Abstract
The study of stabilisation performance is a crucial consideration in the design of offshore floating platforms. For large floating structures, incorporating passive anti-roll tanks is a common technique for roll reduction. To investigate the feasibility of using ballast tanks for roll attenuation on the "Guo Hai Shi 1" platform, this study employs the internal tank theory to analyze the influence of four independent empty tanks, located around the platform, acting as anti-roll tanks with varying ballast water volumes. The results indicate that: (1) Different ballast water volumes within a single tank do not significantly affect the static stability parameters of the platform. (2) In regular wave simulations, the ballast tanks show limited effectiveness in reducing pitch motion along the wave incidence direction but effectively suppress coupled responses in other degrees of freedom. In the resonance case (Case 3), the minimum pitch occurs in Condition 1 at 10.56°, while the maximum pitch reaches 11.45° in Condition 2. Nevertheless, a 40% reduction in roll motion is achieved (3.36° in Condition 4 vs. 5.60° in Condition 1), along with a 24.5% reduction in yaw motion (39.22° in Condition 4 vs. 51.94° in Condition 1). (3) In irregular wave simulations, the ballast tanks effectively reduce the heave amplitude by up to 8.34% in sea state level 4 and 6.06% in sea state level 8, thereby enhancing its wave-following performance in the heave degree of freedom. (4) A CNN_BiLSTM_Attention algorithm is developed using hydrodynamic analysis generated datasets to predict the pitch motion time series of the platform under different ballast water conditions and sea states, while the model has a superior prediction performance (R² = 0.9658, RMSE = 0.5343, MAE = 0.3188, representing a 4.82% increase in R² and 30.31% reduction in RMSE compared to the original model). Future work will further explore the application of ballast tanks on floating platforms, with a focus on performance optimization and the development of advanced neural network models capable of predicting motion responses under various ballast configurations. Moreover, appropriate evaluation metrics will be established to assess the effectiveness of ballast tank designs. Efforts will also be directed towards integrating time-domain motion prediction using neural networks with control theories aimed at dynamically regulating ballast water volume to enhance platform stability.