The underwater acoustic target signal is affected by factors such as the underwater environment and the ship’s working conditions, causing the generalization of the recognition model is essential. This study is devoted to improving the generalization of recognition models, proposing a feature extraction module based on neural network and time-frequency analysis, and validating the feasibility of the model-based transfer learning method. A network-based filter based on one-dimensional convolution is built according to the calculation mode of the finite impulse response filter. An attention-based model is constructed using the convolution network components and full-connection components. The attention-based network utilizes convolution components to perform the Fourier transform and feeds back the optimization gradient of a specific task to the network-based filter. The network-based filter is designed to filter the observed signal for adaptive perception, and the attention-based model is constructed to extract the time-frequency features of the signal. In addition, model-based transfer learning is utilized to further improve the model’s performance. Experiments show that the model can perceive the frequency domain features of underwater acoustic targets, and the proposed method demonstrates competitive performance in various classification tasks on real data, especially those requiring high generalizability.

Target classification and recognition have always been complex problems in underwater acoustic signal processing because of noise interference and feature instability. In this paper, a robust feature extraction method based on multi-task learning is proposed, which provides an effective solution. Firstly, an MLP-based network model suitable for underwater acoustic signal processing is proposed to optimize feature extraction. Then, multi-task learning is deployed on the model in hard parameter-sharing so that the model can extract anti-noise interference features and embed prior feature extraction knowledge. In the model training stage, the simultaneous training method enables the model to improve the robustness and representation of classification features with the knowledge of different tasks. Furthermore, the optimized classification features are sent to the classification network to complete target recognition. The proposed method is evaluated by the dataset collected in the real environment. The results show that the proposed method effectively improves recognition accuracy and maintains high performance under different noise levels, which is better than popular methods.

The artificial lateral line (ALL), comprising distributed flow sensors, has been successful in sensing motion states of bioinspired underwater robots like robotic fish. However, its application to robots driven by rotating propellers remains unexplored due to the complexity of propeller wake flow. This article investigates the feasibility of using ALL to sense propeller wake for underwater robot leader-follower formation. To estimate the lateral motion states of a leader propeller, this article designs a multioutput deep learning network that extracts temporal and spatial features from distributed pressure measurements of propeller wake. Extensive experiments are conducted on a designed testbed, the results of which validate the effectiveness of the proposed propeller wake sensing method.

In the field of underwater acoustic signal processing, broadband array signal processing is an important research issue, which is more complex than that of narrowband. Broadband passive localization of underwater acoustic sources is investigated in this study. In order to improve the ability to locate multiple radiation sources which are emitted from ships, the orthogonal propagator method (OPM) is proposed to estimate direction of arrival (DOA) for the target. Based on the theory of spatial spectrum estimation, the linear decomposition of the covariance matrix is adopted to form the orthogonal propagator, and the spatial spectrum is constructed according to orthogonality of subspaces. Then, the directions of ship radiation noises are determined by searching the extreme points of the spatial spectrum. For broadband underwater acoustic signals, the non-coherent subspace method is used to average the effective frequency points in bandwidth to reduce noise interference, and OPM algorithm operating in broadband underwater acoustic signal, on arbitrary sonar array, is derived. In order to verify this method, numerical simulations are conducted to test its performance in localization accuracy, beam width and spatial resolution. During the simulations, a uniform linear array consisting of 96 elements is designed. Additionally, comparisons between the proposed method and conventional beamforming technique are conducted. Comparison results show that the OPM method performs better in spatial directivity and spatial resolution.