Effective Prediction of Thermal Conductivity of Concrete Using Neural Network Method

Abstract

The temperature distributions of concrete structures strongly depend on the value of thermal conductivity of concrete. However, the thermal conductivity of concrete varies according to the composition of the constituents and the temperature and moisture conditions of concrete, which cause difficulty in accurately predicting the thermal conductivity value in concrete. For this reason, in this study, back-propagation neural network models on the basis of experimental values carried out by previous researchers have been utilized to effectively account for the influence of these variables. The neural networks were trained by 124 data sets with eleven parameters: nine concrete composition parameters (the ratio of water-cement, the percentage of fine and coarse aggregate, and the unit weight of water, cement, fine aggregate, coarse aggregate, fly ash and silica fume) and two concrete state parameters (the temperature and water content of concrete). Finally, the trained neural network models were evaluated by applying to other 28 measured values not included in the training of the neural networks. The result indicated that the proposed method using a back-propagation neural algorithm was effective at predicting the thermal conductivity of concrete.

Numerical identification of the thermal properties of early age concrete using inverse heat transfer problem

“…the isothermal calorimetry, could be useful for this purpose and also for validation of calculated heat source function. Also direct measurements of thermal conductivity and thermal capacity of concrete, at least at the final stage of hydration, could be used for validation of the predicted values [61]. In such a way the accuracy of the obtained solutions would be verified by independent experimental methods.…”

Measurements of Thermal Conductivity of LWC Cement Composites Using Simplified Laboratory Scale Method

“…Similar two-phase and multi-phase models for the thermal conductivity of porous materials are referenced in work [ 40 ], and an approach considering an idealized system of “open and enclosed pores” has been proposed by [ 41 ]. Other researchers have developed trained neural network models to predict the thermal conductivity of concrete, although measured values were not used to train the models to evaluate the algorithms [ 42 ]. Several publications provide results of empirical studies of concrete’s thermal conduc-tivity and heat capacity, typically using concrete or mortar made with natural aggregates.…”

Evolution of thermal parameters of wet‐screened dam concrete after different freeze–thaw deterioration

“…10 "Measured temperature, numerical calculation, inversion-analysis" is another method used to obtain the thermal parameters. [11][12][13][14][15] The thermal-parameter test requires specialized equipment, and the cylindrical concrete specimen has a hole in the central region where a heater is placed in the hole in order to obtain the temperature difference between the interior and exterior. The high-stress concentration may damage the specimens during freezethaw cycling, so it is difficult to properly complete the experiments during freeze-thaw cycling.…”