Automatic recognition of sonar targets using feature selection in micro-Doppler signature

Currently,the use of intelligent systems for the automatic recognition of targets in the fields of defence and military has increased significantly.The primary advantage of these systems is that they do not need human participation in target recognition processes.This paper uses the particle swarm optimization(PSO)algorithm to select the optimal features in the micro-Doppler signature of sonar targets.The microDoppler effect is referred to amplitude/phase modulation on the received signal by rotating parts of a target such as propellers.Since different targets'geometric and physical properties are not the same,their micro-Doppler signature is different.This Inconsistency can be considered a practical issue(especially in the frequency domain)for sonar target recognition.Despite using 128-point fast Fourier transform(FFT)for the feature extraction step,not all extracted features contain helpful information.As a result,PSO selects the most optimum and valuable features.To evaluate the micro-Doppler signature of sonar targets and the effect of feature selection on sonar target recognition,the simplest and most popular machine learning algorithm,k-nearest neighbor(k-NN),is used,which is called k-PSO in this paper because of the use of PSO for feature selection.The parameters measured are the correct recognition rate,reliability rate,and processing time.The simulation results show that k-PSO achieved a 100%correct recognition rate and reliability rate at 19.35 s when using simulated data at a 15 dB signal-tonoise ratio(SNR)angle of 40°.Also,for the experimental dataset obtained from the cavitation tunnel,the correct recognition rate is 98.26%,and the reliability rate is 99.69%at 18.46s.Therefore,the k-PSO has an encouraging performance in automatically recognizing sonar targets when using experimental datasets and for real-world use.

Health Monitoring of Milling Tool Inserts Using CNN Architectures Trained by Vibration Spectrograms

In-process damage to a cutting tool degrades the surface􀀀nish of the job shaped by machining and causes a signi􀀀cant􀀀nancial loss.This stimulates the need for Tool Condition Monitoring(TCM)to assist detection of failure before it extends to the worse phase.Machine Learning(ML)based TCM has been extensively explored in the last decade.However,most of the research is now directed toward Deep Learning(DL).The“Deep”formulation,hierarchical compositionality,distributed representation and end-to-end learning of Neural Nets need to be explored to create a generalized TCM framework to perform eciently in a high-noise environment of cross-domain machining.With this motivation,the design of dierent CNN(Convolutional Neural Network)architectures such as AlexNet,ResNet-50,LeNet-5,and VGG-16 is presented in this paper.Real-time spindle vibrations corresponding to healthy and various faulty con􀀀gurations of milling cutter were acquired.This data was transformed into the time-frequency domain and further processed by proposed architectures in graphical form,i.e.,spectrogram.The model is trained,tested,and validated considering dierent datasets and showcased promising results.

Modeling simulation and experiment of micro-Doppler signature of precession

Spatial precession is a special micro-motion of the spinning-directional target, and the micro-Doppler signature of the cone-shaped target with precession is studied. The micro-motion model of precession is built first, and then the micro-Doppler model is developed based on the proposed concept of micro-motion ma- trix, by which the theoretical formula of micro-Doppler signature of precession is derived. In order to further approach to the actual case, the occlusion effect is firstly considered in micro-Doppler, and the simulated result with occlusion effect is well in accordance with the measured result in microwave anechoic chamber, which suggests that the micro-motion model and micro-Doppler model of precession are both valid.

DETECTION ON MICRO-DOPPLER EFFECT BASED ON LASER COHERENT RADAR

A laser coherent detection system of 1550 nm wavelength was presented, and experimen- tal research on detecting micro-Doppler effect in a dynamic target was developed. In the study, the return signal in the time domain is decomposed into a set of components in different wavelet scales by multi-resolution wavelet analysis, and the components are associated with the vibrational motions in a target. Then micro-Doppler signatures are extracted by applying the reconstruction. During the course of the final data processing frequency analysis and time-frequency analysis are applied to analyze the vibrationM signals and estimate the motion parameters successfully. The experimental results indicate that the system can effectively detect micro-Doppler information in a moving target, and the tiny vibrational signatures also can be acquired effectively by wavelet multi-resolution analy- sis and time-frequency analysis.

