Design and experimental investigation of a GA-based control strategy for a low-speed fin stabilizer

• Published in: Ocean engineering Vol. 218; p. 108234
• Main Authors: Jiguang, Song, Lihua, Liang, Songtao, Zhang, Jiming, Wang
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 15.12.2020
• Subjects: Fin stabilizer; Genetic algorithm; Low-speed stabilization; Roll prediction; Ship model experiment; Roll prediction; Fin stabilizer; Ship model experiment; Genetic algorithm; Low-speed stabilization
• ISSN: 0029-8018; 1873-5258
• DOI: 10.1016/j.oceaneng.2020.108234

Fin stabilizers are widely used for to reduce ship rolling. However, reducing rolling motion at low ship speeds remains a challenge because of uncertainties in ship dynamics, transient and nonlinear hydrodynamic forces of fin. Also the phase difference between the force and fin angle is highly sensitive to ship speed. Herein, an improved control strategy is proposed to avoid these problems and to enhance the anti-roll effect of fin stabilizers. A prediction algorithm based on the radial base function artificial neural network (RBF-ANN) is first used to forecast ship rolling motion, and then the disturbing moment and roll time series are estimated. Uncertainty of disturbances in roll dynamics are encapsulated in the predictive algorithm. Moreover, an inversion method based on the genetic algorithm can be applied to minimize differences between the disturbing moment and stabilizing moment. A ship model is introduced to verify the proposed control strategy. Forced roll tests were carried out using the ship model to determine the optimal fin profile and maximum control moment. Anti-roll experiments and simulations were performed to verify the improved control strategy. •RBF-ANN-based roll prediction unit to estimate disturbing moment.•Virtual middle control variable calculates fin angle through object function.•GA-based inversion can solve object function to compute fin angle.•Improved GA-based control strategy for fin stabilizer verified by experiment.