Passive Sonar Target Research Articles

Adaptive feature enhancement of modulation spectrum of ship radiation noise

The Detection of Envelope Modulation on Noise (DEMON) has been widely used in passive sonar target identification for determining the operational status and propeller structure characteristics of ships. However, the traditional DEMON spectrum is susceptible to environmental noise, which increases the difficulty of feature extraction. To address this issue, this paper investigates an adaptive feature enhancement method that combines Variational Mode Decomposition (VMD) and Singular Value Decomposition (SVD). The VMD algorithm utilizes variational equations to achieve adaptive modal decomposition of multiple feature components, while SVD utilizes the uncorrelated nature of signal and noise to achieve background noise reduction. Simulation results demonstrate that the feature strength and output signal-to-noise ratio of the VMD-SVD algorithm are higher than those of the traditional DEMON algorithm under both uniform and non-uniform modulation modes. Furthermore, processing of actual data validates the superiority of the VMD-SVD algorithm over the traditional DEMON algorithm, with the feature strength and output signal-to-noise ratio being maximally increased by 3 dB and 3.8 dB, respectively, compared to the traditional algorithm.

A characteristic extraction method for VoicePrint slice statistics base on joint time-frequency processing

Mel-Frequency Cepstral Coefficients (MFCC) and its differential coefficients are widely used as a typical non-linear spectral envelope feature in passive sonar target recognition. MFCC emphasizes the frequency domain information at the low-frequency end of the target, while the differential coefficients add dynamic characteristics of MFCC in the time domain. However, the utilization of time information is not sufficient. In response to this issue, we propose two solutions: one is the characteristic fusion method of Weighted Mel-Frequency Cepstral Coefficient based on Bhattacharyya Distance (BD-WMFCC); the other is the characteristic extraction method of VoicePrint Slice Statistics (VPSS) based on time–frequency joint processing. BD-WMFCC combines weighted differential coefficients with MFCC using Bhattacharyya distance, maximizing the utilization of time information. VPSS is a linear spectral feature that utilizes the stability of the spectral intensity within a certain bandwidth over continuous time. It extracts the steady-state characteristics of the target's spectrum with respect to time changes at equidistant bandwidths. Simulation and real data analysis have shown that VPSS demonstrates outstanding separability and classification performance in both non-linear and linear spectral features, with strong stability. In practical data analysis, the accuracy of VPSS features under the AlexNet algorithm is 3.8 % and 5.7 % higher than the spectral (Fre) and Mel features, respectively.

Passive Sonar Target Identification Using Multiple-Measurement Sparse Bayesian Learning.

Accurate estimation of the frequency component is an important issue to identify and track marine objects (e.g., surface ship, submarine, etc.). In general, a passive sonar system consists of a sensor array, and each sensor receives data that have common information of the target signal. In this paper, we consider multiple-measurement sparse Bayesian learning (MM-SBL), which reconstructs sparse solutions in a linear system using Bayesian frameworks, to detect the common frequency components received by each sensor. In addition, the direction of arrival estimation was performed on each detected common frequency component using the MM-SBL based on beamforming. The azimuth for each common frequency component was confirmed in the frequency-azimuth plot, through which we identified the target. In addition, we perform target tracking using the target detection results along time, which are derived from the sum of the signal spectrum at the azimuth angle. The performance of the MM-SBL and the conventional target detection method based on energy detection were compared using in-situ data measured near the Korean peninsula, where MM-SBL displays superior detection performance and high-resolution results.

Passive Sonar Target Tracking Based on Deep Learning

At present, the tracking accuracy of underwater passive target tracking is often limited due to models that are overly simple, with low complexity, poor universality, and an inability to learn. In this paper, a cubature Kalman filter (CKF) algorithm based on a gated recurrent unit (GRU) network is proposed. The filter innovation, prediction error, and filter gain obtained from the CKF are used as the input to the GRU network, and the filter error value is used as the output to train the network. End-to-end online learning is carried out using the designed fully connected network, and the current state of the target is predicted. In this paper, a deep neural network based on the GRU architecture is used to convert the tracking prediction problem into a time series prediction problem in the field of artificial intelligence, and its strong fitting ability is used to resolve the uncertainty of the target motion. Simulation results show that an unmanned underwater vehicle (UUV) state estimation method based on the GRU filter proposed in this paper offers better accuracy and stability than the traditional state estimation method.

