As engineering endeavors push the boundaries of material and design capabilities, the significance of understanding and mitigating fatigue in construction materials becomes paramount. This study specifically investigates the low-cycle fatigue performance of reinforced high-strength concrete (RHSC). Using rigorous data collection, we established a clear link between interpretable machine learning analysis and the fatigue properties of RHSC. A trained model was developed, yielding a straightforward formula tailored to low-cycle fatigue design considerations for RHSC. This model stands as a testament to the potential for marrying traditional engineering practices with advanced statistical techniques. Our results emphasize that, when appropriately applied, regression analysis can be instrumental in enhancing the durability and longevity of RHSC structures exposed to dynamic loadings. This research not only underscores the pivotal role of statistical methods in fatigue design but also champions the broader adoption of such techniques in evolving engineering landscapes.
Read full abstract