A Novel CCA-NMF Whitening Method for Practical Machine Learning Based Underwater Direction of Arrival Estimation

Underwater direction of arrival(DOA)estimation has always been a very challenging theoretical and practical problem.Due to the serious non-stationary,non-linear,and non-Gaussian characteristics,machine learning based DOA estimation methods trained on simulated Gaussian noised array data cannot be directly applied to actual underwater DOA estimation tasks.In order to deal with this problem,environmental data with no target echoes can be employed to analyze the non-Gaussian components.Then,the obtained information about non-Gaussian components can be used to whiten the array data.Based on these considerations,a novel practical sonar array whitening method was proposed.Specifically,based on a weak assumption that the non-Gaussian components in adjacent patches with and without target echoes are almost the same,canonical cor-relation analysis(CCA)and non-negative matrix factorization(NMF)techniques are employed for whitening the array data.With the whitened array data,machine learning based DOA estimation models trained on simulated Gaussian noised datasets can be used to perform underwater DOA estimation tasks.Experimental results illustrated that,using actual underwater datasets for testing with known machine learning based DOA estimation models,accurate and robust DOA estimation performance can be achieved by using the proposed whitening method in different underwater con-ditions.

Design Research on Drive System of Underwater Tapping Machine

The underwater tapping machine is composed of a center bit, a tapping cutter, a seal box, a main drive box, a boring bar assembly, a envelop, a gear case, a counter and so on. The drive system in underwater tapping machine consists of a worm drive, a gear drive system and a screw drive. The worm drive is in the main drive box. The worm is connected with a hydraulic motor and driven by the hydraulic motor. The gear drive system is a combined gear train which is the combinations of the fixed axes and differential gear train in the gear case. On the one hand, by means of the fixed axes gear trains the turn and power of transmission shaft are transferred to the boring bar and the screw rod, causing differential turn between the boring bar and the screw rod. On the other hand, the turns of the boring bar and the screw rod are transferred to the differential gear train. The differential gear train is used to drive a special counter to count axial travel of the boring bar. The screw drive is composed of a feed screw and a nut on the boring bar. There is the differential turn between the boring bar and the feed screw. By means of the nut, the boring bar can feed automatically. With the movement of the sliding gear 7 in the gear case, the designed drive system can also be provided with the ability of fast forward and fast backward movement of the boring bar in its idle motion, resulting in the increase of the tapping efficiency.

Modeling of underwater wet welding seam forming based on support vector machines

Underwater welding is developing fast because of the exploration of marine resources, and underwater wet welding automation is urgently needed because of the rigorous environment. To control the welding process automatically, the model of the process should first be built to predict the current welding process status. In this paper, arc and visual sensors were used simultaneously to obtain the electrical and visual information of underwater wet welding, and support vector machines （SVM） were used to model the process, experiment results showed that the method could effectively use the information obtained and give precise prediction results.

ANALYSIS AND SIMULATION ON THE MECHANISM OF A NOVEL DUAL-WAVE SHOCK TEST MACHINE

For qualifying the anti-shock performance of shipboard equipments and simulating actual underwater explosion environments, a novel dual-wave shock test machine is proposed to increase testing capability of shock test machines as well as to meet certain shock testing specification. The machine can generate a double-pulse acceleration shock for test articles according to specification defined in BV043/85. On the basis of the impact theory, a nonlinear dynamic model of the hydraulically-actuated test machine is established with thorough analysis on its mechanism which involves conversion of gas potential energy and dissipation of kinetic energy. Simulation results have demonstrated that the machine can produce a double-pulse acceleration shock in the time domain or a desired shock response spectrum in the frequency domain, which sets a theoretical base for the construction of the proposed machine.

Classification of underwater still objects based on multi-field features and SVM

A Support Vector Machine is used as a classifier to the automatic detection and recognition of underwater still objects. Discrimination between the objects can be transferred into different projection spaces by the process of multi-field feature extraction. The multi-field feature vector includes time-domain, spectral, time-frequency distribution and bi-spectral features. Underwater target recognition can be considered as a problem of small sample recognition. SVM algorithm is appropriate to this kind of problems because of its outstanding generalizability. The SVM is contrasted with a Gaussian classifier and a k-nearest classifier in some experiments using real data of lake or sea trial. The experimental results indicate that SVM is better than the others two.

