被动声纳目标识别系统设计研究

目标识别是声纳的主要功能之一,其性能包括识别正确率、泛化能力和识别距离。由于数据样本的保密特性,声纳目标识别系统设计有其自身特色。在设计过程中,应首先降低对数据样本的依赖,把目标辐射噪声的机理分析、组成、运动规律等知识巧妙地运用到系统设计中;其次还应尽可能提高泛化率,以提高声纳目标识别系统对未见过的样本的正确识别能力。讨论了声纳目标识别流程、声纳目标识别系统的设计方法;在声纳目标识别系统的性能评估中,给出了目标识别距离的估算方法。     

自适应免疫算法的SVME用于水下目标识别

针对用支持向量机集成提高水下目标识别正确率会使识别系统更加复杂的问题,提出了一种以自适应免疫算法(AIA)的支持向量机选择性集成(SVME)算法(即AIA-SVME算法)进行分类器优化选择,对实测水下目标声信号进行分类识别.与分类器全部集成的识别实验对比证明,该算法在选择9%的分类器后仍可以达到分类器全部集成的识别效果,不仅保证了识别精度,还使得识别系统大幅度精简,节省在线识别的时间.该研究对于水下目标分类决策优化集成的新方法探索具有重要理论价值和实际意义.     

基于图像处理的钢直尺刻度识别算法研究

在钢直尺检定过程中，对目标刻度进行视觉识别，是实现钢直尺自动化检定的基础与核心。本文针对目前刻度线识别范围小，当被测钢直尺误差较大时，一般的视觉识别系统会出现误判的问题，提出一种大范围、高精度识别的刻度线识别算法。该算法通过区分识别钢直尺长刻度线和短刻度线，计算被测钢直尺与标准尺的错位误差，并使用图像旋转算法对图像进行旋转，保证识别精度和算法稳定性。     

基于ICA-GMM的混叠振动目标识别

提出一种基于独立分量分析的混叠振动目标盲分离和混合高斯模型识别相结合的混合模型振动识别方法。建立已知振动目标的GMM，然后实现混叠振动目标自适应盲源分离，提取了振动目标的线性预测系数作为目标识别的参数，产生了训练和识别所用的特征向量。识别阶段，通过解码判断振动目标的类别。仿真结果表明：新的混合模型识别系统在混叠振动目标识别中具有可行性。     

HHT与神经网络在舰船目标特征提取中的应用

目标识别一直是水声领域的关键技术之一。将高阶累积量用于希尔伯特变换特征提取中,通过对舰船目标辐射噪声信号进行采集,得到舰船目标噪声信号,进而提取目标辐射信号各阶模态的相邻平均瞬时频率比、相对标准差、中心频率、平均强度、高阶矩和高阶累积量等作为特征,最终利用BP神经网络来实现对两类舰船目标的分类识别。通过对实际舰船目标噪声进行识别,验证了该舰船目标识别系统具有较好的识别效果。     

桥上列车移动荷载参数自动识别系统试验

提出了一种用于列车移动荷载参数自动识别的系统,并制作了等截面简支钢梁和试验列车模型进行试验研究。利用基于图像处理技术的桥梁动态位移采集系统,获取模型桥梁测点位置的动态位移响应,同时利用自行设计的列车模型参数采集系统获取列车模型的移动速度、轮轴个数和轴间距,最后采用桥梁列车多轴移动荷载识别系统识别出列车轴重荷载值。通过对不同移动速度、不同测点个数下列车参数识别效果的分析,验证了本文所述列车移动荷载参数自动识别系统的可行性和准确性,为今后荷载识别系统的实际应用做好准备。     

信息论在声呐自动目标识别中的应用

声呐自动目标识别（ATR）旨在自动地从背景或杂波中分离出感兴趣目标，一个声呐自动目标识别系统的可行与否取决于它的目标探测性能和识别分类系统的运算效率及训练效率。文章综述了当今信息论在声呐ATR中应用中的理论基础及其可行性分析，最后给出了信息论在声呐ATR特征提取中的应用举例。     

基于方位起伏方差的目标识别方法

根据潜艇目标亮点模型的方位起伏，提出了一种基于目标方位起伏方差的目标识别方法．给出了具体的实现方案和相应的仿真结果．仿真结果表明，按照该方案设计的目标识别系统，只要根据试验修正判决门限的设定，就可以使鱼雷准确地识别真假目标．     

