Detection of acoustic tonals from surfaces and underwater vehicles is important for passive sonar systems. Enhancements of the tonals are usually necessary in passive sonar prior to detections. Conventionally, passive sonars employ adaptive line enhancers (ALE) in order to realise enhancements of the tonals. However, ALEs have requirements on their input signal‐to‐noise ratios (SNR). When the SNR inputs are too low, the ALEs cannot perform well. Therefore, for the purpose of overcoming the limitations of the SNR inputs to ALEs, this study proposes to enhance tonals using unsupervised deep‐learning techniques. The proposed deep‐learning‐based line enhancer (DLE) is based on an autoencoder neural network. The simulation results show that when the input SNR is −28 dB, the proposed DLE still achieves an SNR gain of 15 dB. However, the reference ALE fails. The experimental results also demonstrate the superiority of the proposed DLE.

Effective extraction of target features has always been a key issue in target recognition technology in the field of signal processing. Traditional deep learning algorithms often require extensive data for pre‐training models to ensure the accuracy of feature extraction. Moreover, it is challenging to completely remove noise due to the complexity of the underwater environment. A Time‐Delay Autoencoder (TDAE) is employed to extract ship‐radiated noise characteristics by leveraging the strong coherent properties of line spectrum. This approach eliminates the need for previous data to adaptively develop a nonlinear model for line spectrum extraction. The test data was processed using three distinct approaches, and plots of recognition accuracy curves at various signal‐to‐noise ratios were made. On the dataset utilised in the research, experimental results show that the proposed approach achieves over 75% recognition accuracy, even at a signal‐to‐noise ratio of −15 dB.

Recently, the array-invariant method was proposed to passively localize sources of opportunity in shallow water. It exploits multiple arrivals which are different in terms of beam angle and travel time. Conventional plane-wave beamforming in the existing array-invariant method is used to obtain beam-time migration. The resolution capability of conventional plane-wave beamforming is determined by array aperture, which, however, limits the localization accuracy of the existing array-invariant method. To improve the localization accuracy, this study proposes the use of two-dimensional (2D) deconvolution to obtain a better beam-time migration than in conventional plane-wave beamforming. Our simulation with a small horizontal array showed that the range estimation error of the proposed array-invariant method based on 2D deconvolution was only one-third of that of the existing method. The experiment also demonstrated the validity of our proposed method.