共查询到20条相似文献,搜索用时 483 毫秒
1.
圆板结构周向表面裂纹识别的振动功率流方法 总被引:5,自引:1,他引:5
从结构噪声的观点,利用振动功率流方法对圆板在集中力作用下的周向表面裂纹进行了诊断研究。周向表面裂纹模拟为转动弹簧,利用断裂力学的有关理论得到其转动刚度。在高频情况下,研究了圆板在中心受集中载荷作用下的弯曲波运动以及输入的振动功率流,分析了振动功率流与破损位置及其特征尺寸的关系,从而可进行有效的破损诊断。 相似文献
2.
运用非线性规划的方法对满足破损船舶安全性要求的可行航速下的拖缆参数进行优化计算,并通过目标决策方法选择最优航速及拖缆参数方案,对于方案的可用程度给出了定量的评价,提供了破损船舶拖带计算的一种方法. 相似文献
3.
海洋锋是重要的中尺度海洋现象,具有数据量小、目标小、弱边缘等特性。针对实际检测任务中弱边缘、小目标海洋锋的检测精度低、错检及漏检率高等问题,融合scSE (spatial and channel Squeeze&Excitation)空间注意力模块构建了一种改进的Mask R-CNN海洋锋检测模型。该方法首先对Mask R-CNN骨干网络结构进行改进,采用scSE模块引导的ResNet-50网络作为特征提取网络,通过加权策略对图像通道和空间位置进行特征突出,提升网络对重要特征的提取能力;其次,针对海洋锋目标边缘定位不准确的问题,引入IoU boundary loss构建新的Mask损失函数,提高边界检测精度。最后,为验证方法的有效性,从训练数据和实验模型上,分别设计多组对比实验。实验结果表明,相比传统Mask R-CNN、YOLOv3神经网络及现有Mask R-CNN改进网络,本文方法对SST梯度影像数据集上的强、弱海洋锋检测效果最好,定位准确率(IoU,Intersection-over-union))及检测精度(mAP,Mean Average Precision)均达0.... 相似文献
4.
5.
为实现对养殖鳗鲡(Anguilla)摄食强度的准确评估,提出了一种基于双流残差卷积神经网络的鳗鲡摄食强度评估方法,该方法针对传统双流网络(Two-stream)中存在的问题做出了相应的改进。首先针对传统双流网络存在网络结构较浅,无法提取到充分的鳗鲡摄食行为特征的问题,选择使用ResNet50网络进行替换,以提取到更具代表性的特征。其次针对传统双流网络最后的分类结果是把空间流和时间流的得分取平均值融合而获得,这种方式较为简单,且其空间流和时间流网络为独立进行训练,容易导致网络出现学习不到鳗鲡摄食行为的时空关联特征的问题,选择使用特征层融合方式对空间流和时间流网络提取获得的特征进行融合,让网络能够并行进行训练,以提取到时空信息间的关联特征。试验结果表明:文内提出的基于双流残差卷积神经网络的鳗鲡摄食强度评估方法准确率达到98.6%,与单通道的空间流和时间流网络相比,准确率分别提升了5.8%和8.5%,与传统的双流网络相比准确率也提升了3.2%。 相似文献
6.
分形理论在空间网络分布特征研究中的应用 总被引:1,自引:0,他引:1
探讨了以图论为基础的空间网络的测度方法,以及以分形理论为基础的表达空间网络分布特征的几种分维数,并阐述了各种分维数的地理意义,最后对于分维数的测算进行了评述. 相似文献
7.
对鱼类的行为进行智能监测,精准地量化与识别其健康状态,已成为研究热点。为实现养殖鳗鲡行为状态精准识别,提出一种基于DenseNet双流卷积神经网络的鳗鲡行为状态检测方法。利用混合高斯背景模型进行前景提取构建数据集,针对传统卷积神经网络对于时间动态信息提取能力有限的问题,搭建关联空间特征与时间特征的双流网络结构(Two-stream),并使用DenseNet-121网络替换原网络,对比VGGNet、ResNet等网络,通过密集连接实现特征重用,在搭建更深的网络结构基础上加强了运动特征传递并减少了参数量,更好地提取具有代表性的行为特征。传统双流网络在两端的softmax层仅作简单的决策层平均融合,无法更深程度关联时空高级特征,提出在网络卷积层提取空间特征与时间特征后,加上一层卷积层将时空特征进行卷积融合以提升模型识别精度。实验结果表明:文中提出的基于DenseNet双流卷积神经网络对6种鳗鲡行为状态检测方法准确率达到96.8%,相较于单通道的空间流与时间流网络,准确率分别提升了10.1%和9.5%;相较于以VGGNet、ResNet搭建的双流网络,准确率分别提升了12.4%和4.2%;与决... 相似文献
8.
9.
