Passive sonar identification (Ⅳ):Recognition using fuzzy neural network

This series of papers deals with vessel recognition. The project is conducted by using fuzzy neural networks and basing on the spectra of vessel radiated-noise. This paper is the last in the series. It deals with the application of fuzzy neural network to the recognition of targets. The neural network is a multi-layered forward network and the learning algorithm is BP (error Back Propagation). In the paper, the adust formula of parameter of fuzzier is given. The paper provides a recognition result which is drawn from 1049 samples gathered from 41 vessels in 63 operating conditions, with an original recording time of about 3.5 hours. The identifications are more than 92% correct.

Passive sonar identification Ⅰ:Overall framework and extraction of line-spectrum

This series of papers deal with vessels-target recognition. The project is conducted by using fuzzy neuraI networks and basing recognition on the spectra of vessel radiated-noise. Paper (Ⅰ) describes the characteristics of vessel radiated-noise spectra, which are composed of two distinctive categories: the stationary and the non-stationary. The project framework is introduced in the paper. It includes two steps. One is to extract effectively recognizable features (those common in one category and those distinguish categories). The other is to memorize the characteristics of specific vessel targets. The memorization is realized with characteristics pattern plate library of specific vessels (including line spectrum, double-frequency spectrum and average power spectrum pattern plate library). Detailed discussions on theories, models, parameter analysis, line-spectrum extraction methods, as well as gaps between reality and theory concerning vessels radiated-noise are also included in Paper (Ⅰ). Paper (Ⅰ) finally proposes a method of automatic extraction of line spectrum by using machines. Paper (Ⅱ) will discuss the stability, uniqueness of line spectrum and its pattern plate. Paper (Ⅲ) will focus on the extraction of features from double-frequency spectrum and average power spectrum, and the establishment of their pattern plates. Paper (Ⅳ) will discuss fuzzy neural networks and recognition approaches

Passive sonar identification (Ⅱ): Stability and uniqueness of line spectrum

This series of papers deal with vessel recoghtion. This paper is the second of the paper series. It focuses on how to memorize the stable features of line spectrum of specific vessels by using line spectrum pattern plate and on related problems. This paper examines the analyzing parameters of line spectrum: average times, time length and their impact on the occurrence of stable lines. It compares the impact of two dtherellt average times on the occurrence of stable lines (occurrence ratio > 70%) and unstable lines, and shows that it takes longer time span for average when stable lines for recoghtion are used. Moreover, the paper discusses the statistic methods of establishing line spectrum pattern plate usihg stable lines,including the definition of stability and related para-meters. The stability of line spectrum and the uniqueness of stable lines are investigated in over 1000 samples gathered from 43 vessels in 65 operating conditions (with an original recording time of 3.5 hours). The results demonstrate the statistical implication of such uniqueness. The average overlapping ratio is 5 %; the proportion of vessels without stable lines is 8 %. Studies also show that the richness of line spectrums is not an identifying feature, distinguishing type A vessels from type B vessels

Passive sonar identification (Ⅲ): Feature extraction and pattern plates of double-frequency spectrum as well as average power spectrum

This series of papers deal with vessel recognition. The project is conducted by using fuzzy neural networks and basing on the spectra of vessel radiated-noise. Based on the studies of a large amount of ship radiated-noise data, which has been collected from actual ships on the sea, effectively recognizable features are extracted. Such features include line-spectrum features, stationary and nonstationary spectrum features as well as rhythm features. Finally the categorization are tested by unknown samples on the sea, including 33 surface vessels, 8 underwater vessels in 30 operating conditions. Methods for memorization and classilication are also explored in the project. Paper (Ⅲ) is the thirird in the series. It deals with the extraction method of modulation information in double-frequency power spectrum and the establishment of pattern plate of double-frequency spectrum as well as average power spectrum. To extract features from double-frequency spectrum, the tendency of wave is subtracted from the wave of each channel and the modulation of high frequency is compensated. The modulation degree of lines is shown by relative Value and converted to fuzzy value by fuzzy function. The pattern-plate of double-frequency spectrum memorises stable line and its respective modulation strength. The pattern-plate of average power spectrum memorizes the spectra mean of typical samples and the standard variance

旁侧声呐在海底探测中的应用和工作船动态定位施工技术

随着海洋工程建设及海上事故和海难的增多,日益增加的海底障碍物给海上安全生产和航运带来了前所未有的挑战和安全隐患,需要进行海上搜寻和水下探摸与处理。旁侧声呐和动力定位船的配合使用是处理这类问题的最佳选择,但租用动力定位船费用昂贵,成本很高。而根据工作区的实际情况利用渔船改装的动态定位船操作简单,且费用低廉,被海洋工作者广泛采用。本文介绍了旁侧声呐在海底障碍物探测中的应用和渔船改装的GPS动态定位船进行水上定位的工作原理和施工方法。装备GPS导航软件的渔船可以指示船只的实时位置。通过改变锚绳长度来改变船只位置的动态定位技术适用于水下搜寻和探摸处理工作。

