In ocean remote sensing missions, recognizing an underwater acoustic target is a crucial technology for conducting marine biological surveys, ocean explorations, and other scientific activities that take place in water. The complex acoustic propagation characteristics present significant challenges for the recognition of underwater acoustic targets (UATR). Methods such as extracting the DEMON spectrum of a signal and inputting it into an artificial neural network for recognition, and fusing the multidimensional features of a signal for recognition, have been proposed. However, there is still room for improvement in terms of noise immunity, improved computational performance, and reduced reliance on specialized knowledge. In this article, we propose the Residual Attentional Convolutional Neural Network (RACNN), a convolutional neural network that quickly and accurately recognize the type of ship-radiated noise. This network is capable of extracting internal features of Mel Frequency Cepstral Coefficients (MFCC) of the underwater ship-radiated noise. Experimental results demonstrate that the proposed model achieves an overall accuracy of 99.34% on the ShipsEar dataset, surpassing conventional recognition methods and other deep learning models.

Due to the increasing demand for modern underwater detection, underwater acoustic target recognition (UATR) has always been exploring. By demodulating the underwater target radiated noise (UTRN) received by the passive sonar, the discrete line spectrums reflecting the physical characteristics of the ship can be obtained. In the article, a one-dimensional convolutional neural network (1D-CNN) was proposed to recognize the line spectrums of Detection of Envelope Modulation on Noise (DEMON) spectrum of UTRN. Datasets with different Doppler shifts and signal-to-noise ratios (SNRs) were designed to ensure that the 1D-CNN has an outstanding generalization ability by combining the training and the evaluation process. By exploring a design method of the Field Programmable Gate Array (FPGA)-based CNN model, the DEMON spectrum recognition algorithm based on 1D-CNN was optimized and mapped onto the FPGA embedded platform, which greatly improved the calculation speed while ensuring accuracy. Experimental results show that it is suitable for practical engineering applications, and the recognition process is robust and real-time.

Due to the complexity of the underwater environment, underwater acoustic target recognition (UATR) has always been challenging. Although deep neural networks (DNN) have been used in UATR and some achievements have been made, the performance is not satisfactory when recognizing underwater targets with different Doppler shifts, signal-to-noise ratios (SNR), and interferences. In the paper, a one-dimensional convolutional neural network (1D-CNN) was proposed to recognize the line spectrums of Detection of Envelope Modulation on Noise (DEMON) spectrums of underwater target-radiated noise. Datasets of targets with different Doppler shifts, SNRs, and interferences were designed to evaluate the generalization performance of the proposed CNN. Experimental results show that compared with traditional multilayer perceptron (MLP) networks, the 1D-CNN model better performs in recognition of targets with different Doppler shifts and SNRs. The outstanding generalization ability of the proposed model shows that it is suitable for practical engineering applications.

Spread-spectrum time-domain reflectometry (SSTDR) is used to detect cable faults online. In this study, the signal model of SSTDR cable fault detection was established, and two factors, namely the incident leakage signal and the impedance mismatch between the device and the cable, that affect fault detection performance were analyzed. In this study, an improved method of SSTDR cable fault detection was proposed by combining the transmitter–receiver isolation and trapper. Calibration was performed to obtain the optimal parameters of the circuit. The proposed method can reduce the signal energy leakage from the transmitter to the receiver circuit and suppress the impedance mismatch between the device and the cable. The parameter calibration process of transmitter–receiver isolation and trapper, and the influence of various parameters on the performance of cable fault detection were detailed experimentally. The experiments revealed that the improved SSTDR fault detection can detect faults at various distances. At frequencies of 20, 10, and 5 MHz, the fault detection distance reached 68, 110, and 210 m, respectively. Test results revealed the effectiveness of the proposed method.

The acquisition of target data for underwater acoustic target recognition (UATR) is difficult and costly. Although deep neural networks (DNN) have been used in UATR, and some achievements have been made, the performance is not satisfactory when recognizing underwater targets with different Doppler shifts, signal-to-noise ratios (SNR), and interferences. On the basis of this, this paper proposed a Siamese network with two identical one-dimensional convolutional neural networks (1D-CNN) that recognize the detection of envelope modulation on noise (DEMON) spectra of underwater target-radiated noise. The parameters of underwater samples were diverse, but the states of the collected samples were very homogeneous. Traditional underwater target recognition uses multi-state samples to train the network, which is costly. This article trained the network using samples from a single state. The expectation was to be able to identify samples with different parameters. Datasets of targets with different Doppler shifts, SNRs, and interferences were designed to evaluate the generalization performance of the proposed Siamese network. The experimental results showed that when recognizing samples with Doppler shifts, the classification accuracy of the proposed network reached 95.3%. For SNRs, the classification accuracy reached 85.5%. The outstanding generalization ability of the proposed model shows that it is suitable for practical engineering applications.

In order to improve the detection performance of active sonar and make up for the shortcomings of pulsed active sonar (PAS), linear frequency-modulated continuous wave (LFMCW) was applied in continuous active sonar (CAS). The expression of transmitting waveform was presented, and the echo model of underwater moving targets was established. To detect the LFMCW echoes, the received signal was first demodulated by the transmitting signal, resulting in a de-chirped signal. Unlike radar system, the target velocity of active sonar was not negligible, comparing with the sound velocity in water, and the de-chirped signal was also a LFM signal, whose chirp rate and frequency were related with the velocity and distance of the target. Fractional Fourier Transform (FRFT), a time-frequency analysis method which is generally used to detect and estimate LFM signals, was proposed to detect and estimate the de-chirped signal. In multiple targets situation, "CLEAN" algorithm was proposed to solve the problem of the detection interference from strong targets to weak targets. Simulations show that LFMCW active sonar with the de-chirp-FRFT receiver can get much higher processing gain than conventional PAS with a matched filter (MF) receiver. The resolutions of velocity and distance with the de-chirp-FRFT algorithm fully meets the needs of underwater target detection. The simulation result also shows that the proposed CLEAN algorithm can detect LFMCW multi-target echoes effectively.