Open Access. Powered by Scholars. Published by Universities.®

Engineering Commons

Open Access. Powered by Scholars. Published by Universities.®

Louisiana State University

LSU Doctoral Dissertations

Artificial Neural Network

Articles 1 - 3 of 3

Full-Text Articles in Engineering

A New Generation Of Open-Graded Friction Course For Enhanced Durability And Functionality, Hossam Abohamer Apr 2022

A New Generation Of Open-Graded Friction Course For Enhanced Durability And Functionality, Hossam Abohamer

LSU Doctoral Dissertations

This study aims at (1) enhancing Open Graded Friction Course (OGFC) mixes durability using additives and other by-products; (2) investigating the impacts of selected factors on OGFC pavements seepage characteristics; (3) developing a quantitative tool to model the deterioration in OGFC pavements functional performance; and (4) developing new guidelines of Air Void (AV) content for OGFC for optimum functionality and durability. For the durability objective, eight mixes were prepared with a PG 76-22 binder and two sources of aggregate (i.e., # 78 limestone and # 67 sandstone). Three Warm Mix Additives (WMA), one by-product (i.e., crumb rubber [CR]), and two …


Identification Of Top-Down, Bottom-Up, And Cement-Treated Reflective Cracks Using Convolutional Neural Network And Artificial Neural Network, Nirmal Dhakal May 2020

Identification Of Top-Down, Bottom-Up, And Cement-Treated Reflective Cracks Using Convolutional Neural Network And Artificial Neural Network, Nirmal Dhakal

LSU Doctoral Dissertations

The objective of this study was to formulate a Convolutional Neural Networks (CNN) model and to develop a decision-making tool using Artificial Neural Networks (ANN) to identify top-down, bottom-up, and cement treated (CT) reflective cracking in in-service flexible pavements. The CNN’s architecture consisted of five convolutional layers with three max-pooling layers and three fully connected layers. Input variables for the ANN model were pavement age, asphalt concrete (AC) thickness, annual average daily traffic (AADT), type of base, crack orientation, and crack location. The ANN network architecture consisted of an input layer of six neurons, a hidden layer of ten neurons, …


Geodatabase-Assisted Storm Surge Modeling, Sait Ahmet Binselam Jan 2013

Geodatabase-Assisted Storm Surge Modeling, Sait Ahmet Binselam

LSU Doctoral Dissertations

Tropical cyclone-generated storm surge frequently causes catastrophic damage in communities along the Gulf of Mexico. The prediction of landfalling or hypothetical storm surge magnitudes in U.S. Gulf Coast regions remains problematic, in part, because of the dearth of historic event parameter data, including accurate records of storm surge magnitude (elevation) at locations along the coast from hurricanes. While detailed historical records exist that describe hurricane tracks, these data have rarely been correlated with the resulting storm surge, limiting our ability to make statistical inferences, which are needed to fully understand the vulnerability of the U.S. Gulf Coast to hurricane-induced storm …