Application of RVM for prediction of bead shape in underwater rotating arc welding

Bead sttape in underwater rotating arc welding was affected by several welding parameters. RVM （ relevance vector machine） was used to build a model to predict weld bead shape. The training data set of RVM eortsists of the welding parameters which are rotational frequency, rotational radius, height of torch and welding current and the features of the bead shape. The maximum error and mean error for prediction of width are 0. 10 mm and 0. 09 mm, respectively, and the maximum error and mean error for prediction of penetration are 0. 31 mm and 0. 12mm, respectively, which are showed that the prediction model can achieve higher prediction precision at reasonably small size of training data set.

水下人-机协同搜救作业人因可靠性分析研究

为分析水下人-机协同搜救作业人因可靠性并识别其关键影响因素,根据水下搜救训练实际和相关研究结论提取人因可靠性影响因素;建立人因可靠性影响因素体系,利用解释结构模型定性分析各影响因素间相关关系,将建立的各影响因素的解释结构模型转换为贝叶斯网络拓扑结构,分别构建潜水员作业、无人遥控潜水器(ROV)作业、人-机协同作业人因可靠性分析贝叶斯网络;通过对3类贝叶斯网络进行推理,揭示影响人因可靠性的关键因素及其依赖关系,并定量分析3种作业模式下的人因可靠性变化。结果表明:人-机协同搜救作业中“误解意图”“通信不畅”“信息不对称”“作业精度不足”“丧失救助能力”等影响因素起到关键作用;当上述因素得到较好控制时,人-机协同搜救作业的人因可靠性将会表现出优于单纯的ROV或潜水员独立施救的效能。研究结果可为水下搜救作业人因可靠性分析与提升提供参考。

声光联合引导UUV回收系统光学子系统研究

当今水下无人航行器(UUV)在军事与民用领域都有着广泛的应用前景,布放与回收技术是影响UUV实际应用的一项关键技术。目前主要回收引导方式有声学导引、光学导引、电磁导引这3种,而各自都存在明显的优缺点。本文针对声光联合导引机械臂回收系统光学子系统进行研究,设计一组可在水下200 m、0.05~10 m范围工作的机器视觉镜头及其配合使用的靶标,并完成了系统的仿真。该系统可在环境要求下准确地提取出靶标特征点。

基于机器视觉的UUV水下沉底目标自主识别

水下无人航行器对目标的自动识别研究是未来水下目标探测领域的发展趋势。针对现阶段水下沉底目标声呐图像探测人工识别工作量大、判别困难等问题,研究了机器视觉中基于Canny算子图像边缘检测结合霍夫线变换去噪的识别方法在水下无人航行器自主探测的应用,为此在湖底布放多个水下沉底模拟目标,尝试了水下无人航行器的目标自主探测方案,通过实际湖上试验对比分析三种水下沉底目标声呐图像的算法识别效果,验证了论文所研究方法的有效性,为后续无人平台自主识别算法研究提供参考,以期提高无人航行器对水下沉底目标的自主探测识别能力。

复杂附体结构仿生机器蟹水动力特性研究

借鉴变形机器人的变形技术,在传统仿生机器蟹设计上引入可变形水下滑翔机的概念设计,仿生机器蟹可根据不同工作任务,自主切换工作模式。基于粘性流体理论,将滑移网格法与多计算域法高效结合,对计及复杂附体结构的仿蟹机器蟹水动力性能进行研究,获得在不同航速、不同攻角下的升阻特性;对其压力场、速度场和涡量场的分布进行分析,得到仿生机器蟹在滑翔模式下的最优攻角,并为仿生机器蟹优化设计打下基础。

Underwater acoustic multipath sparse channel estimation via gridless relevance vector machine method

In the scenario of underwater acoustic sparse channel estimation with training sequences,grid points in the measuring matrix are caused by discretizing procedure.Estimated accuracy might not be guaranteed with the state-of-the-art methods when multipath delays don't exactly locate on the grid points.In this paper,we construct a gridless measuring matrix for sparse channel estimation which contains an off-grid adjusting factor.The Relevance Vector Machine(RVM) algorithm is employed to estimate this factor.The numerical experiments for two different underwater channels are performed to testify the newly proposed method.The results demonstrate that this method outperforms conventional ones in terms of estimating error and bit error rate,especially when the grid gets coarser.

