An artificial neural network base prediction model and sensitivity analysis for Marshall Mix Design

2016-06-03
Öztürk, Hande Işık
Demir, Birol
Gungor, Ahmet Gurkan
Show full item record
247
views
0
downloads
This study presents an artificial neural network (ANN) model to predict the Hot Mix Asphalt (HMA) volumetrics of mixtures prepared by following Marshall mix design procedure. The input data set of the model is determined to be the aggregate gradation, bulk specific gravity of aggregates, and binder content of the mixture based on the available data. The proposed ANN model utilizes one-layer Levenberg-Marquardt backpropagation to predict the theoretical maximum specific gravity of the loose mixture (Gmm) and the bulk specific gravity of the compacted mix (Gmb). The ANN was trained using data obtained from numerous roads with a total of 835 dif erent mix designs. The estimated HMA volumetrics, Gmb and Gmm, are used to calculate key design criteria such as percent of air voids (Va), Voids in the Mineral Aggregate (VMA), and Voids Filled with Asphalt (VFA). The results revealed that the ANN is able to predict volumetrics within a promising accuracy. The proposed ANN model was able to predict the Va within ±1.0% range 90% of the time and within ±0.5% range 55% of the time. The reasonable predictions of the model leads to significant time, cost and labor savings with respect to traditional Marshall Mix Design by limiting the number of trials to reach to the optimum mix design. With the developed ANN model, Marshall mix design can take 1.5 to 3 days with little validation ef ort in the laboratory. In addition, the model could be used as a practical Quality Control tool for roadway agencies to verify the mix designs.
Compaction, Mixture design, Voids
https://hdl.handle.net/11511/74767
https://www.h-a-d.hr/pubfile.php?id=1033
6th Eurasphalt & Eurobitume Congress (1-3 June 2016)
Department of Civil Engineering, Conference / Seminar

Suggestions

An artificial neural network model for virtual Superpave asphalt mixture design
Ozturk, Hande I.; Öztürk, Hande Işık (Informa UK Limited, 2014-02-07)
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 t...
An attempt to minimize the cost of extracting lithium from boron clays through robust process design
Buyukburc, A; Köksal, Gülser (2005-06-01)
In this study a robust design method is developed for extracting Li from boron (B) clays with the aim of minimizing cost and maximizing productivity. Lithium is commercially extracted from brines and certain minerals. Its extraction from clays has previously been found to be expensive, a major part of the extraction cost being attributed to the raw materials used. In this study, raw materials from lower-cost resources are used without applying any standardization to them and this might increase variation in...
Development of an integrated lab-on-a-chip (LOC) platform for multidrug effect analysis
Atik, Ali Can; Külah, Haluk; Yıldırım, Ender; Department of Electrical and Electronics Engineering (2019)
This thesis presents analysis, design, fabrication, and testing of microfluidic sub-units designed for a droplet-based multidrug analysis platform. The platform is integrated with normally closed electrostatically actuated microvalves to monitor cytotoxicity of anticancer drugs on single cancer cells encapsulated in microdroplets. Here, elucidation of cancer heterogeneity requires precise functional analysis at single-cell levels which can assist to select effective drug regimens for personalized chemothera...
A study on heat transfer inside the wellbore during drilling operations
Apak, Esat Can; Özbayoğlu, Evren; Department of Petroleum and Natural Gas Engineering (2006)
Analysis of the drilling fluid temperature in a circulating well is the main objective of this study. Initially, an analytical temperature distribution model, which utilizes basic energy conservation principle, is presented for this purpose. A computer program is written in order to easily implement this model to different cases. Variables that have significant effect on temperature profile are observed. Since the verification of the analytical model is not probable for many cases, a computer program (ANSYS...
An artificial neural network estimator design for the inferential model predictive control of an industrial multi-component distillation column
Bahar, Almila; Özgen, Canan; Department of Chemical Engineering (2003)
An inferential control methodology, that utilizes an artificial neural network (ANN) estimator for a model predictive controller, is developed for an industrial multi-component distillation column. In the column, propane and butane is separated from a mixture of propane, n-butane, i-butane, and i-pentane with a top product purity of 96% propane and a bottom product purity of 63% n- butane. Dual composition control of the column must be used in a multivariable model predictive controller for an efficient ope...
Citation Formats
H. I. Öztürk, B. Demir, and A. G. Gungor, “An artificial neural network base prediction model and sensitivity analysis for Marshall Mix Design,” presented at the 6th Eurasphalt & Eurobitume Congress (1-3 June 2016), Prague, Czech Republic, 2016, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/74767.
METU IIS - Integrated Information Service open@metu.edu.tr