改进的射频识别系统的防冲突算法

在射频识别系统中，须采取有效的防冲突算法解决多个标签与阅读器数据交换时引起的数据冲突问题。新的防冲突算法采取动态互补的二进制树形搜索法，充分利用已得到的冲突信息，有效减小了判决过程中数据的传输量，提高了标签的识别效率。     

遗传算法应用于目标识别系统在线学习

在线学习是水声目标识别系统的重要功能之一，本文提出了遗传算法用于水声目标识别系统多层感知器分类网络在线学习的一种实现方法，实验表明，所提出的方法能够取得一定的效果，使原样本训练地宾ＭＬＰ网络经过在线学习对新增目标的识别率有明显增加。     

Bistatic SAR ATR

With the present revival of interest in bistatic radar systems, research in that area has gained momentum. Given some of the strategic advantages for a bistatic configuration, and technological advances in the past few years, large-scale implementation of the bistatic systems is a scope for the near future. If the bistatic systems are to replace the monostatic systems (at least partially), then all the existing usages of a monostatic system should be manageable in a bistatic system. A detailed investigation of the possibilities of an automatic target recognition (ATR) facility in a bistatic radar system is presented. Because of the lack of data, experiments were carried out on simulated data. Still, the results are positive and make a positive case for the introduction of the bistatic configuration. First, it was found that, contrary to the popular expectation that the bistatic ATR performance might be substantially worse than the monostatic ATR performance, the bistatic ATR performed fairly well (though not better than the monostatic ATR). Second, the ATR performance does not deteriorate substantially with increasing bistatic angle. Last, the polarimetric data from bistatic scattering were found to have distinct information, contrary to expert opinions. Along with these results, suggestions were also made about how to stabilise the bistatic-ATR performance with changing bistatic angle. Finally, a new fast and robust ATR algorithm (developed in the present work) has been presented.     

Application of mid-infrared spectroscopy: measuring hydrogen peroxide concentrations in bleaching baths

The presented work applies mid-infrared attenuated total reflection (ATR) spectroscopy to the measurment of hydrogen peroxide in aqueous matrices. The performance of different ATR crystals mounted in flow cells was investigated in the presence of aqueous hydrogen peroxide solutions. Quantitative determination has been achieved by evaluation of specific OH stretching and deformation vibrations with linear correlation between peak areas or peak heights and hydrogen peroxide concentration in the range of 1-10% (weight in water). Important aspects such as chemical stability of the waveguide material and influences of pH and ionic strength on the performance are discussed. Feasibility for the investigation of real world samples is demonstrated by measuring industrial bleaching solutions with known concentrations of hydrogen peroxide fitting well with calibration graphs established with neat hydrogen peroxide solutions. The presented sensor system is capable of determining hydrogen peroxide within complex matrices and clearly corroborates the potential of providing an in situ measurement concept for on-line hydrogen peroxide detection.     

Demonstration of improved automatic target-recognition performance by moment analysis of correlation peaks

We report the results of experimental tests of an optical-correlator-based automatic target recognition (ATR) system that uses the correlation-peak moment analysis technique of Caprari [Appl. Opt. 38, 1317 (1999)] to assist in discrimination between target and clutter peaks. The ATR system and its operation are briefly described with particular attention devoted to a practical scheme for enhancing the basic ATR system with correlation-peak moment detectors. We investigate the variation of detection and false-alarm rates of moment detectors with moment threshold values. For fixed moment thresholds, we present receiver operating characteristics of both basic and enhanced systems as the conventionally used correlation-peak energy threshold is varied. Results demonstrate that correlation-peak moment analysis materially improves ATR system target-detection performance.     

Integrated approach for automatic target recognition using a network of collaborative sensors

We introduce what is believed to be a novel concept by which several sensors with automatic target recognition (ATR) capability collaborate to recognize objects. Such an approach would be suitable for netted systems in which the sensors and platforms can coordinate to optimize end-to-end performance. We use correlation filtering techniques to facilitate the development of the concept, although other ATR algorithms may be easily substituted. Essentially, a self-configuring geometry of netted platforms is proposed that positions the sensors optimally with respect to each other, and takes into account the interactions among the sensor, the recognition algorithms, and the classes of the objects to be recognized. We show how such a paradigm optimizes overall performance, and illustrate the collaborative ATR scheme for recognizing targets in synthetic aperture radar imagery by using viewing position as a sensor parameter.     

