Abstract
Compressive strength is an important mechanical property of high-strength concrete (HSC), but testing methods are usually uneconomical, time-consuming, and labor-intensive. To this end, in this paper, a long short-term memory (LSTM) model was proposed to predict the HSC compressive strength using 324 data sets with five input independent variables, namely water, cement, fine aggregate, coarse aggregate, and superplasticizer. The prediction results were compared with those of the conventional support vector regression (SVR) model using four metrics, root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and correlation coefficient (R2). The results showed that the prediction accuracy and reliability of LSTM were higher with R2 = 0.997, RMSE = 0.508, MAE = 0.08, and MAPE = 0.653 compared to the evaluation metrics R2 = 0.973, RMSE = 1.595, MAE = 0.312, MAPE = 2.469 of the SVR model. The LSTM model is recommended for the pre-estimation of HSC compressive strength under a given mix ratio before the laboratory compression test. Additionally, the Shapley additive explanations (SHAP)-based approach was performed to analyze the relative importance and contribution of the input variables to the output compressive strength.
Highlights
High-strength concrete (HSC), which is defined by the compressive strength of more than 40 MPa [1], was developed in the late 1950s and early 1960s in the field of cementitious materials
Abobakr et al [13] developed an extreme learning machine (ELM) model to predict the compressive strength of high-strength concrete, and the results showed that the ELM method has good prediction accuracy and fast learning speed compared with the traditional back-propagation (BP) neural network
Compared with support vector regression (SVR), higher model prediction accuracy was obtained by the long short-term memory (LSTM) model with R2 = 0.997, root mean square error (RMSE) = 0.508, mean absolute error (MAE) = 0.08, and mean absolute percentage error (MAPE) = 0.653, which could be recommended as a candidate for the compressive strength prediction tool of HSC
Summary
Concrete has been widely used worldwide with its economic, monolithic, modular, and durable advantages. Abobakr et al [13] developed an extreme learning machine (ELM) model to predict the compressive strength of high-strength concrete, and the results showed that the ELM method has good prediction accuracy and fast learning speed compared with the traditional back-propagation (BP) neural network. The LSTM model has exhibited good performance in the prediction of mechanical properties of concrete, but there is still relatively little research in concrete strength prediction, and in-depth analysis and research are needed before further popularization and application For this reason, this paper attempts to propose an LSTM-based prediction model to predict the HSC compressive strength and compare the prediction results with the conventional support vector regression (SVR) model.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call