Search for: All records

Abstract Fish fin rays constitute a sophisticated control system for ray-finned fish, facilitating versatile locomotion within complex fluid environments. Despite extensive research on the kinematics and hydrodynamics of fish locomotion, the intricate control strategies in fin-ray actuation remain largely unexplored. While deep reinforcement learning (DRL) has demonstrated potential in managing complex nonlinear dynamics; its trial-and-error nature limits its application to problems involving computationally demanding environmental interactions. This study introduces a cutting-edge off-policy DRL algorithm, interacting with a fluid–structure interaction (FSI) environment to acquire intricate fin-ray control strategies tailored for various propulsive performance objectives. To enhance training efficiency and enable scalable parallelism, an innovative asynchronous parallel training (APT) strategy is proposed, which fully decouples FSI environment interactions and policy/value network optimization. The results demonstrated the success of the proposed method in discovering optimal complex policies for fin-ray actuation control, resulting in a superior propulsive performance compared to the optimal sinusoidal actuation function identified through a parametric grid search. The merit and effectiveness of the APT approach are also showcased through comprehensive comparison with conventional DRL training strategies in numerical experiments of controlling nonlinear dynamics. 

In this study, the effects of antagonistic muscle actuation on the propulsion of a bilaminar-structure fish fin ray were investigated using a two-dimensional computational flow–structure interaction (FSI) model. The structure and material properties of the model were based on the realistic biological data of the sunfish fin. The effect of muscle actuation was modelled using root displacement offset between the two hemitrichs. Parametric FSI simulations were conducted by assuming a sinusoidal function of the offset over a cycle and varying the amplitude and phase difference between the actuations and pitching/plunging motions. The results show that the phase of muscle actuation is a critical factor affecting its effects. Three performance regions can be identified with different phase ranges, including a thrust-favour region, an efficiency-favour region and a thrust-efficiency-unfavour region. In each region, the relationships among the root actuations, fin-ray kinematics, vortex dynamics and resulting performance are studied and discussed. Furthermore, a strong positive correlation between the trailing–leading amplitude ratio and thrust coefficient as well as a negative relationship between the efficiency and angle of attack at the centre of mass of the fin ray are observed. 

This study presents a novel method that combines a computational fluid-structure interaction model with an interpretable deep-learning model to explore the fundamental mechanisms of seal whisker sensing. By establishing connections between crucial signal patterns, flow characteristics, and attributes of upstream obstacles, the method has the potential to enhance our understanding of the intricate sensing mechanisms. The effectiveness of the method is demonstrated through its accurate prediction of the location and orientation of a circular plate placed in front of seal whisker arrays. The model also generates temporal and spatial importance values of the signals, enabling the identification of significant temporal-spatial signal patterns crucial for the network’s predictions. These signal patterns are further correlated with flow structures, allowing for the identification of important flow features relevant for accurate prediction. The study provides insights into seal whiskers’ perception of complex underwater environments, inspiring advancements in underwater sensing technologies.