Usage of Optimized Least Square SVR to Volume Expansion Estimation of Cement Paste Including Fly Ash and Mgo Expansive Additive

The limited hydration capacity and challenges related to delayed expansion prevent fly ash (𝐹𝐴) and 𝑀𝑔𝑂 expansive additive (𝑀𝐸𝐴) from being used significantly. Nonetheless, utilizing these two procedures in hydraulic mass concrete applications is a frequently used approach that yields favorable outcomes. To construct and assess machine learning-based algorithms to assess the volume expansion (𝑉𝑒) of cement paste, which consists of 𝐹𝐴 and 𝑀𝐸𝐴, 170 experimental findings from published studies are employed. A novel approach called least square support vector regression (𝐿𝑆𝑆𝑉𝑅) has been developed. The efficacy of 𝐿𝑆𝑆𝑉𝑅 is significantly impacted by its hyperparameters (𝑐 and 𝑔), which were fine-tuned using the Dwarf Mongoose Optimization Algorithm (𝐷𝑀𝑂𝐴) and the Equilibrium Optimization Algorithm (𝐸𝑂𝐴). Based on the results obtained, it can be inferred that there exists a significant potential for both 𝐿𝑆𝑆𝑉𝑅𝐸 and 𝐿𝑆𝑆𝑉𝑅𝐷 models to accurately predict the 𝑉𝑒 of cement paste that incorporates fly ash and 𝑀𝑔𝑂 expansive addition. In the training and testing phases, the Theil inequality coefficient (𝑇𝐼𝐶) values for 𝐿𝑆𝑆𝑉𝑅𝐸 are observed to be 0.0906 and 0.01043, which are comparatively higher than the 𝑇𝐼𝐶 values for 𝐿𝑆𝑆𝑉𝑅𝐷, which are 0.0382 and 0.0044, respectively. By predicting the volume expansion accurately, engineers can adjust the proportions of 𝐹𝐴 and 𝑀𝐸𝐴 to achieve desired expansion properties, improving the durability and stability of concrete structures. Accurate prediction models allow for better control of thermal stresses, reducing the risk of thermal cracking and extending the structure's lifespan.