Improved Informer Evaluation of Long-term Compressive Strength of GGBS Concrete
In order to develop a method for accurately predicting the compressive strength of blast furnace slag (GGBS)concrete over a long period of time.In view of its dynamic characteristics,we choose the Informer model as the basis,and make innovative improvements from three perspectives:da-ta decomposition,encoder design and loss function optimization.Compared with the original Informer, LSTM and Transformer models,it is proved that the improved model has excellent performance in pre-diction accuracy and stability.The results showed excellent performance in R2,RMSE and MAE.In addition,the influence of key components such as cement,water reducing agent and blast furnace slag on the compressive strength of concrete is deeply analyzed.This study not only improves the prediction accuracy,but also provides an important reference for the application of deep learning in the perform-ance evaluation of building materials,helping to promote the development of the field.
blast furnace slag concretecompressive strength at long agesimproved Informer modelperformance evaluation of building materials