To enhance ship path planning and obstacle avoidance in complex marine environments while improving the efficiency and safety of ship navigation, this study proposes a novel method based on an improved DDPG algorithm.

A priority experience replay mechanism, guided by a path importance score, is introduced to enhance the utilization efficiency of important experience in the learning process. A self-attention mechanism is integrated into the actor-critic network to enhance its ability to capture environmental features. In addition, the network architecture is optimized by using the dueling deep Q-network to improve the accuracy of value function estimation.

Simulation results in the East China Sea and the Indian Ocean show that, compared with the DDPG and A* algorithms, the improved algorithm achieves significant improvements in path length, inflection points and collision avoidance. For example, in the East China Sea, the improved algorithm reduces path length by 0.75%, inflection points by 26.92%, and collisions by 15.80% compared with the DDPG algorithm; and reduces path length by 4.59% and inflection points by 42.42% compared with the A* algorithm.

The improved algorithm is superior to DDPG and traditional A* algorithms in marine environments of varying complexity, demonstrating its significant advantages and strong generalizability. It provides a reference for intelligent decision-making in ship navigation.

The purpose of this paper is to explore an efficient and accurate numerical calculation method for cabin transient noise under transient excitation.

First, numerical calculation models of cabin transient noise in the time domain and frequency domain under the vibro-acoustic coupling mode are established respectively. By comparing the numerical calculation results of cabin transient noise under transient acoustic excitation and transient acoustic-force excitation, the differences between the two methods in computational accuracy, efficiency, solution scale, and modeling difficulty are discussed. Considering the broadband characteristics of transient excitation, a full-band numerical calculation method for cabin transient noise under multi-source excitation is given and a real ship test is carried out.

The results show that the total level error of cabin transient noise obtained by the test results and recommended numerical method is within 3 dB, which verifies the effectiveness of the numerical method proposed in this paper. The computational accuracy of the time-domain and frequency-domain methods given in this paper are comparable, with the time-domain method showing higher computational efficiency than that of the frequency-domain method, but also higher modeling difficulty. The influence range of transient air noise sources is smaller than that of transient structural vibration sources.

The method proposed herein can accurately predict the transient response of large cruise ship cabins and transient noise in the design stage of ship cabins, thereby reducing the design cost.

Based on the acoustic black hole and anti-resonance theories, this paper presents an elastic anti-resonant energy harvester which is suitable for multi-frequency domain vibration reduction.

By adjusting the structural parameters of the energy harvester, low and medium frequency vibrations on the transmission path and the source of the power equipment can be reduced accurately, addressing the disadvantage of the traditional acoustic black hole structure with poor low-frequency range vibration reduction effects. The Rayleigh method is used to derive the fundamental frequency calculation formula of the energy harvester. The designed multilayer energy harvester is then applied to a standard ship engine room panel and its vibration reduction effect is verified. In accordance with the research results, the vibration reduction rules and effect are analyzed, and corresponding improvements are made.

The average vibration speed level near the first resonance frequency of the engine room panel with a nine-layer energy harvester group is reduced by about 8.7 dB, and the peak value of the frequency response curve shows a broadband reduction. By adjusting the size and position of the added mass, the improved multi-mode energy harvester can participate in the vibration reduction of the structure.

Compared with the traditional embedded two-dimensional acoustic black hole structure, the elastic anti-resonant energy harvester proposed herein features small additional mass and non-destructive structural strength, and can be designed in any combination, giving it good application value for targeted ship vibration and noise reduction in the low frequency band.

This paper aims to reveal the influence law of cushion pressure on the underwater noise radiation of air cushion vehicles (ACVs).

An ACV is taken as a computational example. First, the forming process of the skirt under cushion pressure is simulated according to the Newton–Raphson iteration method. Second, a numerical model considering skirt-air cushion-water coupling is established via the vibro-acoustic finite element method (FEM) and calibrated based on modal tests. Third, comparisons are made of the sound power level (SWL) of the ACV's underwater radiation noise under different pressure levels on the skirt and different cushion depression depths.

Underwater radiation noise is found to be positively correlated with air cushion pressure. The overall SWL increases by nearly 0.97 dB while the air cushion pressure increases by 1000 Pa. Increasing the stiffness of the skirt can effectively reduce the underwater radiation noise in the low frequency band, and increasing the cushion depression depth will increase the peak value of the SWL in the higher frequency band, and make the peak position shift to the low frequency direction.

The influence law of air cushion pressure revealed in this paper has important guiding significance for evaluating and numerically predicting the acoustic performance of ACVs.