The analysis of high-strength concrete slump and strength based on GA-SVM

摘要

This paper proposes a support vector machine with genetic algorithm optimized parameters lor predicting of high-strength concrete (IISC) slump and strength. The rules of strength variation with time and slump variation with the level are found through creating a support vector machine (SVM) model. The experimental result presents that this method supports nonlinear prediction comparing with the partial least square regression (I'LSR) and computes more precise through less sample training comparing with BP. In addition, the variation rule of HSC in a deeper level is obtained according to the analysis of the fitting function.