Underwater target recognition remains a challenging task due to the complex and changeable environment. There have been a huge number of methods to deal with this problem. However, most of them fail to hierarchically extract deep features. In this paper, a novel deep learning framework for underwater target classification is proposed. First, instead of extracting features relying on expert knowledge, sparse autoencoder (AE) is utilized to learn invariant features from the spectral data of underwater targets. Second, stacked autoencoder (SAE) is used to get high-level features as a deep learning method. At last, the joint of SAE and softmax is proposed to classify the underwater targets. Experiment results with the received signal data from three different targets on the sea indicated that the proposed approach can get the highest classification accuracy compared with support vector machine (SVM) and probabilistic neural network (PNN).

Time-frequency (T-F) masking is an effective method for stereo speech source separation. However, reliable estimation of the T-F mask from sound mixtures is a challenging task, especially when room reverberations are present in the mixtures. In this paper, we propose a new stereo speech separation system where deep neural networks are used to generate soft T-F mask for separation. More specifically, the deep neural network, which is composed of two sparse autoencoders and a softmax regression, is used to estimate the orientations of the dominant source at each T-F unit, based on low-level features, such as mixing vector (MV), interaural level, and phase difference (IPD/ILD). The dataset for training the networks was generated by the convolution of binaural room impulse responses (RIRs) and clean speech signals positioned in different angles with respect to the sensors. With the training dataset, we use unsupervised learning to extract high-level features from low-level features and use supervised learning to find the nonlinear functions between high-level features and the orientations of dominant source. By using the trained networks, the probability that each T-F unit belongs to different sources (target and interferers) can be estimated based on the localization cues which is further used to generate the soft mask for source separation. Experiments based on real binaural RIRs and TIMIT dataset are provided to show the performance of the proposed system for reverberant speech mixtures, as compared with a model-based T-F masking technique proposed recently.

Autonomous underwater vehicles (AUVs) are an important equipment for ocean investigation. Actuator fault diagnosis is essential to ensure the sailing safety of AUVs. However, the lack of failure data for training due to unknown ocean environments and unpredictable failure occurrences is challenging for fault diagnosis. In this paper, a meta-self-attention multi-scale convolution neural network (MSAMS–CNN) is proposed for the actuator fault diagnosis of AUVs. Specifically, a two-dimensional spectrogram of the vibration signals obtained by a vibration sensor is used as the neural network’s inputs. The diagnostic model is fitted by executing a subtask-based gradient optimization procedure to generate more general degradation knowledge. A self-attentive multi-scale feature extraction approach is used to utilize both global and local features for learning important parameters autonomously. In addition, a meta-learning method is utilized to train the diagnostic model without a large amount of labeled data, which enhances the generalization ability and allows for cross-task training. Experimental studies with real AUV data collected by vibration sensors are conducted to validate the effectiveness of the MSAMS–CNN. The results show that the proposed method can diagnose the rudder and thruster faults of AUVs in the cases of few-shot diagnosis.

Forward-looking sonar (FLS) image segmentation plays a significant role in ocean engineering. However, the existing image segmentation algorithms present difficulties in extracting features from FLS images with weak semantic information, complex backgrounds and strong environmental noises. Convolutional neural networks (CNNs) have demonstrated remarkable capabilities in semantic segmentation tasks, but the locality of convolution limits the ability to extract global context and long-range semantic information. The effective extraction of global contextual information is indispensable for achieving accurate segmentation results in sonar image processing. In this paper, we propose a novel semantic segmentation architecture for forward-looking sonar images called SonarNet. SonarNet is based on a hybrid CNN-Transformer-HOG framework and comprises four modules. 1) The Global-Local Encoder can extract both global and detailed feature information of the underwater target; 2) the Network Decoder converts the high-semantic feature map into a pixel-level classification; 3) as a bridge between dual encoders, the Global-Local Fusion Module ensures semantic consistency between different encoders; 4) the HOG Feature Encoder and Fusion can extract traditional manual features and perform feature alignment. We conducted comprehensive ablation experiments to validate the efficacy of the designed modules. Finally, experimentation revealed that SonarNet significantly outperforms other CNN-based and CNN-Transformer FLS image segmentation methods.

A high-temperature acoustic field measurement and analysis system (HTAFS) was self-designed and developed to achieve real-time acoustic field analysis and quantitative cavitation characterization within high-temperature liquids. The acoustic signal was acquired by a high-temperature resistant waveguide and calibrated by separate compensation of line and continuous spectra to eliminate frequency offsets. Moreover, a new method was proposed to derive from the continuous-spectrum sound intensity and line-spectrum sound intensity in the frequency band above 1.5 times the fundamental frequency to characterize the intensity of transient cavitation and stable cavitation. The acoustic field characteristics within solidifying liquid Al-7 %Si alloy were successfully determined by this system. With the increase of ultrasound amplitude, the acoustic pressure in the alloy melt increased to be stable, the transient cavitation intensity first rose and then declined, and the stable cavitation intensity remained unchanged. Combined with the structural evolution of the primary α(Al) phase, the transient cavitation intensity was determined to be the dominant factor for the ultrasound-induced grain refinement effect.