Generative adversarial learning for improved data efficiency in underwater target classification

In the realms of the ocean, it becomes a formidable task to detect and classify the passive acoustic targets from the convoluted acoustic mixture confronted by the sonar frontend. Though the advances in deep learning driven by enormity of data and computational infrastructure have resulted in a tremendous leap in performance across various domains, passive sonar target recognition still remains an elusive task for the acoustic as well as signal processing communities. Various channel related artifacts together with the inherent difficulty in obtaining annotated data limit the target records required for training these massive supervised networks so as to yield an optimal performance. This demands models that can generalize well beyond the often sparse training instances. In order to address this issue, generative frameworks can be utilized to model the causal attributes of the target signature so that the network becomes tolerant to the distortions induced by the ambient noise and channel artifacts. This paper exploits the generative modelling capability of an Auxiliary Classifier Generative Adversarial Network (ACGAN) to construct a data-efficient underwater target classifier. These class-conditioned frameworks based on unsupervised representation learning can model the true data distribution using the latent attributes of the training data. In order to make the causal factors of variation more explicit, the raw time domain samples are transformed into joint time–frequency representations using filterbanks initialized at different perceptual scales. Experimental evaluation of the proposed system on target instances collected from diverse locations of the Indian Ocean yields promising results in terms of data efficiency, class confidence and classification accuracy.

Efficiency of Various Time-Frequency Representations in Deep Neural Network based Passive Sonar Target Classifiers

Passive acoustic target classification is an exceptionally challenging problem due to the complex phenomena associated with the channel and the relatively low Signal to Noise Ratio (SNR) manifested by the pervasive ambient noise field. Inspired by the overwhelming success of Deep Neural Networks (DNNs) in many such hard problems, a carefully crafted network specifically for target recognition application has been employed in this work. Although deep neural networks can learn characteristic features or representations directly from the raw observations, domain specific intermediate representations can mitigate the computational requirements as well as the sample complexity required to achieve an acceptable error rate in prediction. As the sonar target records are essentially a time series, spectro-temporal representations can make the intricate relationship between time and spectral components more explicit. In a passive sonar target recognition scenario, since most of the defining spectral components reside at the lower part of the spectrum, a nonlinear dilated spectral scale having an emphasis on low frequencies is highly desirable. This can be easily achieved using a filterbank based time-frequency decomposition, which allows more filters to be positioned at the desired frequency ranges of interest. In this work, a rigorous analysis of the performance of time-frequency representations initialized at various frequency scales, is conducted independently as well as in combination. A convolutional neural network based spectro-temporal feature learner has been utilized as the initial layers, while a deep stack of Long Short Term Memories (LSTMs) with residual connections has been used for learning the intricate temporal relationships hidden in the intermediate representations. From the experimental results it can be observed that a linear scale spectrogram achieves an accuracy of 92.4% and 90.2% respectively for validation and test sets in the single feature configuration, whereas the gammatone spectrogram is capable of attaining an accuracy in the order of 96.7% and 96.1% respectively for the same. In a multifeatured setup however, the accuracy reaches up to 97.3% and 96.6% respectively, which reveals that a combination of properly initialized intermediate representations can improve the classification performance significantly.

Classification of Sonar Targets Using an MLP Neural Network Trained by Dragonfly Algorithm

Due to the compatibility of the designed classifiers with MLP Neural Networks (MLP NNs), in this article, MLP NNs have been used to identify and classify active and passive sonar targets. On the one hand, the great importance of precise and immediate classification of sonar targets, and on the other hand, being trapped in local minimums and the low convergence speed in classic MLP NNs have led the newly proposed Dragonfly Algorithm (DA) to be offered for training MLP NNs. In order to assess the performance of the designed classifier, this algorithm have been compared with BBO, GWO, ALO, ACO, GSA and MVO algorithms in terms of precision of classification, convergence speed and the ability to avoid local optimum. To have a comprehensive comparison, the three sets of active and passive data were used. Simulation results indicate that DA-based classification have better results in all three datasets compared to benchmark algorithms.