TRONKA声纳系统在蛙人探测中的应用研究

随着蛙人侵袭活动的猖獗,探测蛙人的声纳引起了注意,为此提出了水下安全防护系统。文中针对TRONKA声纳在水下安全防护系统中的应用进行了详细阐述。该声纳系统可探测、跟踪、分类活动和固定目标,并向岸站发出报警信号,以便对威胁进行防御,保护港口、舰船等的安全。

航道整治透水框架群对鱼类集群影响的水声学探测

四面六边透水框架是一种具有良好防冲促淤功能的生态水工构造物,在航道整治工程中得到广泛应用。为了探究四面六边透水框架群对鱼类的影响,于2014年5-6月,应用EY60回声探测仪和双频识别声呐(ARIS Explorer 1800)对金城洲透水框架工程区水域进行定点水声学监测,并采集工程区附近的渔获物。结果表明,工程区共捕获鱼类114尾,包含3目、4科、12属、14种,体长均值为(27.64±10.06)cm,95%置信区间为25.77~29.50 cm;体重均值(551.84±1 252.02)g,95%置信区间为319.52~784.16 g。EY60回声探测仪对工程区共监测时长9 589 min,测得鱼的数目12 356尾,工程区鱼体的目标强度均值为(-63.24±5.79)d B,95%置信区间为-63.35^-63.15 d B;数据独立性T检验显示,工程区与对照区之间无显著性差异(P>0.05);通过回声探测仪和双频识别声呐对鱼类出现频次监测,工程淹没区是对照区的1.18倍,而工程半淹没区却是对照区的0.85倍;说明处于水下的四面六边透水框架群对鱼类具有一定的诱集作用。

主动声纳直达波干扰抑制的盲分离算法

针对舰艇编队作战中主动声纳之间存在的强直达波干扰,提出了一种基于信号统计二阶矩的直达波干扰抑制算法,实现了强干扰背景下的微弱目标回波检测。这种方法将盲分离理论和匹配相关技术相结合,首先对接收数据进行直达波干扰抑制,再利用已知发射信号副本进行匹配相关,最后提取目标回波信号。相比其它强干扰抑制算法,特别是高阶累计量法,该算法具有计算复杂度低的优点。通过数值仿真实验表明:该算法能够对直达波干扰进行有效抑制,对目标回波的检测性能优于直接匹配相关方法。

被动声纳信号分类特征提取的研究

对被动声纳信号进行了分析和特征提取，基于听觉系统识别声音信号的原理，提出了一种新颖的平稳恒Ｑ 特征，并给出了距离指数和识别指数２ 种更为合理的评价方法。实验结果表明本文提出的平稳恒Ｑ特征较原有几种典型特征，具有良好的分类正确性．

双频识别声呐水下影像监测系统及其应用

本文介绍了双频识别声呐水下影像监测系统的工作原理,对通过仿射变换特征图像配准法对数据进行处理得到清晰整体图像的核心技术进行了分析论证;并通过系统在三河闸水下结构损坏监测中的运用情况,阐述了系统在我国水利工程水下监测中的推广应用前景。

基于三维高密度电阻率法的露天铁矿山采空区精准探测

针对露天铁矿山地下隐伏采空区精准探测的技术难题,以某露天铁矿山实际矿床地质特征和不同岩矿体电阻率值为基础,建立三种异常识别模型,分析横向电性不均一条件下采空区的异常响应特征,得到了地电场分布规律并通过现场试验进行应用研究.结果表明:异常识别模型能够较准确地模拟地电场分布;三维高密度电阻率法在大面积探测工作中能够有效克服二维高密度电阻率法体积效应对采空区位置精准判别的干扰,减弱了异常扩展等效应.

倒谱和复倒谱在被动声纳目标识别中的应用

基于声纳员的感受被动声纳可以认为是一个发声体,这个发声体可以表示为激励噪声源与发声体冲激响应的卷积。在这种情况下,使用倒谱和复倒谱的形式分析被动声纳目标噪声的时域特征,得到的目标特征不够明显,因此提出了利用指数倒谱和指数复倒谱的频谱特性来提取目标噪声的特征,进行分类识别。设计了BP神经网络分类器,利用实测数据对三类目标进行分类。分析比较了两种方法的分类结果,验证了基于倒谱和复倒谱的指数运算的被动声纳目标特征提取方法的可行性。

自主式水下机器人控制系统及声呐目标识别

[目的]为满足水下搜救、勘探、目标检测与跟踪等需求,[方法]针对研制的"探海I型"自主式水下机器人(AUV),利用其搭载的前视声呐开展目标识别试验,选取获取的运动目标图像中的典型帧进行目标检测和识别研究。阐述"探海I型"AUV的系统组成与工作原理。提出一种控制系统架构:以笔记本电脑配合水面控制箱为水面控制单元;以PC104工控板作为自动驾驶仪的主控单元;同时配备摄像头PC104板卡单独进行摄像头图像处理。采用三帧差分法检测声呐目标,并基于Hough变换的快速椭圆检测算法提取目标特征。[结果]湖上试验表明:研制的AUV运行可靠、正常,可满足水下工作的需求,声呐目标识别效果较好。[结论]该AUV控制系统架构和目标识别方法对于中、大型AUV的研制及视频、红外等其他领域的目标识别具有借鉴意义。

