In the field of underwater acoustic field prediction, numerical simulation methods and machine learning techniques are two commonly used methods. However, the numerical simulation method requires grid division. The machine learning method can only sometimes analyze the physical significance of the model. To address these problems, this paper proposes an underwater acoustic field prediction method based on a physics-informed neural network (UAFP-PINN). Firstly, a loss function incorporating physical constraints is introduced, incorporating the Helmholtz equation that describes the characteristics of the underwater acoustic field. This loss function is a foundation for establishing the underwater acoustic field prediction model using a physics-informed neural network. The model takes the coordinate information of the acoustic field point as input and employs a fully connected deep neural network to output the predicted values of the coordinates. The predicted value is refined using the loss function with physical information, ensuring the trained model possesses clear physical significance. Finally, the proposed prediction model is analyzed and validated in two dimensions: the two-dimensional acoustic field and the three-dimensional acoustic field. The results show that the mean square error between the prediction and simulation values of the two-dimensional model is only 0.01. The proposed model can effectively predict the distribution of the two-dimensional underwater sound field, and the model can also predict the sound field in the three-dimensional space.

GNSS/INS can provide position, attitude, and velocity (PAV) information for shipborne platforms. However, if the ship has a long-term linear motion or a stationary state, and is under the combined actions of sea surface swells, there will be a situation of sideslip and drift; if the ship is traveling slowly or shaking violently, the attitude calculation will not be completed. In the above situation, the traditional single-antenna GNSS/INS measurement mode is not suitable, and the attitude observability is poor; the heading angle attitude information, especially, will gradually diverge. Unreliable information will directly lead to a significant increase in underwater positioning errors. In this paper, a multi-antenna GNSS/INS combination algorithm is developed and used to provide high-precision PAV information, and is thereby able to obtain high-precision underwater positioning results. The experimental results show that the method has improved the acquisition of position and velocity in the horizontal direction and the accuracy of navigation attitude measurement. In particular, the attitude measurement accuracy in the 3 degrees of freedom (DoF) are improved by 10.1% (roll), 8.6% (pitch), and 29.3% (yaw).

The utilization of multibeam sonar systems has significantly facilitated the acquisition of underwater bathymetric data. However, efficiently processing vast amounts of multibeam point cloud data remains a challenge, particularly in terms of rejecting massive outliers. This paper proposes a novel solution by implementing a cone model filtering method for multibeam bathymetric point cloud data filtering. Initially, statistical analysis is employed to remove large-scale outliers from the raw point cloud data in order to enhance its resistance to variance for subsequent processing. Subsequently, virtual grids and voxel down-sampling are introduced to determine the angles and vertices of the model within each grid. Finally, the point cloud data was inverted, and the custom parameters were redefined to facilitate bi-directional data filtering. Experimental results demonstrate that compared to the commonly used filtering method the proposed method in this paper effectively removes outliers while minimizing excessive filtering, with minimal differences in standard deviations from human-computer interactive filtering. Furthermore, it yields a 3.57% improvement in accuracy compared to the Combined Uncertainty and Bathymetry Estimator method. These findings suggest that the newly proposed method is comparatively more effective and stable, exhibiting great potential for mitigating excessive filtering in areas with complex terrain.

With the aim of solving the problem of identifying complex underwater acoustic targets using a single signal feature in the Time–Frequency (TF) feature, this paper designs a method that recognizes the underwater targets based on the Delay-Doppler joint feature. First, this method uses symplectic finite Fourier transform (SFFT) to extract the Delay-Doppler features of underwater acoustic signals, analyzes the Time–Frequency features at the same time, and combines the Delay-Doppler (DD) feature and Time–Frequency feature to form a joint feature (TF-DD). This paper uses three types of convolutional neural networks to verify that TF-DD can effectively improve the accuracy of target recognition. Secondly, this paper designs an object recognition model (TF-DD-CNN) based on joint features as input, which simplifies the neural network’s overall structure and improves the model’s training efficiency. This research employs ship-radiated noise to validate the efficacy of TF-DD-CNN for target identification. The results demonstrate that the combined characteristic and the TF-DD-CNN model introduced in this study can proficiently detect ships, and the model notably enhances the precision of detection.