Passive sonar target classification using multi-layer perceptron trained by salp swarm algorithm

Due to the variability of the radiated signal of the sonar targets, passive sonar target classification is a challenging problem in the real world application. Adaptive Mel-frequency cepstral coefficients (MFCCs) and multi-layer perceptron (MLP) approaches are proposed, including cepstral features to alleviate dataset's dimension and MLP network to adapt the variability in changing condition. In spite of the capabilities of MLP networks, low classification accuracy, and getting stuck in local minima are the main shortcomings of MLP networks. To overcome these shortcomings, this paper proposes the use of the newly introduced salp swarm algorithm (SSA) for training MLP network. In order to investigate the efficiency of the proposed classifier, four high-dimensional benchmark functions, as well as an experimental passive sonar data set, are employed. The designed classifier is compared to gray wolf optimizer (GWO), biogeography-based optimization (BBO), interior search algorithm (ISA), and group method of data handling (GMDH) in terms of classification accuracy, entrapment in local minima, and convergence speed. The results showed that the proposed classifier is more efficient than the other benchmark algorithms; therefore, the SSA classifies sonar data set as much as 0.9017 percent better than GMDH being the best results among the other classifiers.

Passive manipulation of low resonance scattering frequency associated with subsonic Rayleigh waves on submerged polymer spheres

Observation of the backscattering form function for a solid polymethylmeth-acrylate(PMMA) sphere reveals a significant enhancement at low frequencies, which is associated with the subsonic Rayleigh waves resonance. The presence of these resonances suggests that solid PMMA spheres may be used as passive sonar targets for certain applications.The slightly deformed PMMA spheres with regular corrugation are constructed for studying and manipulating the low-frequency resonances of subsonic Rayleigh waves. For the regular-corrugated PMMA spheres, the first-order approximate of Rayleigh normal mode solution is obtained with the perturbation method and the backscattering form function is analyzed in each order. It can be found that coupling among multiple resonance modes is introduced by the boundary deformation and leads to the shift of resonance frequency. An approximate formula for the frequency shift with respect to the parameters of corrugated boundary is deduced. Based on this formula, it is possible to evaluate resonance frequency of subsonic Rayleigh waves quickly and then manipulate acoustic scattering filed of the slightly deformed PMMA spheres in water passively.

주파수 영역 수동소나 표적신호 분리 및 잡음 제거 알고리즘

주파수 영역 수동소나 표적신호 분리 및 잡음 제거 알고리즘

Aural Spectrum Analysis for Naval Vessel Radiation Noise

A passive long wave cochlea model is applied to extract audial feature of naval vessel radiation noise. Based on the model, a two dimensional time space distribution Spectrum of noise signal is calculated. Four one dimensional features with simple form are presented. The experiment results shows that the features based on cochlea model is consistent with auditory perception of noise signal. The approach is a new method to extract feature for passive sonar target recognition.

Passive sonar target tracking with a vertical hydrophone array in a deep ocean environment

When operating in a deep ocean environment, limited power availability makes it imperative to conserve energy. This is achieved through the use of computational efficiency, as well as a passive sonar configuration that eliminates the need for a sonar source. Mallat and Zhang’s Matching Pursuits algorithm with a Kalman filter is implemented for use in passive target tracking. This makes it possible to determine the range of a moving target through the use of dot products and other simple calculations. The model setup used to test this approach includes a vertical hydrophone array at a depth of 4-5km and a near surface target between 10 and 45 km away. Simulated results using ray tracing (BELLHOP) and wavenumber integration (OASES) were used in developing this method. Preliminary results indicate this to be an effective means of target tracking. Possible future improvements include determining the bearing as well as the range of the target.

