Russian Federation
Russian Federation
Russian Federation
Purpose: To extend the possibility of interpreting the results of a limited number of physical experiments while selecting the components for the creation of concrete mixes and concrete on its basis with the required output properties. Methods: Using a neural network in the analytical environment Loginom, a model with six input variables representing introduced special additives and seven output variables representing the quality parameters of the concrete mix and concrete has been built. Results: In the process of training a three-layer network model has been formed, with the help of which the predicted output characteristics of concrete mix and concrete have been obtained. Experimental data and neural model prediction for each output variable have been compared in a clear graphical form. Practical significance: Prediction of the required characteristics of the synthesized material by means of the neural model response to various combinations of input data allows to carry out an optimal number of physical experiments. It is possible to apply the proposed modeling method for various multicomponent materials.
Neural network, multiple regression, concrete mix, numerical experiment, physical experiment
1. Kalashnikov V. I. Evolyuciya razvitiya sostavov i izmenenie prochnosti betonov. Betony nastoyaschego i buduschego / V. I. Kalashnikov // Stroitel'nye materialy. - 2016. - № 1/2. - S. 96-103.
2. Belov V. V. Teoreticheskoe obosnovanie optimal'nyh zernovyh sostavov kompoziconnyh materialov s mineral'nymi napolnitelyami / V. V. Belov, P. V. Kulyaev // Stroitel'stvo i rekonstrukciya. - 2017. - № 5(73). - S. 94-101.
3. Rezaev R. O. Primenenie kompleksnogo podhoda k optimizacii proizvodstvennyh sostavov na primere tovarnogo betona / R. O. Rezaev, A. A. Dmitriev, N. A. Borodulya i dr. // ALITinform: Cement. Beton. Suhie Smesi. - 2021. - № 2(63). - S. 42-55.
4. Nizina T. A. Postroenie eksperimental'no-statisticheskih modeley «sostav - svoystvo» fiziko-mehanicheskih harakteristik modificirovannyh dispersno-armirovannyh melkozernistyh betonov / T. A. Nizina, A. S. Balykov // Vestnik Volgogradskogo gosudarstvennogo arhitekturno-stroitel'nogo universiteta. Seriya: Stroitel'stvo i arhitektura. - 2016. - S. 54-66.
5. Nizina T. A. Eksperimental'no-statisticheskie modeli svoystv modificirovannyh dispersno-armirovannyh melkozernistyh betonov / T. A. Nizina, A. S. Balykov // Inzhenerno-stroitel'nyy zhurnal. - 2016. - № 2. - S. 13-24.
6. Nizina T. A. Primenenie modeley «sostav - svoystvo» dlya issledovaniya svoystv modificirovannyh dispersno-armirovannyh melkozernistyh betonov / T. A. Nizina, A. S. Balykov, L. V. Makarova // Vestnik BGTU im. V. G. Shuhova. - 2016. - № 12. - S. 15-21.
7. Dvorkin L. I. Optimal'noe proektirovanie sostavov betona / L. I. Dvorkin. - L'vov: Vischa shkola, 1981. - 159 s.
8. Voznesenskiy V. A. Statisticheskie resheniya v zadachah analiza i optimizacii kachestva stroitel'nyh materialov (metodologiya i opyt primeneniya): avtoref. diss. ... d-ra tehn. nauk / V. A. Voznesenskiy. - M., 1970. - 44 s.
9. Voznesenskiy V. A. Kompromissnaya mnogofaktornaya optimizaciya garantirovannogo kachestva shlakoschelochnyh vyazhuschih / V. A. Voznesenskiy, T. V. Lyashenko, A. D. Dovgan' // Sovremennoe promyshlennoe i grazhdanskoe stroitel'stvo. - 2007. - T. 3. - № 1. - S. 5-15.
10. Komohov P. G. Struktura i svoystva cementnogo kamnya s pozicii komp'yuternogo materialovedeniya / P. G. Komohov, A. M. Haritonov // Academia. Arhitektura i stroitel'stvo. - 2007. - № 4. - S. 63-66.
11. Komohov P. G. Imitacionno-chislennaya model' struktury i svoystv cementnogo kamnya / P. G. Komohov, A. M. Haritonov // Izvestiya vuzov. Stroitel'stvo. - 2008. - № 4(592). - S. 10-16.
