Nihat Morova

Prediction of the marshall stability of reinforced asphalt concrete with steel fiber using fuzzy logic

In this study, Marshall Stability MS of steel fiber reinforced asphalt concrete has been predicted using steel fiber rate 0%, 0.25%, 0.50%, 0.75%, 1.0%, 1.5%, 2.0% and 2.5%, bitumen content 5%, 5.5% and 6.0% and unit weights 2,465--2,515 gr/cm3 by Fuzzy Logic FL. Results have shown that developed FL model has a strong potential for predicting the MS of asphalt concrete without performing any experimental studies.

Modeling Marshall Stability of light asphalt concretes fabricated using expanded clay aggregate with Artificial Neural Networks

In this study, an Artificial Neural Network (ANN) model has been developed to estimate Marshall Stability (MS) of lightweight asphalt concrete containing expanded clay. In the model, amount of bitumen (%), transition speed of ultrasound (μs), unit weight (gr/cm3) were used as inputs and Marshall Stability (kg) was used as output. Developed ANN model results and the experimental results were compared and good relationship was found.

Modelling Marshall Stability of fiber reinforced asphalt mixtures with ANFIS

In this study, an Adaptive Neural Fuzzy Inference System (ANFIS) model for predicting the Marshall Stability (MS) of basalt fiber reinforced asphalt concrete mixtures and various mix proportions has been developed. Experimental details were used to construct the model. The amounts of bitumen (%), Fiber (Basalt) Ratio (%) were used as input variables and Marshall Stability (kg) values were used as output variables. Statistical equations were used to evaluate the Developed ANFIS model. Results showed that developed ANFIS model has strong potential to predict Marshall Stability of asphalt concrete using related inputs in a short time. Also, the Marshall Stability of Fiber-Reinforced asphalt concrete and various mix proportions can be found without performing any experiments.

Marshall stability estimating using artificial neural network with polyparaphenylene terephtalamide fibre rate

Due to the complex behaviour of asphalt pavement materials under various loading conditions, pavement structure, and environmental conditions, accurately predicting stability of asphalt pavement is difficult. To predict, it is required to find the mathematical relation between the input and output data by an accurate and simple method. In recent years, artificial neural networks (ANNs) have been used to model the properties and behaviour of materials, and to find complex relations between different properties in many fields of civil engineering applications, because of their ability to learn and to adapt. In the present study, laboratory data are obtained from an experimental study that was used to develop an ANN model. For predicting the Marshall Stability value of mixture using ANN models, an appropriate selection of input parameters (neurons) is essential. There are four nodes in the input layer corresponding to four variables: Polyparaphenylene Terephtalamide fibre (PTF) rate, binder rate, flow, volume of the specimen. The result indicates that the proposed model can be applied in predicting Marshall Stability of asphalt mixtures. The model is further applied to evaluate the effect of different rates of Polyparaphenylene Terephtalamide on Marshall Stability.

Evaluation of Colemanite Waste as Aggregate Hot Mix Asphalt Concrete

In this study usability of waste colemanite which is obtained after cutting block colemanite for giving proper shape to blocks as an aggregate in hot mix asphalt. For this aim asphalt concrete samples were prepared with four different aggregate groups and optimum bitumen content was determined. First of all only limestone was used as an aggregate. After that, only colemanite aggregate was used with same aggregate gradation. Then, the next step of the study, Marshall samples were produced by changing coarse and fine aggregate gradation as limestone and colemanite and Marshall test were conducted. When evaluated the results samples which produced with only limestone aggregate gave the maximum Marshall Stability value. When handled other mixture groups (Only colemanite, colemanite as coarse aggregate-limestone as fine aggregate, colemanite as fine aggregate-limestone as coarse aggregate) all groups were verified specification limits. As a result, especially in areas where there is widespread colemanite waste, if transportation costs did not exceed the cost of limestone, colemanite stone waste could be used instead of limestone in asphalt concrete mixtures as fine aggregate

Asphalt concrete stability estimation from non-destructive test methods with artificial neural networks

The core drilling method has often been used to determine the current status of asphalt concretes. However, this method is destructive so causes damage to the asphalt concretes. In addition, this method causes localized points of weakness in the asphalt concretes and is time consuming. In recent years, non-destructive testing methods have been used for pavement thickness estimation, determination of elasticity modulus, and density and moisture measurements. In this study, the above-mentioned non-destructive and destructive tests with data obtained by applying the Marshall stability to the same asphalt concretes were estimated using the artificial neural networks approach.

Determining amount of bituminous effects on asphalt concrete strength with artificial intelligence and statistical analysis methods

In this study, an experimental study has been conducted to determine compressive strength of asphalt concrete. The scope of study by preparing 45 Marshall samples Marshall stability experiment was conducted and compressive strength of asphalt concrete was determined. Compressive strength of asphalt concrete as depending on bituminous amount prediction models were developed by using obtained experiment results. Compressive strength of asphalt concrete values as depending on bituminous amount have been estimated on prediction models developed with regression analyses and Artificial Neural Network (ANN) Methods. Results obtained from models were compared with experiment results. Prediction performances of developed models were evaluated as compared. As a result it was determined that possible to estimate the compressive strength of asphalt concrete as depending on bituminous amount with developed ANN model and that ANN model was more successful than regression model for estimating the compressive strength of asphalt concrete.

PREDICTION OF NOISE CAUSED BY URBAN TRAFFIC BY ARTIFICIAL NEURAL NETWORK

ABSTRACT Noise which is one of the important results of gradually increase of urbanization and technologic developments especially in recent years, as parallel with the increasing population also is important problem of environment, life and health. The important factor of the problem in urban areas is inner city traffic and noise caused by that traffic. In this study, aim of the predict of the noise caused by the traffic, various models have been developed with the Artificial Neural Network (ANN). The data obtained from various sources have been used creating the ANN models. In the model as an input data Heavy Vehicle Number (Vehicle/Hour), Light Vehicle Number (Vehicle/Hour), Total Traffic per Hour (vehicle/hour) and Speed (Km/Hour) were used and as an output data Noise caused by the traffic (Leq dB(A)) was used. Developed ANN model and predicted results of noise caused by the traffic were compared with the classical model results (measured) and it has been seen that the results are acceptable. Predicting the noise caused by the traffic it has been determined that instead of the mathematical methods the ANN model can be used. Key words: