Compressive Strength-Prediction Model for Coal Gangue Concrete via Genetic Algorithm Theory and Support Vector Machine

The objective of this paper is to construct a prediction model that can forecast the unconfined compressive strength of a coal gangue concrete. An improved support vector machine (SVM) using genetic algorithm (GA) to optimize parameters is proposed in this paper. The SVM is chosen as a method for prediction because it shows many unique advantages in solving small -sample, nonlinear, and high dimensional pattern recognition. The cross-validation model is also established. Through the comparison of its prediction results with those of the cross-validation model, the results show that the mean relative error of the GA-SVM model is smaller than the cross-validation model’s, which proves the feasibility of the method. The GA-SVM model is a very viable-candidate for the prediction of the unconfined compressive strength of a coal gangue concrete.