Parity recognition of blade number and manoeuvre intention classification algorithm of rotor target based on micro-Doppler features using CNN

This paper proposes a parity recognition of blade number and manoeuvre intention classification algorithm of rotor target based on the convolutional neural network(CNN) using micro Doppler features. Firstly, the time-frequency spectrograms are acquired from the radar echo by the short-time Fourier transform.Secondly, based on the obtained spectrograms, a seven-layer CNN architecture is built to recognize the blade-number parity and classify the manoeuvre intention of the rotor target. The constructed architecture contains a leaky rectified linear unit and a dropout layer to accelerate the convergence of the architecture and avoid over-fitting. Finally, the spectrograms of the datasets are divided into three different ratios, i.e., 20%, 33% and 50%,and the cross validation is used to verify the effectiveness of the constructed CNN architecture. Simulation results show that, on the one hand, as the ratio of training data increases, the recognition accuracy of parity and manoeuvre intention is improved at the same signal-to-noise ratio(SNR);on the other hand, the proposed algorithm also has a strong robustness: the accuracy can still reach 90.72% with an SNR of – 6 dB.

Parameter estimation for rigid body after micro-Doppler removal based on L-statistics in the radar analysis

In traditional inverse synthetic aperture radar （ISAR） imaging of moving targets with rotational parts, the micro-Doppler （m-D） effects caused by the rotational parts influence the quality of the radar images. Recently, L. Stankovic proposed an m-D removal method based on L-statistics, which has been proved effective and simple. The algorithm can extract the m-D effects according to different behaviors of signals induced by rotational parts and rigid bodies in time-frequency （T-F） domain. However, by removing m-D effects, some useful short time Fourier transform （STFT） samples of rigid bodies are also extracted, which induces the side lobe problem of rigid bodies. A parameter estimation method for rigid bodies after m-D removal is proposed, which can accurately re- cover rigid bodies and avoid the side lobe problem by only using m-D removal. Simulations are given to validate the effectiveness of the proposed method.

Continuous frequency and phase spectrograms: a study of their 2D and 3D capabilities and application to musical signal analysis

A new lighting and enlargement on phase spectrogram （PS） and frequency spectrogram （FS） is presented in this paper. These representations result from the coupling of power spectrogram and short time Fourier transform （STFT）. The main contribution is the construction of the 3D phase spectrogram （3DPS） and the 3D frequency spectrogram （3DFS）. These new tools allow such specific test signals as small slope linear chirp, phase jump case of musical signal analysis is reported. The main objective is to and small frequency jump to be analyzed. An application detect small frequency and phase variations in order to characterize each type of sound attack without losing the amplitude information given by power spectrogram

Micro-Doppler feature extraction of micro-rotor UAV under the background of low SNR

Micro-Doppler feature extraction of unmanned aerial vehicles(UAVs)is important for their identification and classification.Noise and the motion state of the UAV are the main factors that may affect feature extraction and estimation precision of the micro-motion parameters.The spectrum of UAV echoes is reconstructed to strengthen the micro-motion feature and reduce the influence of the noise on the condition of low signal to noise ratio(SNR).Then considering the rotor rate variance of UAV in the complex motion state,the cepstrum method is improved to extract the rotation rate of the UAV,and the blade length can be intensively estimated.The experiment results for the simulation data and measured data show that the reconstruction of the spectrum for the UAV echoes is helpful and the relative mean square root error of the rotating speed and blade length estimated by the proposed method can be improved.However,the computation complexity is higher and the heavier computation burden is required.

Particle swarm optimization for rigid body reconstruction after micro-Doppler removal in radar analysis

The rotating micro-motion parts produce micro-Doppler(m-D)effects which severely influence the quality of inverse synthetic aperture radar(ISAR)imaging for complex moving targets.Recently,a method based on short-time Fourier transform(STFT)and L-statistics to remove m-D effects is proposed,which can separate the rigid body parts from interferences introduced by rotating parts.However,during the procedure of removing m-D parts,the useful data of the rigid body parts are also removed together with the m-D interferences.After summing the rest STFT samples,the result will be affected.A novel method is proposed to recover the missing values of the rigid body parts by the particle swarm optimization(PSO)algorithm.For PSO,each particle corresponds to a possible phase estimation of the missing values.The best particle is selected which has the minimal energy of the side lobes according to the best fitness value of particles.The simulation and measured data results demonstrate the effectiveness of the proposed method.

Micro-Doppler Parameter Estimation Method Based on Compressed Sensing

A micro-Doppler parameter estimation method based on compressed sensing theory is proposed in this paper.The micro-Doppler parameter estimation algorithm was improved for micro-motion targets with translation in this paper.Relatively ideal micro-Doppler parameter estimation results were obtained.The proposed micro-Doppler parameter estimation was compared with the traditional micro-Doppler parameter estimation algorithm.Requirements for return signal length were analyzed with this new algorithm and its performance was also analyzed in various environments with different SNR.

