Comparative Evaluation of Support Vector Machine and Multiple Linear Regression for Predicting the Compressive Strength of Fly Ash-Containing Concrete

Fly ash-containing concrete has attracted considerable attention as an effective approach to sustainable concrete development due to its potential to reduce cement consumption, reuse an industrial by-product, and mitigate the environmental impacts associated with cement production. However, the complex and nonlinear relationships among mix-design constituents, concrete age, and compressive strength make accurate strength prediction challenging. This study investigates and compares the performance of a Support Vector Machine (SVM) with a Radial Basis Function (RBF) kernel and Multiple Linear Regression (MLR) for predicting the compressive strength of fly ash-containing concrete. For this purpose, a dataset comprising ۴۷۱ laboratory observations with seven input variables representing mix-design parameters and concrete age was employed. The data were divided into training and testing sets, and five-fold cross-validation was performed to assess the stability and generalizability of the models. The SVM hyperparameters were optimized using grid search. The results demonstrated that SVM outperformed MLR in modeling the complex relationships governing compressive strength. Specifically, during the training phase, SVM achieved a correlation coefficient of ۰.۹۸۸, compared with ۰.۸۱۴ for MLR. The cross-validation results further confirmed the superior performance and greater stability of the SVM model. These findings highlight the potential of nonlinear machine-learning models for estimating compressive strength and supporting the design of sustainable fly ash-containing concrete.

کلیدواژه ها:

Fly ash-containing concrete ، Compressive strength ، five-fold cross-validation ، Support Vector Machine ، Multiple linear regression