Artificial intelligence-based hull structural plate corrosion damage detection and recognition using convolutional neural network

With the support of big data and GPU acceleration training, the artificial intelligence technology with deep learning as its core is developing rapidly and has been widely used in many fields. At the same time, feature extraction operations are required by the current image-based corrosion damage detection method in the field of ships, with little effect but consuming the large amount of manpower and financial resources. Therefore, a new method for hull structural plate corrosion damage detection and recognition based on artificial intelligence using convolutional neural network is proposed. The convolutional neural network (CNN) model is trained through a large number of classified corrosion damage images to obtain a classifier model. Then the classifier model is used with overlap-scanning sliding window algorithm to recognize and position the location of corrosion damage. Finally, the damage detection pattern for hull structural plate corrosion damage as well as other types of superficial structural damage using convolutional neural network is proposed, which can accelerate the application of artificial intelligence technology into the field of naval architecture & ocean engineering.     

中国无人机遥感技术突破与产业发展综述

无人机是未来网络环境下一种数据驱动的空中移动智能体,而无人机遥感则是无人机应用最重要的引领性产业。本文首先以国内外无人机遥感发展现状为背景,重点概述了中国无人机遥感21世纪以来“十五”到“十三五”所获得的具有代表性的国家支持与推动的发展历程,阐述了无人机遥感定标场,航空航天定标场的建立以及应用验证,包括无人机遥感系统的载荷与系统技术发展;然后,进一步阐述了以遥感定标场、地物参量引导载荷性能、系统模型为代表的中国无人机遥感的相关技术跨越;接着,概略介绍了无人机遥感在国防反恐安全以及跨国应急救援,国土测绘与海洋岛礁测绘应用,地质灾害应用以及国家应急救援等领域的产业应用;最后,介绍了中国在无人航空遥感领域展开的跨越性的工作,包括组网智能控制、精度和实时性度量基础、载荷平台自组织冗余容错、遥感大数据云处理技术和无人机遥感组网实用化等内容。未来无人机遥感发展的总体目标是建立起具备迅捷信息获取能力的无人航空器组网观测系统,实现无人航空器组网技术由项目层面跨越到遥感领域,同时也为中国成为世界遥感强国的国家战略跨越奠定基础。     

Advances of geo-spatial intelligence at LIESMARS

ABSTRACT

The enhancement of computing power, the maturity of learning algorithms, and the richness of application scenarios make Artificial Intelligence (AI) solution increasingly attractive when solving Geo-spatial Information Science (GSIS) problems. These include image matching, image target detection, change detection, image retrieval, and for generating data models of various types. This paper discusses the connection and synthesis between AI and GSIS in block adjustment, image search and discovery in big databases, automatic change detection, and detection of abnormalities, demonstrating that AI can integrate GSIS. Moreover, the concept of Earth Observation Brain and Smart Geo-spatial Service (SGSS) is introduced in the end, and it is expected to promote the development of GSIS into broadening applications.     

Introducing run-size driven fisheries management for the coastal fishery of Atlantic salmon: Preseason forecasts for policy makers

The Finnish coastal fishery of Atlantic salmon (Salmo salar) in the northern Baltic Sea is regulated using multi-annual, pre-fixed, opening dates of harvests that aim to enhance spawning escapement of early migrating wild salmon. Such an inflexible management regime does not set regulations that track varying run sizes of salmon. We introduce an array of computational intelligence techniques to estimate and forecast coastal run size and escapement of salmon into three spawning rivers in the northern Baltic Sea. Our results indicated that the present management pattern, driven largely by regional fisheries policy, contrasts greatly with a “run-size driven” (i.e. abundance-based) management approach. Introducing run-size driven management, i.e. setting regulations annually by tracking preseason forecasts, would better ensure adequate escapement and at the same time allow the maintenance of coastal catch at sustainable level. Setting regulations annually would allow effective harvesting in years when the run is high, and would effectively restrict harvests when the run is low.     

