PREDICTION OF COMPRESSIVE STRENGTH OF MECHANISM SAND CONCRETE BASED ON BP NEURAL NETWORK
Mechanism sand concrete strength influence factors are complex,collect domestic and foreign authoritative literature test data to establish a database of 162 groups of mechanism sand compressive strength,using BP neural network to predict the mechanism sand concrete compressive strength.The artificial neural network model was trained and predicted using the multilayer back propagation algorithm,and it was found that the BP neural network model had good prediction and generalization ability,and the predicted value of the model was highly consistent with the measured value;the influence of stone powder content on different strength grades of machine-made sand concrete was analyzed based on the BP neural network model,and it was found that the stone powder content reached the maximum value when the content was about 10%,and the error of the predicted value and the actual value was within 8%,which was the same as the actual value.The error between the predicted value and the actual value is within 8%.The deep learning method can effectively improve the experimental efficiency of the proportion design of mechanism sand concrete and reduce the cost of materials and time.
万方数据
维普
