Estimating compressive strength of coral sand aggregate concrete in marine environment by combining physical experiments and machine learning-based techniques.

To widely apply coral sand aggregate (CSA) concrete in practical ocean engineering, it requires to have a precious evaluation of its compressive strength in marine environment. In the study, 1280 triaxial shear tests on concrete containing different content and properties of CSA in marine environment was conducted. Based on the test results, a database was established, and a unique machine learning method was developed via combining the Logic Development Algorithm (LDA) with the ensemble technique of Adaptive Boosting Algorithm (AdaBoost) and Artificial Neural Network (ANN). This novel approach represents the first attempt to utilize this model for estimating the compressive strength of CSA concrete. To validate the applicability of the proposed approach, five conventional machine learning algorithms were also built as a reference, including LDA optimized ANN and Support Vector Machine, Particle Swarm Optimization Algorithm and Genetic Algorithm optimized AdaBoost-ANN. The research findings indicate: Firstly, the AdaBoost-ANN model optimized by LDA outperforms than the conventional models in terms of predictive accuracy and efficiency; For example, for the LDA-AdaBoost-ANN, LDA-SVM, LDA-ANN, GA-AdaBoost-ANN and PSO-AdaBoost-ANN model, their Root Mean Square Error (RMSE) is 2.73, 5.82, 6.97, 7.47 and 3.85 on testing datasets respectively; for the LDA-AdaBoost-ANN, LDA-SVM, LDA-ANN, GA-AdaBoost-ANN and PSO-AdaBoost-ANN model, their Mean Absolute Error (MAE) is 4.8, 11.34, 12.5, 9.86 and 8.45 on testing datasets respectively; for the LDA-AdaBoost-ANN, LDA-SVM, LDA-ANN, GA-AdaBoost-ANN and PSO-AdaBoost-ANN model, their Mean Absolute Percentage Error (MAPE) is 6.26%, 23.36%, 24.35%, 10.19% and 13.79% on testing datasets respectively. Secondly, the sensitivity analysis by using the novel model reveals that confining pressure, CSA content and immersion period in seawater have relatively high impact on the compressive strength. Thirdly, an analytical formula was established based on the novel algorithm. • 1280 triaxial shear tests were performed on coral sand aggregate concrete. • A unique machine learning model was developed based on the experimental database. • The compressive strength of the concrete was assessed by using the model. [ABSTRACT FROM AUTHOR]