Comparison of automatic target recognition system performance with full- and reduced-resolution correlators

The performance of an automatic target recognition (ATR) system with full- and reduced-resolution correlators was compared. In addition, the ATR system performance with reduced-resolution filter sets designed by use of multiresolution analyasis (MA) and downsampling (DS) techniques was also compared. It was discovered that results obtained at the optical correlator subsystem level, pertaining to the relative merits of the MA and the DS techniques, could not be extrapolated to the system level. This was because target signature differences between the test and the training imagery were discovered to have a greater influence on system performance than the choice of filter design technique. In addition, it was found that, for the case in which the target signature and the reduced-resolution filter were of the same size, there was some degradation in the receiver-operating-characteristic curve for reduced resolution compared with full. Nevertheless, this was deemed to have no practical significance, and thus the use of reduced-resolution optical correlators for ATR merits serious consideration.     

Direct analysis of oxidizing agents in aqueous solution with attenuated total reflectance mid-infrared spectroscopy and diamond-like carbon protected waveguides

A novel approach for the direct detection of oxidizing agents in aqueous solution is presented using diamond-like carbon (DLC) protected waveguides in combination with attenuated total reflectance (ATR) mid-infrared spectroscopy. Pulsed laser deposition was applied to produce high-quality DLC thin films on ZnSe ATR crystals with thicknesses of a few 100 nm. Scanning electron microscopy and X-ray photoelectron spectroscopy has been used to investigate the surface properties of the DLC films including the sp(3)/sp(2) hybridization ratio of the carbon bonds. Beside excellent adhesion of the DLC coatings to ZnSe crystals, these films show high chemical stability against strongly oxidizing agents. IR microscopy was utilized to compare differences in the chemical surface modification of bare and protected ATR waveguides when exposed to hydrogen peroxide, peracetic acid, and peroxydisulfuric acid. The feasibility of DLC protected waveguides for real-time concentration monitoring of these oxidizing agents was demonstrated by measuring calibration sets in a concentration range of 0.2-10%. Additionally, principal component regression has been applied to analyze multicomponent mixtures of hydrogen peroxide, acetic acid, and peracetic acid in aqueous solution. Due to high chemical stability and accurate monitoring capabilities, DLC protected waveguides represent a novel approach for directly detecting oxidizing agents in aqueous solution with promising potential for industrial process analysis.     

Production of hydrogen by autothermal reforming of propane over Ni/delta-Al2O3

The performance of Ni/delta-Al2O3 catalyst in propane autothermal reforming (ATR) for hydrogen production was investigated in the present study. The catalysts were characterized using XRD, TEM, and SEM. The activity of the Ni/delta-Al2O3 catalyst manufactured by the water-alcohol method was better than those of the catalysts manufactured by the impregnation and chemical reduction methods. The Ni/delta-Al2O3 catalysts were modified by the addition of promoters such as Mg, La, Ce, and Co, in order to improve their stability and yield. Hydrogen production was the largest for the Ni-Co-CeO2/Al2O3, catalyst.     

Model-based sea mine classification with synthetic aperture sonar

The quality and effectiveness of sensor information provided by mine-hunting autonomous underwater vehicles (AUVs) equipped with high-resolution sonars has improved drastically in recent years. In parallel, data rates have significantly increased resulting in information overload. Automatic target recognition (ATR) is regarded as a solution for this problem. This study describes a specific ATR technique based on model matching for application to high-resolution data. A sonar model for generation of high-resolution synthetic aperture sonar (SAS) images is described and applied both as database generator and classification. The performance of the model matching, which is attained by correlation and stochastically, is evaluated using a large data set covering the variety expected in mine-hunting operations. The model-based features generated in this way are able to reach an acceptable classification performance. The article is concluded with one real data example, which is easily classified when training with the simulated database. Further work is next aimed to confirm performance on real data.     

模糊综合评判与数理统计知识结合的目标识别效果评估

针对目标识别效果评估，利用数理统计知识确立了评估指标及测度方法。随后，使用模糊综合评判建立了一种开放的评估模型，该模型可以给出客观的、定量化的评估结果。最后，结合实测数据完成了仿真。