Sloshing frequency of liquid in movable rectangular tank in various approaches supported with machine learning prediction

This study aims to improve the understanding of sloshing phenomena in partially filled movable storage systems, particularly in rectangular tanks where experimental data remain limited. A multi-approach methodology was employed by combining analytical and numerical solutions validated with experimental work and supported with various machine learning (ML) prediction approaches. The results were validated by conducting experimental investigations at three different liquid heights (150, 100, and 50) mm. The accuracy of the ML model in predicting the fundamental frequency was compared with three different error metrics and cross-validation, where the extreme gradient boost revealed more robust performance compared with support vector regression and artificial neural networks. The parametric investigations are presented, showing the impact of slope on the first fundamental frequency values for various nonstandard shapes of the liquid fillings, sloped from one side, from both sides, symmetrically, and asymmetrically beveled. The outputs revealed that such a combination of physics-based models with ML prediction provides further insight into sloshing phenomena and frequency responses at various circumstances.