Discovering concrete properties takes time, money, laboratory design, material preparation, and testing with adequate equipment at the right ages. As a consequence, in the concrete sector, solutions that minimize or reduce cost, time, and other downsides are essential. So, utilizing forecasting systems to compute concrete characteristics based on historical data is quite advantageous. Employing the rapid chloride penetration test (), this study proposed novel classification models for predicting chloride penetration into self-compacting concrete (). Designs for predicting the quantity of are constructed utilizing optimized random forest () classifications, which have not yet been outlined in the literature. The fundamental objective of this research is to build innovative combined classification models that combine with optimization techniques such as particle swarm optimization (), whale optimization algorithm (), and Harris hawks optimization () for better approximation of Using and five critical model hyperparameters were fine-tuned to provide the most powerful and dependable models ever. Considered combined classifications were trained by seven variables, namely cement content, fly ash, silica fume, a ratio of coarse and fine aggregates, water to cement ratio, and temperature. The findings reveal that in the training/testing phases, all three approaches had appropriate efficiency in estimating the reflecting the allowable correlation among actual and anticipated values. outperforms the other versions in both stages, with and of 0.9854 and 28.6 for the learning phase and 0.9645 and 41.44 for the assessment phase, respectively. Although the performance evaluator indices for are lower than and models, it has acceptable results with larger than 0.9243. Overall, the findings show that the method is more capable than and at calculating the ideal value of hyperparameters.
Read full abstract