Prediction of Water Resistance of Magnesium Oxychloride Cement Concrete Based upon Hybrid-BP Neural Network

To obtain the magnesium oxychloride cement concrete (MOCC) ratio with excellent water resistance quickly and accurately, a BP neural network (BPNN) model with a topology structure of 4-10-2 was designed, and the PSO (particle swarm optimization), GWO (gray wolf optimization), and WOA (whale optimization algorithm) algorithms were used to optimize the model. The input layer parameters of the model above were n(MgO/MgCl₂), Grade I fly ash, phosphoric acid (PA), and phosphate fertilizer (PF) content, and the output layer was the MOCC's compressive strength and softening coefficient. The model had a dataset of 144 groups, including 100 training set data, 22 verification set data, and 22 test set data. The results showed that the PSO-BPNN model had the highest predictive accuracy among the four models, with a mean R² of 0.99, mean absolute error(MAE) of 0.52, mean absolute percentage error(MAPE) of 0.01, and root mean square error (RMSE) of 0.73 in predicting compressive strength, and a mean R² of 0.99, MAE of 0.44, MAPE of 0.01, and RMSE of 0.62 in predicting the softening coefficient. The results showed that using the PSO-BPNN to predict the compressive strength and softening coefficient of MOCC is feasible and can provide theoretical guidance for designing the MOCC mix.

Research and Engineering Application of Salt Erosion Resistance of Magnesium Oxychloride Cement Concrete

Aiming at the problem that ordinary cement concrete is subjected to damage in heavy saline soil areas in China, a new type of magnesium oxychloride cement concrete is prepared by using the gelling properties of magnesium oxychloride cement in this study, and the erosion resistance of the synthesized magnesium oxychloride cement concrete in concentrated brine of salt lakes is studied through the full immersion test. The effects of concentrated brine of salt lakes on the macroscopic, microscopic morphology, phase composition and mechanical properties of magnesium oxychloride cement concrete are investigated by means of macro-morphology, erosion depth, SEM, XRD and strength changes. The salt erosion resistance mechanism of magnesium oxychloride cement concrete is revealed. The results demonstrate that under the environment of full immersion in concentrated brine of salt lakes, there is no macroscopic phenomenon of concrete damage due to salt crystallization, and the main phase composition is basically unchanged. The microscopic morphology mostly changes from needle-rod-like to gel-like. Due to the formation of a new 5·1·8 phase on the surface layer and the increase in compactness, its compressive strength has a gradual increase trend. Based on the engineering application of magnesium oxychloride cement concrete, it is further confirmed that magnesium oxychloride cement concrete has excellent salt erosion resistance and good weather resistance, which provides theoretical support for future popularization and application.