Micro-Doppler effect testing technique for attitude of projectile in space flight

To measure projectile attitude in space flight, based on continuous wave （CW） radar, a new micro-Doppler effect testing technique is developed in this paper. It also establishes radar testing model for attitude of flying projectile and resolve micro-Doppler effect of projectile motion attitude. By distinguishing and geting attitude parameters such as micro-motion period, this technique can in- tuitively estimate the flight stability of projectile, and the validity of this technique is proved accord- ing to flight tests.

Convex Optimization-Based Rotation Parameter Estimation Using Micro-Doppler

We present a novel algorithm that can determine rotation-related parameters of a target using FMCW （frequency modulated continuous wave） radars, not utilizing inertia information of the target. More specifically, the proposed algorithm estimates the angular velocity vector of a target as a function of time, as well as the distances of scattering points in the wing tip from the rotation axis, just by analyzing Doppler spectrograms obtained from three or more radars. The obtained parameter values will be useful to classify targets such as hostile warheads or missiles for real-time operation, or to analyze the trajectory of targets under test for the instrumentation radar operation. The proposed algorithm is based on the convex optimization to obtain the rotation-related parameters. The performance of the proposed algorithm is assessed through Monte Carlo simulations. Estimation performance of the proposed algorithm depends on the target and radar geometry and improves as the number of iterations of the convex optimization steps increases.

一个面向短波通信的LHOG话音检测方法

噪声环境下语音检测准确率偏低是短波通话面临的公开挑战。当前已有方法应用有限,其根源在于难以可靠地在噪音环境下提取准确且高效的语音特征。针对上述问题,提出了一个面向短波通信的低秩方向梯度直方图(Low-rank Histogram of Oriented Gradient,LHOG)话音检测方法。首先,对目标音频源数据进行预处理,实现噪声环境下语音信息的可视化表征;然后,在HOG特征提取器中嵌入低秩化结构,缓解特征中的冗余信息,并降低噪声干扰,从而获得准确且高效的特征;最后,通过常用的SVM分类模型便可在噪声环境中准确快速地区分话音和噪声。测试结果表明,该方法的准确率达到了95.12%,误报率仅为0.96%,漏报率为13.14%。与现有主流方法的对比实验证明,该方法话音检测准确率高,资源占用少,能够有效提高短波通信侦控效率。

心音频谱图在二尖瓣反流患者左心室功能监测中的作用

目的探求使用可穿戴设备获取心音频谱图,观察不同程度二尖瓣反流(MR)患者心音频谱特征在左心室功能监测中的作用。方法入选2020年6月至2021年5月因心血管疾病入住上海交通大学医学院附属瑞金医院的102例MR患者,根据心脏超声MR反流束面积/左心房面积比值超过20%将其分为轻度MR组72例和中度及以上MR组30例。基于心音频谱图对心音持续时间、最大声强、最大心音振幅进行分析,并与心脏超声测定的左心室射血分数(LVEF)进行相关性分析。结果心音频谱图第一心音持续时间与收缩期持续时间比值(S11-S12/S11-S21)与LVEF呈线性负相关(r=-0.535,P<0.01),S11-S12/S11-S21用于判定LVEF降低(LVEF<50%)曲线下面积为0.840(95%CI=0.756~0.924,P<0.01),截断值是55.50%,敏感度78.6%,特异度83.3%。结论心音频谱图提示,MR患者心脏收缩期第一心音持续时间占比与LVEF呈负相关性,在二尖瓣病患的心功能居家监测中存在潜在的应用价值。

基于语谱图的管制员疲劳状态检测研究

现阶段利用陆空通话语音对管制员疲劳状态的研究中,大多只考虑了语音在时域或频域的变化,而忽视了疲劳会同时在时域与频域上产生影响。将三种疲劳状态下的陆空通话语音分别转化为可同时反映时域与频域特性的语音频谱图像,利用灰度共生矩阵提取四维典型的特征参数,对比管制员在不同状态下特征参数的变化情况,构建管制员疲劳检测模型并对输入特征进行检测。结果表明:利用语谱图特征结合传统特征作为输入特征的检测准确率最高,达到95.49%,较单一使用传统特征的检测准确率高出4%;管制员疲劳状态的变化会直观地反映在语谱图上,会对其特征值产生影响,利用这种影响对管制员疲劳状态进行检测,可以得到良好的检测结果。

双解码卷积循环网络风噪声有源控制

本文提出一种利用双解码卷积循环网络(Dual-decoder Convolutional Recurrent Network,DCRN)代替FxLMS(Filtered-x Least Mean Square)算法的有源噪声控制方法,考虑到相位信息在有源噪声控制(Active Noise Control,ANC)中的重要性,DCRN网络的输入特征为噪声信号的复数频谱(包括实部谱和虚部谱).网络结构中,采用编码模块从噪声复数频谱中提取特征,利用双解码模块分别估计网络输出的实部谱和虚部谱,采用参数共享机制和组策略以降低训练参数的数量并提高网络的学习能力和泛化能力.特别是针对风噪声,选用新的损失函数以及对训练数据进行正则化处理以提升DCRN的性能.实验结果表明,DCRN方法在仿真环境与有源降噪耳机环境下对一般噪声和风噪声都表现出良好的降噪性能和鲁棒性.

