基于SVR的混凝土水泥的配合比对其抗压强度影响规律的研究-材料物理与化学专业论文.docxVIP

ABSTRACT Nowadays, it is more and more pay attention how to improve building safety, therefore concrete/cement has been greatly concerned by people. One of the most serious problems is how to enhance the compressive strength of concrete/cement. The compressive strength of concrete/cement has been extensively investigated by scholars because of its importance to the safety of the buildings. Preparation technique of concrete/cement material has been widely used in industry. Although large-scale industrial production has been achieved, it also faces many shortcomings and deficiencies in the use of concrete/cement materials, thus it needs to be further studied and improved. In the case of the concrete/cement possessing sufficient compressive strength, how to improve the economic efficiency efficiently also plays very important. Because the material mix-proportion has a very closed relationship with its compressive strength of concrete/cement, it is quite important for us to accurately model and optimize the mix-proportion for concrete/cement. If there is no a feasible method for guidance, one needs a lot of manpower, material resources for a large number of experiments to find the suitable material mix-proportion. Therefore, how to design a reasonable experiment, analysis of experimental data effectively, and reduce experiment costs, becomes an unavoidable scientific problem. In this thesis, the support vector regression (SVR) theory combined with particle swarm optimization (PSO) was proposed to model the influence of the materials mix-proportion on its compressive strength of concrete/cement. The main contents are as following: According to an experimental dataset, the SVR was employed to regress and predict the compressive strength of ordinary concrete via 3 factors including water, coarse aggregate, and cement. The result revealed that the modeling capacity of SVR is superior to that of the spatial autocorrelation model. The optimal mix-proportion was obtained base