Active sonar systems are one of the most commonly used acoustic devices for underwater equipment. They use observed signals, which mainly include target echo signals and reverberation, to detect, track, and locate underwater targets. Reverberation is the primary background interference for active sonar systems, especially in shallow sea environments. It is coupled with the target echo signal in both the time and frequency domain, which significantly complicates the extraction and analysis of the target echo signal. To combat the effect of reverberation, an attention and cepstrum analysis-guided network (ACANet) is proposed. The baseline system of the ACANet consists of a one-dimensional (1D) convolutional module and a reconstruction module. These are used to perform nonlinear mapping and to reconstruct clean spectrograms, respectively. Then, since most underwater targets contain multiple highlights, a cepstrum analysis module and a multi-head self-attention module are deployed before the baseline system to improve the reverberation suppression performance for multi-highlight targets. The systematic evaluation demonstrates that the proposed algorithm effectively suppresses the reverberation in observed signals and greatly preserves the highlight structure. Compared with NMF methods, the proposed ACANet no longer requires the target echo signal to be low-rank. Thus, it can better suppress the reverberation in multi-highlight observed signals. Furthermore, it demonstrates superior performance over NMF methods in the task of reverberation suppression for single-highlight observed signals. It creates favorable conditions for underwater platforms, such as unmanned underwater vehicles (UUVs), to carry out underwater target detection and tracking tasks.
A defense platform is usually based on two methods to make underwater acoustic warfare strategy decisions. One is through Monte-Carlo method online simulation, which is slow. The other is by typical empirical (database) and typical back-propagation (BP) neural network algorithms based on genetic algorithm (GA) optimization, which is less accurate and less robust. Therefore, this paper proposes a method to build an optimal underwater acoustic warfare feedback system using a three-layer GA-BP neural network and dropout processing of the neural network to prevent overfitting, so that the three-layer GA-BP neural network has adequate memory capability while still having suitable generalization capability. This method improves the accuracy and stability of the defense platform in making underwater acoustic warfare strategy decisions, thus increasing the survival probability of the defense platform in the face of incoming torpedoes. This paper uses the optimal underwater acoustic warfare strategies corresponding to incoming torpedoes with different postures as the sample set. Additionally, it uses a three-layer GA-BP neural network with an overfitting treatment for training. The prediction results have less error than the typical single-layer GA-BP neural network, and the survival probability of the defense platform improves by 6.15%. This defense platform underwater acoustic warfare strategy prediction method addresses the impact on the survival probability of the defense platform due to the decision speed and accuracy.
Dolphin signals are effective carriers for underwater covert detection and communication. However, the environmental and cost constraints terribly limit the amount of data available in dolphin signal datasets are often limited. Meanwhile, due to the low computational power and resource sensitivity of Unmanned Underwater Vehicles (UUVs), current methods for real-time generation of dolphin signals with favorable results are still subject to several challenges. To this end, a Masked AutoEncoder Generative Adversarial Network (MAE-GAN) model is hereby proposed. First, considering the few-shot condition, the dataset is extended by using data augmentation techniques. Then, to meet the low arithmetic constraint, a denoising autoencoder with a mask is used to obtain latent codes through self-supervised learning. These latent codes are then utilized in Conditional Wasserstein Generative Adversarial Network-Gradient Penalty (CWGAN-GP) to generate a whistle signal model for the target dataset, fully demonstrating the effectiveness of the proposed method for enhancing dolphin signal generation in data-limited scenarios. The whistle signals generated by the MAE-GAN and baseline models are compared with actual dolphin signals, and the findings indicate that the proposed approach achieves a discriminative score of 0.074, which is 28.8% higher than that of the current state-of-the-art techniques. Furthermore, it requires only 30.2% of the computational resources of the baseline model. Overall, this paper presents a novel approach to generating high-quality dolphin signals in data-limited situations, which can also be deployed on low-resource devices. The proposed MAE-GAN methods provide a promising solution to address the challenges of limited data and computational power in generating dolphin signals.
As acoustic decoys can simulate the scale of the target through orderly control of the echo delay, simulated acoustic decoys have scale characteristics similar to those of the scaled target. Consequently, simulated acoustic decoys make it difficult for active acoustic homing torpedoes to recognize acoustic decoys through traditional echo broadening or apparent angle. This will lead to a decrease in the anti-interference capability of torpedoes. In combat, acoustic decoys deceive torpedoes and deviate from the tracking course so that torpedoes cannot find the real target, or waste the range, eventually failing to strike the target and failing in combat. The accurate underwater target scale recognition of active acoustic homing torpedoes is considered a difficult technique. In this paper, we propose a target recognition method based on the correlation between target echo broadening and apparent angle. This specific simulation example shows that conventional target scale recognition methods cannot distinguish between suspended and homing acoustic decoys with virtual scale. By contrast, the target scale recognition method proposed in this paper can accurately distinguish between suspended and homing acoustic decoys with virtual scale at close range, under non-positive transverse port angle conditions. This method improves the anti-interference capability of torpedoes. In addition, it can improve the accuracy of active sonar recognition scale targets of ships, which guide active sonar target recognition.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.