基于最小二乘图像坐标修正的中阶梯光谱仪谱图还原算法

中阶梯光谱仪具有交叉色散特征,二维谱图还原是决定其波长测量准确性的关键环节,但是环境变化、加工装调等引起的光斑坐标变化对谱图还原精度造成严重影响。本文提出了一种基于最小二乘图像坐标修正的中阶梯光谱仪谱图还原算法,首先提取校准汞灯光源多波长光斑质心坐标,利用理论像点和实际像点坐标构建系数矩阵,通过最小二乘法估计获得二维像面的平移、缩放、旋转系数,再采用多项式拟合减小残差影响,实现不同波长光斑的图像坐标修正,进而实现波长精确解算。实验结果显示,该算法能有效提高中阶梯光谱仪的谱图还原精度,在模拟较大装调误差条件下,修正后坐标与理想坐标偏差小于0.6个像元,证明了该算法具有较高的精度。

合成语声的声学分析及识别特征算法

当前社会新型犯罪中电信诈骗案件频发,急需一种能够自动有效区分语声真伪的方法。为进一步增强目前深度学习领域识别合成语声的能力,为保障语声信息安全提供技术上的支持,针对合成语声声学特性上异于真实语声的特点,分析对比合成语声和真实语声的声学特性,设计了一种声学特征均方根角量化语声声强变化程度,结合基频变化率和语声窄带频谱图声学特征进行融合,量化了声学特性差异,聚焦了合成语声中关键声学信息。在神经网络模型中融合输入声学特征,在FoR数据集的验证集上得到了0.6%的等错误率,在测试集上最好结果达到了10.8%的等错误率。该文成功实现了对合成语声的识别,证实了声学特征的有效性和研究方案的可行性,在一定程度上拓宽了合成语声特征设计的研究思路。

基于Mel声谱图与改进SEResNet的鱼类行为识别

养殖环境中饲料投放、水流变化等刺激源导致鱼类声音分辨难,使行为识别准确率不高,为解决上述问题,提出基于Mel声谱图(Mel spectrogram)与改进SEResNet的鱼类行为识别模型TAP-SEResNet。首先针对鱼类行为声音频率波动大、特征差异小,造成特征提取难的问题,采用高分辨率、特征表示较好的Mel声谱图以捕捉鱼类声音的频谱特征。其次针对鱼类声音特征关键信息易丢失的难题,提出在SEResNet模型中融合时序聚合池化层(Temporal Aggregated Pooling,TAP),提取池化区域的最大值和平均值,保留鱼类行为更多细粒度声音特征,提高识别准确率。为验证所提模型的有效性,分别设计了消融试验和模型性能对比试验,试验结果显示:TAP-SEResNet相比SEResNet在不降低检测速度的条件下准确率提升了3.23%;相比PANNS-CNN14、ECAPA-TDNN及MFCC+ResNet等先进声音识别模型,TAP-SEResNet在准确率上分别提升了5.32%、2.80%和1.64%。所提模型有助于养殖过程中对鱼类行为实现精准监测,对精准养殖具有重要的推动作用。

基于实体GIS设备试验的局部放电光学信号传播特性研究

光测法具有电磁免疫性,特别适用于具有封闭结构的气体绝缘开关设备(gas insulated switchgear, GIS)局部放电检测,但是光信号在传播过程中易因传播距离增加或部件遮挡而快速衰减。为此,基于110 kV实际GIS设备开展局部放电光学信号传播特性试验,研究传播距离和绝缘子遮挡对导杆尖刺缺陷和悬浮电位缺陷局部放电光信号的影响规律。结果表明,随着传播距离的增加:尖刺缺陷检测到光信号最大幅值和放电数均有所衰减,放电谱图变化不大;悬浮缺陷放电光信号幅值明显衰减,放电数不变,放电谱图特征逐渐失去“矩形”特征。此外,当光学信号透过带有通气孔的绝缘子传播时,光学信号明显衰减,且幅值波动较大。