Civil Engineering / İnşaat Mühendisliği

Permanent URI for this collectionhttps://hdl.handle.net/11147/13

Browse

Filters

2014 - 20202

Settings

Institution Author: search.filters.institutionAuthor.Erdem, Tahir KemalWoS Q: search.filters.wosQuartile.Q2

Search Results

Now showing 1 - 2 of 2
  • Article
    Citation - WoS: 1
    Citation - Scopus: 1
    Generalized Regression Neural Network and Empirical Models To Predict the Strength of Gypsum Pastes Containing Fly Ash and Blast Furnace Slag
    (Springer Verlag, 2020) Erdem, Tahir Kemal; Cengiz, Okan; Tayfur, Gökmen
    Gypsum is widely used in constructions owing to its easy application, zero shrinkage, and excellent fire resistance. Several parameters can affect the properties of gypsum pastes. To study the strength of the gypsum pastes experimentally by trying all these parameters is time-consuming and costly. Therefore, artificial intelligence methods can be very useful to predict the paste strength, which, in turn, can reduce the number of trial batches. Based on experimental data, the generalized regression neural network (GRNN) and empirical models were developed to predict strength of gypsum pastes containing fly ash (FA) and blast furnace slag (BFS). Gypsum content, pozzolan content, curing temperature, curing duration, and testing age constituted the input variables of the models while the paste strength was the target output. The trained and tested GRNN model was found to be successful in predicting strength. Sensitivity analysis by the GRNN model revealed that the curing duration and temperature were important sensitive parameters. In addition to the GRNN model, empirical models were proposed for the strength prediction. The same input variables formed the input vectors of the empirical models. The same dataset used for the calibration of the GRNN model was employed to establish the empirical models by employing genetic algorithm (GA) method. The empirical models were successfully validated. The GRNN and GA_based empirical models were also tested against the multi-linear regression (MLR) and multi-nonlinear regression (MNLR) models. The results showed the outperformance of the GRNN and the GA_based empirical models over the others.
  • Article
    Citation - WoS: 54
    Citation - Scopus: 69
    Strength Prediction of High-Strength Concrete by Fuzzy Logic and Artificial Neural Networks
    (American Society of Civil Engineers (ASCE), 2014) Tayfur, Gökmen; Erdem, Tahir Kemal; Kırca, Önder
    High-strength concretes (HSC) were prepared with five different binder contents, each of which had several silica fume (SF) ratios (0-15%). The compressive strength was determined at 3, 7, and 28 days, resulting in a total of 60 sets of data. In a fuzzy logic (FL) algorithm, three input variables (SF content, binder content, and age) and the output variable (compressive strength) were fuzzified using triangular membership functions. A total of 24 fuzzy rules were inferred from 60% of the data. Moreover, the FL model was tested against an artificial neural networks (ANNs) model. The results show that FL can successfully be applied to predict the compressive strength of HSC. Three input variables were sufficient to obtain accurate results. The operators used in constructing the FL model were found to be appropriate for compressive strength prediction. The performance of FL was comparable to that of ANN. The extrapolation capability of FL and ANNs were found to be satisfactory.