Passive sonar target localization and tracking using sequential bayesian filter in uncertain sea environment

A problem of localizing and tracking an acoustic source is researched when ocean environment including water column sound speed profile, ocean depth and seabed property is uncertain. In a Bayesian framework, the source and environmental parameters are regard as random variables with known prior knowledge, then the prior knowledge of parameters and acoustic model are combined with a likelihood function of data to provide posterior probability density functions (PDF) of both south and environmental parameters, target location parameters are estimated by marginalization integrates over the environmental parameters finally. In other hand, the environmental parameters and target location parameters evolve in time or space, which can be described by state-space model. Information on these parameters evolution and uncertainty at preceding steps can be incorporated to determine future probability of parameters with acoustic data being available at current step. A framework of a sequential Bayesian filter is derived naturally based on the model. A Kalman filter or particle filter could be used to implement the sequential Bayesian filter depend on the linear or nonlinear of the measurement equation or/and the state equation. The sequential Bayesian filter is demonstrated to be able to localize and track a source broadcasting a broadband signal in shallow water using both simulated and real data acquired by a towed array.

Intelligent PSR estimator for feature extraction of a passive sonar target

In real-time sonar classification, the propeller shaft rate (PSR) estimator for a feature extraction of the passive sonar target has the following problems: it requires an accurate and efficient performance due to the difficulty of distinguishing the harmonic family composed of the PSR fundamental and its harmonics from multiple spectral lines in the frequency spectrum, and it requires an easy design procedure in terms of structure and parameters. To solve these problems, an intelligent PSR estimator (IPSRE) using expert knowledge and the evolution strategy (ES) is proposed here. Simulation results show that the proposed algorithm effectively solves sonar classification problems in real-time.

수동 소나 표적의 식별을 위한 지능형 특징정보 추출 및 스코어링 알고리즘

실시간 시스템 적용에 있어서, 수동 소나 표적의 식별을 위한 특징정보 추출 및 스코어링 알고리즘은 다음과 같은 문제점들을 가지고 있다. 즉, 주파수 스펙트럼으로부터 PSR(Propeller Shaft Rate) 및 BR(Blade rate) 등의 특징정보를 실시간으로 구별하는 것은 매우 어렵기 때문에 정확하고 효율적인 특징정보 추출(extraction)법을 요구한다. 또한, 추출된 특징정보들로 구성된 식별 DB(DataBase)는 잡음 및 불완전한 구성을 갖기 때문에 강인하고 효과적인 특징정보 스코어링(scoring)법을 요구한다. 나아가, 구조와 파라메터에 있어서 용이한 설계 절차를 요구한다. 이러한 문제들을 해결하기 위해서 진화 전략(ES : Evolution Strategy) 및 퍼지(fuzzy) 이론을 이용하는 지능형 특징정보 추출 및 스코어링 알고리즘이 제안되었다. 제안된 알고리즘의 성능을 검증하기 위해서는 수동 소나 표적의 실시간 식별이 수행되었다. 시뮬레이션 결과는 제안된 알고리즘이 실시간 시스템 적용에서 존재하는 문제점들을 효과적으로 해결할 수 있음을 보여준다. In real-time system application, the feature extraction and scoring algorithm for classification of the passive sonar target has the following problems: it requires an accurate and efficient feature extraction method because it is very difficult to distinguish the features of the propeller shaft rate (PSR) and the blade rate (BR) from the frequency spectrum in real-time, it requires a robust and effective feature scoring method because the classification database (DB) composed of extracted features is noised and incomplete, and further, it requires an easy design procedure in terms of structures and parameters. To solve these problems, an intelligent feature extraction and scoring algorithm using the evolution strategy (ES) and the fuzzy theory is proposed here. To verify the performance of the proposed algorithm, a passive sonar target classification is performed in real-time. Simulation results show that the proposed algorithm effectively solves sonar classification problems in real-time.

Relationship between material parameters and target strength of fluid-filled spherical shells in water: calculations and observations

Thin fluid-filled spherical shells have been used as passive sonar targets for many years. They possess a large target strength which is highly dependent on the sound-speed mismatch between the fluid contained within the shell and the exterior fluid surrounding the shell. In the past, to obtain the appropriate mismatch, the interior fluid mixture contained chlorofluorocarbons (CFCs). Due to a recent production ban on CFCs, it is necessary to choose alternative fluids. The present research analyzes the backscattering target strength of a fluid-filled spherical shell as a function of several material parameters as a guide to choosing alternative fluids and shell materials. Calculations over a broad range of material values display the target strength dependence on the interior fluid parameters as well as the parameters defining the metallic shell. The range of material values presented here is far larger than any previous study addressing the focusing effects of fluid-filled spherical shells. The results should aid in determining liquid fillers and shell materials which yield the maximum possible backscattered returns. Also, several experiments were conducted with stainless steel shells containing a hydrochlorofluorocarbon (HCFC), dichlorofluoroethane. The results are compared with results found from calculations as well as from other experiments involving shells containing a previously used CFC mixture.

