Prediction of the compressive strength of sulfate attack concrete based on SSA-BP algorithm
Sulfate attack is one of the most important factors affecting the durability of concrete.Based on the shortcomings of the BP neu-ral network method in predicting the compressive strength of sulphate attacked concrete,such as large error,poor stability,randomization of weight thresholds and weak generalization,a hybrid SSA-BP algorithm model is established by introducing the sparrow search algorithm(SSA),which can achieve more accurate prediction of the compressive strength of sulphate attacked concrete and has more strong general-ization ability.By collecting 525 sets of data used to train and test the model,12 influencing factors related to material composition,erosion medium,and storm conditions were selected as model input variables,and the compressive strength of the concrete after sulfate erosion was used as the output parameter.The prediction results of the SSA-BP hybrid model were compared with the BP independent model by root mean square error,mean absolute error,correlation coefficient and comprehensive evaluation index.Finally,the generalization ability of the SSA-BP model was validated using 66 sets of completely new sample data.The results show that SSA-BP model can effectively predict the compressive strength of sulfate attack concrete,and its prediction accuracy is significantly higher than that of BP model.This model can pro-vide a new prediction method for concrete durability performance assessment under complex environmental conditions.
万方数据
维普
