Prediction of the compressive strength of fly ash concrete based on hybridizing grid search and support vector regression
Support vector regression(SVR)has been applied to the prediction of mechanical properties of con-crete,but the selection of its hyper-parameters has been a key factor affecting the prediction accuracy.A hybrid machine learning combines the SVR model and grid search(GS),namely the GS-SVR model,is proposed to predict the compressive strength of concrete and to analyze its sensitivity in this work.The hybrid model is trained and tested on a total of 98 data sets retrieved from literature,and the model performance is compared with that of the original SVR model on the same data sets.The results obtained for R,MSE,RMSE,MAE and MAPE are 0.981,3.44,1.85,1.17 and 0.05,respectively,demonstrating that the GS-SVR model proposed can be a candidate method for compressive strength prediction in subsequent related studies.Additionally,a graphical user interface(GUI)is developed to conveniently provide some initial estimates of the outcomes before performing extensive laboratory or fieldwork.Finally,the effect of each variable on the compressive strength in a random environment is analyzed.
万方数据
维普
