Enhancing underwater target localization through proximity-driven recurrent neural networks

Aiming at the issue that in view of the common underwater target electric field detection and localization technology, its electric signal attenuation in the water is faster and easy to be affected by the underwater complex environmental noise, which affects the detection performance of the problem, the paper carries out a research based on active and passive electric field detection and localization technology. First, a target electric field detection and localization system is designed. Then, two sets of basis functions in the horizontal and vertical directions are derived based on this detection system model, and then the detection and localization of underwater targets are realized by energy calculation. Finally, the image fusion algorithm of wavelet transform is adopted to further realize the detection and localization of underwater targets in a two-dimensional plane through the form of a heatmap. All the above contents are experimentally verified by simulation tools, and the experimental results show that compared with the traditional electric field detection and localization techniques for underwater targets, the method in this paper has better performance in the environment with a lower signal-to-noise ratio.

Underwater imaging plays an important role in sonar detection. Compressive sensing can achieve high-precision airborne sound source localization with a small computational effort, but underwater target localization and ranging have not been fully achieved. This study proposes a metamaterial-based compressive sensing imaging method for underwater sound source localization and target imaging. To overcome the poor wave manipulation performance caused by the impedance difference between water and the structure, a strong coupling interaction between the flexible structure and the medium is introduced to reduce reflection and scattering, dramatically improving the acoustic signal transmission amplitude via the resonance mechanism. Analytical and numerical results show that this device can achieve directional irrelevant modulation of incident acoustic waves in different directions. Besides, the multi-information fusion compressive sensing method and dual-sensor joint compressive sensing method can reconstruct the sound source information from the received mixed signals. Experimental results show that the metamaterial-based compressive sensing imaging device realizes the perception and localization of a single sound source underwater in multiple directions. The metamaterial-based hydroacoustic imaging device eliminates the dependence on large-caliber arrays and complex control systems, thus opening the way to establish a sonar system with low cost and high precision.

Considering the limited availability of usable signal sources and the instability of sensor measurements in underwater environments, this paper proposes a novel underwater target enhanced localization using distributed estimation and search optimization. First, a dual mapping from the signal domain to the position domain is established using time-of-arrival measurements between acoustic base stations and underwater beacons. Second, a singular value decomposition-enhanced unscented Kalman filter is introduced to improve the stability of the covariance matrix. Combined with a strong tracking mechanism, the filter gain is adaptively adjusted to perform a first-stage filtering estimation. Then, the underwater target localization optimization is transformed into an unconstrained problem, where a cascade quasi-Newton optimization model is constructed to mitigate the accumulation of errors and suppress abnormal positioning outputs. Compared with the improved two-step weighted least squares, the square-root unscented Kalman filter, and the successive constrained optimization modified polar representation, the proposed method demonstrates superior localization accuracy in both multivariable simulations and lake-based field experiments. The consistency between simulation and experimental results confirms the effectiveness of the proposed method in suppressing the impact of uncertain measurements.

Aiming at the application demand in underwater noise monitoring, observation of marine animal, antisubmarine and underwater target localization, a high-SNR underwater acoustic signal acquisition (UASA) node that combines a self-contained acquisition system and floating platform is designed to improve the acquisition performance of a single UASA node, and a high-accuracy synchronization sampling method among multiple distributed UASA nodes based on master-slave dual phase-locked loops (MSDPLL) is proposed to improve the synchronization sampling accuracy. According to the equivalent model of hydrophone and application requirements, low noise signal conditioning circuit and large-capacity data storage modules are designed. Based on the long-term monitoring requirements for underwater acoustic signal and distributed positioning requirements for underwater targets, the structure of a single UASA node is designed and MSDPLL is developed for high-accuracy synchronization sampling among multiple UASA nodes. Related experimental results verified the performance of the UASA node and the synchronization sampling method.

A real-time magnetic localization method based on unscented particle filter (UPF) is proposed to solve the problem for real-time localization of underwater non-cooperative magnetic targets. The state space model of non-cooperative magnetic targets is set up according to its motion characteristic, and the state is estimated in real time by UPF. In order to improve the observability of the system, the particle state is constrained and magnetic moment is inverted by the least square method. The simulation results and ferromagnetic object localization experimental results show that the method is good in localization precision and real-time performance, which can be applied to the real-time magnetic localization in near field.

Active sonar systems are used in the detection and localization of underwater targets. While traditional approaches use pulsed active sonar (PAS) to transmit short bursts, high duty cycle (HDC) sonar systems have been the focus of recent research and can overcome the shortcomings of PAS. Since HDC sonar systems transmit a long pulse train waveform, we must address sub-pulse interference issues, which requires multiple orthogonal sub-pulses and generalized sinusoidal frequency modulated (GSFM) pulses are suitable for this purpose. Unfortunately, conventional GSFM pulse train design methods do not generate an adequate number of orthogonal sub-pulses. Therefore, we propose an improved GSFM pulse train waveform design approach for overcoming the limitations of these conventional methods. The proposed method is organized into two parts, the first focused on the assessment of the auto-correlation, and the second focused on the optimizing the orthogonality between sub-pulses. Cost function is also carefully designed for this purpose. From simulation experiments, we found that the proposed method was able to produce 30 orthogonal sub-pulses and an optimized waveform that demonstrated better detection performance than conventional waveforms under most conditions. We also verified the performance of the proposed method via actual sea experiments, with analysis showing superior performance matching that of simulations. An analysis on the bandwidth parameter K is also conducted and it is found K = 1.25 to be the best option.

