Concrete materials compressive strength using soft computing techniques

• Published in: Multiscale and Multidisciplinary Modeling, Experiments and Design Vol. 7; no. 2; pp. 1209 - 1221
• Main Author: Lu, Chongyang
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.06.2024
• Subjects: Characterization and Evaluation of Materials; Engineering; Mathematical Applications in the Physical Sciences; Mechanical Engineering; Numerical and Computational Physics; Original Paper; Simulation; Solid Mechanics; Charged system search; Prediction of strength; Colliding bodies optimization; Particle swarm optimization; TSK model
• ISSN: 2520-8160; 2520-8179
• DOI: 10.1007/s41939-023-00276-4

A robust and reliable method to estimate the strength of concrete materials based on their mix parameters is required, considering their extensive use in construction over the last few decades. Consequently, the relationship between the compressive strength of the concrete and its mixed components is highly nonlinear. In this study, artificial intelligence techniques are applied to predict the compressive strength of cement-based concrete materials, whether they contain or do not contain metakaolin. A surrogate model, including the TSK fuzzy inference system, has been expanded to forecast the compressive strength of concretes based on experimental data available in the literature. Results indicate that the TSK model can reliably and robustly approximate the compressive strength of concretes. The TSK model has been optimized for mean square error (MSE) to train the inference system. In this regard, motion-based algorithms such as Particle Swarm Optimization (PSO), Colliding Bodies Optimization (CBO), and Charged System Search (CSS) have been used. The TSK fuzzy inference system, as a surrogate model, has been expanded to predict the compressive strength of concrete based on experimental data available in the literature.