Numerical Modeling of Dual-Pulse Shock Test Machine for Simulating Underwater Explosion Shock Loads on Warship Equipments

In order to qualify shock resistance performance of shipboard equipments and simulate real underwater explosion environment,a novel dual-pulse shock test machine is proposed.The new machine will increase testing capability and meet special shock testing requirement.Two key parts of the machine,the velocity generator and the shock pulse regulator,play an important role in producing the positive acceleration pulse and the succeeding negative acceleration pulse,respectively.The generated dual-pulse shock for test articles is in conformity with an anti-shock test specification.Based on the impact theory,a nonlinear dynamic model of the hydraulically-actuated test machine is established with thorough analysis on its mechanism that involves conversion of gas potential energy and dissipation of kinetic energy.Simulation results have demonstrated that the proposed machine is able to produce a double-pulse acceleration shock in the time domain or a desired shock response spectrum in the frequency domain,which sets up a base for the construction of the machine.

DRHA-UIE:基于双重残差混合注意力模块的水下图像增强方法

在水下环境中,悬浮的颗粒会对光造成散射和波长相关的衰减,使水下图像呈现出颜色失真、对比度低等问题.针对上述问题,本文提出一种基于双重残差混合注意力模块的水下图像增强方法(Dual Residual Hybrid Attention Underwater Image Enhancement method,DRHA-UIE).该方法采用改进的双重残差块完成特征学习,并通过在双重残差块中引入混合注意力模块,沿通道和空间两个维度对特征进行注意力权重推断,以捕获显著特征.本文设计结合像素级损失、结构相似性损失和内容感知损失的联合特征损失函数,以获得具有更精细纹理的增强图像.此外,本文应用水下图像形成模型(Image Formation Model,IFM)对水下图像基准数据集(Underwater Image Enhancement Benchmark dataset,UIEB)进行优化,获得了具有更高视觉质量的N-UIEB(New-UIEB)数据集,实验表明,相较于UIEB数据集,基于N-UIEB训练得到的增强图像具有更自然的颜色和更清晰的细节.为验证本文方法的有效性,将本文方法与主流的10种方法进行测试和比较,结果表明,DRHA-UIE方法有效提高了图像对比度并恢复了图像颜色,在与水下图像增强算法的定量比较中获得了最优的性能.

基于深平均流预测模型的水下滑翔机路径优化

随着水下滑翔机在海洋调查及声学探测领域的广泛运用,精准、高效控制其路径对精细化海洋观测至关重要。针对水下滑翔机受海流影响产生较大偏航差问题,采用最小二乘支持向量机法(LSSVM)预测深平均流,以单剖面偏航差最小为目标函数,以实际航向与计划航向夹角不超过一定值为约束条件,构建非线性约束极值模型,确定预设剖面最优目标航向及出水点坐标,从而实现路径优化目的。采用“海燕-II”型水下滑翔机历史数据进行验证,结果表明:1) LSSVM法预测深平均流准确性较高,但当局部流向有明显变化时预测效果不佳,取前3个剖面数据作为训练样本时预测效果更好;2)采用文中方法优化后,水下滑翔机路径更稳定,各剖面偏航差平均为281.1 m。

深度多属性增强水声目标识别方法

被动声纳系统由于其隐蔽性好的特点在军事任务中发挥着重要作用。针对被动水声目标识别问题,开展了水声目标多属性特征提取与识别方法研究。利用深度学习方法从舰船辐射噪声中提取目标多属性特征并识别水声目标。提出了深度多属性增强水声目标识别方法,该方法可以从时域舰船辐射噪声中提取水声目标多属性特征及多属性之间的相关性特征,并用来增强深度模型对水声目标类别属性的表达能力。基于海试实测数据的6类水声目标识别实验结果表明,相比于不考虑多属性的识别方法,提出的深度多属性增强水声目标识别方法的平均正确识别率提高了3.6%~18.2%,并且具有更好的识别稳定性。

