Cement Compressive Strength Prediction Model Based on GM(1,N)Optimized BP Neural Network
SONG Saiwei
CHENG Ke
JIANG Yuanhao
Abstract：Cement compressive strength is one of the important indicators to measure the quality of cement.In order to im-prove the accuracy of the prediction of cement compressive strength,a GM(1,N)optimized BP neural network prediction model is designed.Hybrid optimization stages for independent pre-training stages and post-training stages.In the independent pre-training stage,the BP neural network prediction model and the GM(1,N)prediction model are independently trained,and the results gen-erated by the two models are weighted and optimized by the differential evolution algorithm in the post-mixed optimization stage,thereby further improving the prediction accuracy.The results show that compared with using BP neural network and GM(1,N)pre-diction model alone,the mean square error of the model designed in this paper is reduced by 37.96%on average,indicating that the proposed method can use data mining method to analyze cement composition information,thereby effectively improving the predic-tion accuracy of the compressive strength of cement.
Keywords：compressive strength of cementBP neural networkgrey relational degreedifferential evolution
Publication Date：2025-05-20
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 1317-1321 )