete is investigated based on a laboratory experimental program including the design variables of aggregate type, gradation, asphalt content, binder grading, binder modification, and the experimental variables of cooling rate, and specimen size. The design of experiment is proposed according to the fractional factorial design principles to reduce the required number of test specimens. Mix designs are performed according to the Superpave mix design guide...
Parametric cost estimation system for light rail transit and metro trackworks
Gunduz, Murat; Ugur, Latif Onur; Ozturk, Erhan (Elsevier BV; 2011-03-01)
The main objective of this work is to develop early cost estimation models for light rail transit and metro trackworks using the multivariable regression and artificial neural network approaches. These two approaches were applied to a data set of 16 projects by using 17 parameters available at the early design phase. The regression analysis estimated the cost of testing samples with an error of 2.32%. On the other hand, artificial neural network estimated the cost with 5.76% error, which was slightly higher...
Systemic seismic vulnerability and risk analysis for buildings, lifeline networks and infrastructures safety gain (SYNER-G)
Yakut, Ahmet(2013)
SYNER-G is research project which has the following main goals: (1) To elaborate appropriate, in the European context, fragility relationships for the vulnerability analysis and loss estimation of all elements at risk, for buildings, building aggregates, utility networks (water, waste water, energy, gas), transportation systems (road, railways, harbors) as well as complex medical care facilities (hospitals) and fire-fighting systems. (2) To develop social and economic vulnerability relationships for quantif...
Citation Formats
A. Öcal, “Backcalculation of pavement layer properties using artificial neural network based gravitational search algorithm /,” M.S. - Master of Science, Middle East Technical University, 2014.
METU IIS - Integrated Information Service open@metu.edu.tr