联合SVM和HMM的水上/水下导航场景感知模型构建

导航场景感知是智能化PNT的重要特征,更是实现多场景无缝导航定位的基础。本文聚焦水上/水下导航场景,考虑电磁波的衰减程度差异将其细分为水上、浅水、深水3类场景,利用支持向量机(support vector machine,SVM)进行场景分类与识别,在此基础上,引入隐马尔可夫模型(hidden Markov model,HMM)表达导航场景切换,进一步提升场景识别可靠性。本文分别构建了基于结果联合(SVM-HMM1)及基于概率联合(SVM-HMM2)的水上/水下导航场景感知模型。实测分析表明,两种模型能够实现高精度场景感知,SVM-HMM1与SVM-HMM2识别准确率分别为91.36%与95.11%;与单一的HMM和SVM模型相比,联合模型在结果分类与识别上更为稳定,准确率提升约为0.95%~8.46%。

隧道接缝三维变形分布式光纤智能感知方法

为解决传统技术难以准确监测水下隧道接缝三维变形的难题,结合分布式光纤应变传感技术和人工智能技术机器学习算法提出隧道接缝三维变形感知新方法。首先,利用分布式光纤应变传感技术,设计隧道接缝变形光纤监测的方法,依据光纤应变与变形量的理论关系,建立隧道接缝三维变形计算模型,得到12组数据。其中,每组共有4000个隧道接缝变形量与光纤应变的数据。然后,提出基于决策树、随机森林和支持向量机的两级递进机器学习分类新算法,实现对隧道接缝三维变形量的准确计算,隧道接缝变形的计算精确度可达0.1 mm。研究发现,相比于决策树和随机森林2种机器学习算法,支持向量机对隧道接缝三维变形计算具有较高的准确性和稳定性。

水下光声图像空间配准算法研究综述

水下光声图像配准是水下设备实现信息融合的关键技术。在简述了水下光声图像配准的概念及实例的基础上,分析了目前水下光声图像重建与复原的相关算法,详细综述了水下异源图像基于区域和特征的配准算法研究进展,重点论述了基于图像域和形状特征相似度的两个准确度较高的研究方向的发展现状,并根据其他领域的异源图像配准的研究热点,从增加成像模型的结构性约束、引入相位一致性和生成对抗网络等算法提高配准精度,展望了水下声光图像配准研究的发展趋势。

水下单壁桩钻铣切割机设计及验证

针对水下单壁钢桩切割作业需求,设计并制造水下液压钻铣切割机,以立铣刀为切割工具,使用液压缸进给、液压马达驱动铣刀钻铣及回转切割,完成切割作业。对设备的设计依据及设备的组成进行了详细描述,分析钻铣刀、驱动马达、传动系统等参数的选用,并根据设计方案制造样机。通过对水下液压钻铣切割样机的海上及车间测试,验证设备可靠性,得出样机切割效率、铣刀消耗参数等数据。实际测试表明:该设备运行可靠,且该设备加工、使用及维护成本低,适合水下单壁钢桩切割推广使用。

基于多模型深度特征集成的水声目标识别方法

基于深度学习的水声目标识别算法表现出强大的数据分布拟合能力,已经成为研究重点和热点。深度模型的拟合能力与其复杂度正相关,但过于复杂的模型会显著增加计算成本。综合考虑识别性能以及计算成本,提出了基于多模型深度特征集成的水声目标识别方法。首先利用预训练好的深层模型提取深度特征,再利用特征压缩和集成方法将深度特征融合到浅层模型中,通过改变集成的深度特征维度构建多个深度特征集成模型作为子模型,最后多个子模型通过加权投票实现目标识别。实验结果表明,提出方法的平均正确识别率比对比方法提高了0.37%~5.46%,同时参数量仅为Xception的1/34。