测深仪HD-17在动态定位中的应用

HD-17测深仪因其性能稳定、精度可靠,在测量生产中得到广泛应用。文中详细地介绍了HD-17测深仪的工作原理、水底信号识别技术、使用方法、实际应用效果以及注意事项。

北盘江董箐与光照库区鱼类资源水声学调查

2014年7月16-28日,首次利用双频识别声纳DIDSON对贵州北盘江光照与董箐库区的鱼类进行了水声学调查,同步进行水质监测。航线均采用＂之＂字形,平均航速约5 km/h,董箐库区航程15.30 km,光照库区航程总计11.57 km。同步水质监测使用Hydrolab DS5多参仪,走航过程中坐标位置由GPS（Mobile Mapper 10）读取。水质采样点上用vector Pluse多普勒点式流速仪测量该点表层流速。监测期间,在各个江段进行水声学探测后,使用网目6 cm的流刺网在水体底层进行生物采样。董箐库区体长50-100 cm鱼所占比例为49.48%,光照库区体长20-50 cm鱼比例达60.55%。董箐库区的鱼类多分布在0-15 m的中上层水层,而光照库区的鱼类多集中在15-30 m的中下层水层。各水层分布的鱼类数量,董箐库区相差不大,而光照库区差异较大。2库区表层水体中温度、溶氧和叶绿素a值存在显著差异;中层水体中温度、溶氧和叶绿素a值差异显著;底层水体的温度和溶氧差异显著。董箐与光照库区表层水流流速差异显著。鱼类平均密度董箐库区为（17 240±6 240）×103尾/km3,光照库区为（11 750±1 860）×103尾/km3。董箐库区探测江段共收集渔获物94 580.62 g,鱼类20种、231尾;放流的长臀鮠C.bouderius、光倒刺鲃S.hollandi、白甲鱼O.sima和花鱼骨H.maculats占渔获物重量66.17%、数量44.23%。光照库区探测段共收集渔获物92 165.45 g,鱼类13种、155尾;放流的4种鱼占渔获物重量28.22%、数量31.41%。北盘江梯级电站开发以来,董箐和光照库区现存鱼类资源密度偏低,但生长结构基本合理。

双频识别声呐在三河船闸工程水下检测中的应用

为了了解三河船闸工程闸室、下游海漫及引航道运行状态,采用DIDSON 300m型双频识别声纳系统对1～5号闸室、下游海漫及引航道进行水下声纳检测成像并进行分析.经成像分析,可以发现闸室及廊道的混凝土部分损坏,伸缩缝内填料流失,部分检测区域有石块沉积.双频识别声纳（DIDSON）能够在浑浊、黑暗的水下获得清晰的影像数据,可有效探测和识别水下目标,能够为水下工程检测、航运安全提供很好的服务.

基于自适应生长的声呐图像增强算法

从声呐图像增强的实践出发,采用自适应生长算法对三维成像声呐进行图像增强处理,以提高水下目标识别的能力,通过相关的理论分析和计算机仿真计算表明,该算法具有简单快速的优点,能够较好地分割出声成像中的目标数据,可作为进一步特征提取和目标识别的基础。

双频识别声纳技术在水工建筑物水下外观病害检测中的应用

针对水工建筑物水下外观病害的类型特点,提出用双频识别声纳技术进行检测,并在工程实践中开展应用。实践表明,双频识别声纳技术对水工建筑物水下外观病害具有较好的检测效果,研究内容可为水工建筑物安全监测提供参考。

基于BTR的雷达声呐探测目标匹配融合技术

为了解决被动声呐无法有效分辨水面和水下目标的问题,将雷达探测目标航迹映射到被动声呐探测目标的时间方位历程图(BTR),通过将雷达和声呐探测目标航迹进行匹配融合处理,实现了不同维度目标信息的关联融合,从而准确分辨是水面目标,还是水下目标。试验结果表明,该技术能够有效实现雷达声呐共同探测目标的匹配关联,能够对水下目标的准确分辨提供理论指导。

双频识别声呐在浑浊海域ROV海管调查中的应用

【目的】为解决混浊海域ROV海管调查遇到的困难,引入双频识别声呐协助作业。【方法】在中国南海某浑浊海域ROV海管调查作业中,搭载双频识别声呐,对整段海管、特征点进行声学成像,同时与ROV搭载光学摄像头成像进行对比。【结果】在浑浊海域海管调查应用中,双频识别声呐可以在ROV搭载光学摄像头无法成像的情况下声学成像,生成几乎等同影像质量的图像。【结论】作为一种目视检查手段,ROV搭载双频识别声呐可以清楚地观察海管的状态,实时呈现动态画面,有效地协助作业人员在浑浊海域进行ROV海管调查,极大地提高了作业的安全,保证了作业质量;而且,ROV搭载双频识别声呐在浑浊海域海管调查时的速度不亚于在能见度良好海域中的调查速度,保证了其作业效率和经济性。