Target strength of fluid-filled spherical shells related to material parameters and alternate filling fluids

Fluid-filled, thin spherical shells have been studied for use as passive sonar targets with applications in underwater navigation and calibration [see, e.g., D. L. Folds etal., J. Acoust. Soc. Am. 73, 1147–1151 (1983)]. The present research investigates the target strength of fluid-filled spheres as a function of shell and fluid parameters to aid in choosing alternative filling fluids. (Partial motivation is from the recent discontinuation of several chlorofluorocarbons which are commonly used.) Calculations based on 3-D elasticity theory describe the target strength dependence on the internal fluid density and sound speed. Here both time and frequency calculations of the form function and time domain scattering signatures describe favorable fluid characteristics. These features relate to the thickness and density of the confining spherical shell. It is shown that internal-fluid density requirements vary considerably for thin aluminum and stainless-steel shells. Several different filling fluids are tested in spherical shells with consideration given to effective target strength, safety considerations, and cost.

The use of spectral information in optimal detection of a source in the presence of a directional interference

The detection of a passive sonar target in the presence of ambient noise and a plane wave interference is discussed. Intuitively, such a detector consists of a spatial filter which nulls the interference, followed by a temporal filter. In this paper we study the role of the a priori knowledge of the spectrum of the interference and/or signal in improving detector performance. We develop three different generalized likelihood ratio test (GLRT) detectors, resulting from different cases of prior spectral information. We show that, for all cases of known/unknown source and/or interference power spectrum, the GLRT detectors are, as expected, null steering systems. The depth and shape of the null, as well as the postbeamforming temporal filter, are different and are functions of the a priori known spectrum. Under the assumption that all signals and noise are zero-mean Gaussian processes, we analyze the performance of the different detectors and we exploit their dependency on the array beampattern, as well as on the source and interference signal-to-noise ratio. This analysis serves to identify scenarios where the use of prior spectral information leads to significant performance improvement. >

A neural networks approach to multiple passive sonar targets identification by source separation technique

A source separation and neural network unsupervised learning procedure has been proposed and applied to the identification of multiple passive sonar targets. Acoustic noises radiated from 101 fishing boats were collected from two widely separated underwater hydrophones. A noise background whitening algorithm was applied to flatten the power density spectra (PDS) [W. A. Struzinski and E. D. Lowe, J. Acoust. Soc. Am. 76, 1738–1742 (1984)]. The system was trained by using the single-target spectrum shapes derived from one of the hydrophones and then used these to identify the sources from the other hydrophone for both single and multiple targets. Multitarget signals were preprocessed by a source separation technique to obtain the individual signals. Results of practical testing indicated that the system could correctly identify 90.1% of the recordings for a single sonar target. Identification rate of the multi-target signals can achieve 84% for 50 different combinations of single-target signals. This paper describes the system configuration, the experiment design, and experiences with the practical applications. [Work supported by CSIST.]

Glory- and rainbow-enhanced acoustic backscattering from fluid spheres: Models for diffracted axial focusing

Transmitted-wave contributions to backscattering from large spheres are calculated. Amplitudes due to glory rays are enhanced, relative to those of axial reflections, because of focusing. The glory pressure amplitudes are proportional to a(ka)1/2, where a is the sphere’s radius and k is the wavenumber. The model, though similar in form to one for optical scattering from air bubbles [D. S. Langley and P. L. Marston, Phys. Rev. Lett. 47, 913–916 (1981)], contains new features to facilitate the summing of amplitudes in a range of angles. An additional enhancement due to rainbow focusing is modeled for certain sound velocity ratios M; for these M the backscattered amplitude is proportional to a(ka)2/3. Major features of the exact scattering are reproduced by these models when ka=1000 and (with defects) ka=100. The enhancements are not intrinsically due to resonance. Applications to the design of passive sonar targets are noted.