融合物理理解与模糊逻辑的分类强对流客观短期预报系统:（2）表现评估

本文对分类强对流客观短期概率预报系统2022年6月13日强对流过程预报产品的表现进行分析,基于2022年的雷暴、短时强降水、雷暴大风及冰雹客观概率预报产品和可用的分类强对流监测实况资料,结合强对流预报业务中使用的空间检验方法和常用的确定性及概率性检验指标,对该短期预报系统提供的四类强对流天气客观概率预报产品进行了详细的性能评估。用于评估的预报资料是时段为2022年4月1日至9月30日每天08时(北京时)起报,96 h内逐12 h间隔的预报产品。预报个例分析显示,四类产品均可提前24 h指示需要关注的强对流天气区域。统计检验结果表明,短时强降水各方面性能最好,其次是雷暴,雷暴大风也有一定的可参考性。四类强对流天气预报产品均存在预报概率与实况频率相比偏高的过度预报问题。雷暴、短时强降水和雷暴大风预报产品均存在与预报覆盖时效有关的日变化。评估结果为预报模型和系统后续改进发展奠定了基础,为应用基于融合物理理解与模糊逻辑人工智能方法的分类强对流预报产品提供了有益参考。     

智能潜器控制系统的实航验证

本文介绍了某智能潜器的系统概要及其使命规划系统和使命控制系统的结构,并通过对其实航试验结果的分析,证明了本系统能够实现自主导航、自主避障等功能。特别是,本系统对潜器的位置和艏向具有优良的控制特性,达到了预定的研究目标。     

基于改进InceptionV3模型的常见矿物智能识别

以常见的16类矿物作为研究对象,收集每一类矿物约1000张图像,按比例划分为训练集、验证集和测试集,通过图像随机选取增加数据的多样性,建立矿物识别InceptionV3模型,训练7万次在测试集上获得81%的识别正确率。通过对损失函数的改进,引入Center Loss损失函数,训练40万次识别准确率提高到86%。对分类的混淆矩阵分析发现,孔雀石等外观特征明显的矿物识别正确率很高,而闪锌矿等与其他矿物容易混淆导致正确率较低。从特征图分析看出,模型很好地提取了孔雀石的放射状特征,矿物图像特征向量聚集程度很高,也说明了模型的可靠性。     

余震的序列参数稳定性和余震短期发生率预测效能的连续评估——以2014年云南鲁甸6.5级地震为例

为考察目前国际上广泛使用、对真实地震序列描述最好的"传染型余震序列模型"(ETAS)在主震后的序列参数拟合、余震短期发生率预测的效能,本研究以2014年云南鲁甸MS6.5地震序列为例,采用滑动连续拟合与预测的方式,考察了ETAS模型参数的动态变化和余震短期发生率预测的实际效能.连续滑动拟合结果表明,在主震发生后的早期阶段,α值有明显的不稳定变化,在震后5.10天稳定在1.6~2.0;p值在震后25.00天内由1.07逐渐下降至0.78左右,其后稳定在0.72~0.85;b值在震后35.00天内逐渐由0.80增加至0.95,其后稳定在0.93~0.97.对连续滑动预测结果的N-test检验表明,余震发生率预测会出现部分失效现象,1天预测时间窗失效比例约为12%、3天预测时间窗失效比例为6%.建议可在震后早期采用1天的较短预测时间窗,而在序列参数较为稳定时段采用较长的3天预测时间窗.     

数据仓库技术在生物信息学中的应用研究

对目前国际互联网中的异地异构生物信息数据源进行研究,分析了生物信息数据的特性,利用数据挖掘技术,设计了一种基于Web的生物信息数据仓库系统的实现方案。采用该方案,可以增强异地生物信息数据库之间的数据交互能力,提高数据库的使用效率;并为解决基于异构数据源的复杂信息数据库的设计提供参考。     

为社会进步服务的测绘高新技术

当今正值国民经济快速发展,科技创新不断涌现。测绘地理信息技术在人类生活中发挥了越来越大的作用,渐渐地形成了跨界发展,越来越多的行业与测绘地理信息技术建立联系。现如今,社会各行各业的发展已经离不开测绘地理信息行业的服务保障,与此同时,随着互联网时代的深度变革,云计算、大数据、人工智能、虚实融合等智能化技术的发展在测绘行业不断渗透,并与测绘地理信息技术相互融合,取得了很多创新性成果。