Underwater Wireless Sensor Networks (UWSNs) have emerged as a critical component within underwater distributed perception applications. Due to the external factors, including ocean currents and undulating seabed topography, the UWSNs topology that changes dynamically over time cannot ensure optimal service performance. This paper proposes a balancing energy consumption and localization through coverage (BECLC), which adjusts the position of drifting underwater nodes through improved virtual forces, while achieving improvements in node energy consumption and localization accuracy. Firstly, the UWSNs coverage problem is modeled as a virtual force problem involving underwater nodes, underwater relay nodes, and obstacles, which can guide densely or sparsely dispersed underwater nodes to suitable locations under the action of joint virtual forces. Next, considering that the underwater relay node needs to consume more energy in the process of forwarding more data, the non-uniform deployment combined with hierarchy routing is proposed to reduce the coverage holes caused by node energy exhaustion. Finally, with regards to the drifted coordinates and noisy ranging of uncertain measurements, the theoretical localization performance of underwater target is evaluated with use of Cramer-rao lower bound as a benchmark. The experimental results show that proposed method not only enhances the UWSNs coverage rates, but also prolongs the network surviving time and improves the localization accuracy of underwater targets.

Deep learning for surface electromyography artifact contamination type detection

This paper presents results on recent developments pertaining to the coordinated motion control of a fleet of marine robotic vehicles. Specifically, we address the Cooperative Moving Path Following (CMPF) motion control problem, that consists of steering the robotic vehicles along a priori specified geometric paths that jointly move according to a target frame, while achieving a pre-defined coordination objective. To this end, each vehicle will need to communicate with their neighbors in order to cooperatively solve the CMPF task. Two distinct robust Moving Path Following motion control strategies for achieving robustness on the moving path following tasks are proposed. Experimental results demonstrating the application of CMPF to marine vehicles in the context of source localization and tracking of underwater targets are presented backed with stability and convergence guarantees.

Hybrid method based on particle filter and NARX for real-time flow rate estimation in multi-product pipelines

Mold temperature control of a rubber injection-molding machine by TSK-type recurrent neural fuzzy network

In this paper, underwater target bearing detection performance is investigated with time and frequency domain beamforming. Since dynamic underwater environment is challenging for signal transmission, increasing processing gain and directivity detection success with the use of planar transducer arrays can be helpful especially at low signal powers. In order to understand the effects of use in practical sonar systems better, directivity function of planar array beamforming and performance of with time and frequency domain processing are presented via computer simulations.

Side scan sonar images have great application prospects in underwater surveys, target detection, and engineering activities. However, the acquired sonar images exhibit low illumination, scattered noise, distorted outlines, and unclear edge textures due to the complicated undersea environment and intrinsic device flaws. Hence, this paper proposes a multi-scale fusion strategy for side scan sonar (SSS) image correction to improve the low contrast and noise interference. Initially, an SSS image was decomposed into low and high frequency sub-bands via the non-subsampled shearlet transform (NSST). Then, modified multi-scale retinex (MMSR) was employed to enhance the contrast of the low frequency sub-band. Next, sparse dictionary learning (SDL) was utilized to eliminate high frequency noise. Finally, the process of NSST reconstruction was completed by fusing the emerging low and high frequency sub-band images to generate a new sonar image. The experimental results demonstrate that the target features, underwater terrain, and edge contours could be clearly displayed in the image corrected by the multi-scale fusion strategy when compared to eight correction techniques: BPDHE, MSRCR, NPE, ALTM, LIME, FE, WT, and TVRLRA. Effective control was achieved over the speckle noise of the sonar image. Furthermore, the AG, STD, and E values illustrated the delicacy and contrast of the corrected images processed by the proposed strategy. The PSNR value revealed that the proposed strategy outperformed the advanced TVRLRA technology in terms of filtering performance by at least 8.8%. It can provide sonar imagery that is appropriate for various circumstances.

Modern radar systems often face various interference signals in complex and rapidly changing electronic environments. The task of suppressing this interference in the radar echo signal to extract vital information is challenging. A radar interference suppression method is proposed based on a generative adversarial network (GAN). This method effectively recovers the target signal from the echo signal, which contains interference and noise, by leveraging the powerful fitting ability of GAN. Specifically, this method was tested using coherent suppression interference, smart noise interference, and noise frequency modulation suppression interference. We compared the proposed GAN method with recurrent neural network, short‐time Fourier transform time‐varying filtering, short‐time fractional Fourier transform time‐varying filtering algorithms and RNN approach. The results show that the interference suppression algorithm based on GAN is superior to the other three algorithms.

The marine environmental noise formed by wind noise, rain noise, biological noise, sea surface waves, seismic disturbances, and so on is a kind of interference background field in underwater acoustic channels, which brings adverse effects to underwater acoustic target recognition. To improve the recognition accuracy of underwater targets under background noise interference, a bidirectional denoising autoencoder (BDAE) is proposed in this paper for underwater acoustic target signal denoising robust representation learning. The proposed bidirectional denoising autoencoder is an extension of the regular denoising autoencoder, which uses the original underwater acoustic target signals and their corresponding denoised signals to learn robust representations. We then measure the usefulness of the learned representations using a support vector machine classifier. Our proposed approach is verified on the ShipsEar database. Experimental results indicate that the proposed bidirectional denoising autoencoder can effectively learn the robust representations of underwater acoustic target signal denoising and is superior to the traditional methods.