This paper addresses tracking control problems for autonomous underwater vehicle (AUV) systems with coupled nonlinear functions. For the first time, the radial basis function (RBF) is applied to the model reference adaptive control system, and the vehicle horizontal plane model is proposed. When the AUV movement is affected by the driving force, ocean resistance, and the force generated by the water current, the expected output of the AUV’s system is difficult to meet the expectations, making the AUV trajectory tracking problems challenging. There are two main options for finding suitable controllers for AUVs. The first is making the AUV model achieve better stability using a more complex controller. The second is the simpler controller structure, which can ensure faster system feedback. The RBF and model reference adaptive control (MEAC) system are combined to increase the number of hidden layers, increasing the AUV tracking stability. Because the embedded computing module of an AUV is a bit limited, 31 hidden layers are chosen to simplify the controller structures. A couple of Lyapunov functions are designed for the expected surge and sway velocities, and the vehicle tracking error gradually converges to (0,0). The controller design results are imported into the AUV actuator model by software, and after 0.64 s, the AUV tracking error is less than 1%. At last, the vehicle tracking experiments were carried out, showing that after 0.5 s, the AUV tracking error was less than 1%.

Ship propulsion performance is important for navigating. This study aims to enhance the propulsion performance of a 9500 DWT ship by integrating PBCFs into the hull–rudder–propeller–coupled system. A total of 27 PBCF models with different fin installation angles, radius ratio, and tilt angles are designed in the study. The computational fluid dynamics method is employed and a propeller open-water test is also performed to optimize the PBCF design, which is integrated into different coupled systems. The numerical results show that the PBCFs exhibit differential enhancements of propeller performance across system configurations with their efficiency changing from 4.05% to 2.87%. Moreover, the reliability of ship self-propulsion simulation is mutually validated through the combined BF (body force) and MRF (multi-reference frame) methods. Then, simulations were conducted using these two methods for the self-propulsion of a 9500 DWT ship at three different speeds. Finally, the results from using the MRF method show that the incorporation of PBCFs can reduce delivered power to propeller by 1.32% at different F_r.