本文在总结对16块因耐久性破损而拆换下来的码头面板进行详细的鉴定分级和残余承载力测定试验所取得成果的基础上,对砼板破损程度检测方法、破损等级的划分标准以及相应的维修处理提出了建议意见,并提出了由破损程度估计承载力拆减系数的经验公式。 相似文献
10.
运用复杂网络理论的分析方法,在世界海运船期数据的基础上,构建海洋货运网络。通过拓扑结构分析,描述了网络的空间格局,并采用k-core算法对网络进行分层,提出使用最大连通规模的相对大小及网络效率的相对大小衡量该类网络抗毁性,并提出以整体网络及分层后的多层网络进行随机攻击的方式,分析该网络的抗毁性,结果表明:海洋货运网络具有小世界效应,网络密集且度分布近似幂律分布,符合复杂网络的基本特征。网络对于随机出现的各类海洋灾害所造成的网络损毁具有很强的抗毁性,网络中节点损毁数量为影响网络规模及效率的主要因素,一般性攻击对于网络造成的影响集中于网络效率的下降,关键性节点损毁对于网络整体的运输情况影响不明显。 相似文献
11.
12.
海洋沉积物工程定名对于开展海洋工程建设具有重要作用,然而海底粉土和黏性土的定名受人为因素影响容易产生误差。使用人工神经网络的方法对黄河口埕岛海域284组细粒土数据进行了训练和学习,得到了只利用沉积物粒径质量分数进行定名的方法。结果表明,使用人工神经网络的方法能够有效地对沉积物进行工程定名。当网络含有5个输入层节点、9个隐藏层节点、3个输出层节点、训练函数为Scaled conjugate gradient时定名准确率最高,检验准确率高达97.7%。训练数据的数量是造成神经网络预测存在误差的重要因素,随着数据量的增加,网络的可靠性和通用程度将越来越高。 相似文献
13.
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. 相似文献
14.
This paper deals with the application of nonparametric system identification to a nonlinear maneuvering model for large tankers using artificial neural network method. The three coupled maneuvering equations in this model for large tankers contain linear and nonlinear terms and instead of attempting to determine the parameters (i.e. hydrodynamic derivatives) associated with nonlinear terms, all nonlinear terms are clubbed together to form one unknown time function per equation which are sought to be represented by the neural network coefficients. The time series used in training the network are obtained from simulated data of zigzag maneuvers and the proposed method has been applied to these data. The neural network scheme adopted in this work has one middle or hidden layer of neurons and it employs the Levenberg–Marquardt algorithm. Using the best choices for the number of hidden layer neurons, length of training data, convergence tolerance etc., the performance of the proposed neural network model has been investigated and conclusions drawn. 相似文献
15.
16.
17.
Conventional retrieval and neural network methods are used simultaneously to retrieve sea surface wind speed(SSWS) from HH-polarized Sentinel-1(S1) SAR images. The Polarization Ratio(PR) models combined with the CMOD5.N Geophysical Model Function(GMF) is used for SSWS retrieval from the HH-polarized SAR data. We compared different PR models developed based on previous C-band SAR data in HH-polarization for their applications to the S1 SAR data. The recently proposed CMODH, i.e., retrieving SSWS directly from the HHpolarized S1 data is also validated. The results indicate that the CMODH model performs better than results achieved using the PR models. We proposed a neural network method based on the backward propagation(BP)neural network to retrieve SSWS from the S1 HH-polarized data. The SSWS retrieved using the BP neural network model agrees better with the buoy measurements and ASCAT dataset than the results achieved using the conventional methods. Compared to the buoy measurements, the bias, root mean square error(RMSE) and scatter index(SI) of wind speed retrieved by the BP neural network model are 0.10 m/s, 1.38 m/s and 19.85%,respectively, while compared to the ASCAT dataset the three parameters of training set are –0.01 m/s, 1.33 m/s and 15.10%, respectively. It is suggested that the BP neural network model has a potential application in retrieving SSWS from Sentinel-1 images acquired at HH-polarization. 相似文献
18.
A method for determining the total ozone (TO) with high spatial (3×3 km2) and temporal (15 min) resolutions by using measurements of the Earth’s outgoing thermal radiation from Meteosat geostationary satellites is proposed. The method is based on measurements with a SEVIRI instrument (eight IR channels) and involves additional information on the three-dimensional field of the atmospheric temperature and on the surface temperature obtained from polar satellites (AIRS instrument). The inverse problem of TO determination is solved by the method of neural networks. TO measurements with the AIRS instrument are also used for training the neural networks. Ground-based TO measurements at the international ozonometric network are used for controlling the quality of AIRS data and detecting the errors of the proposed method of TO determination from SEVIRI data. The mean and rms differences between TO values obtained with the use of the proposed method and from the results of measurements at the international ozonometric network are shown to be 1.5 and 6.5%, respectively. Examples of TO distributions reconstructed with high spatial and temporal resolutions are presented. These examples show that the elaborated method for solving various scientific and applied problems and, in particular, for investigating stratospheric dynamics is promising. 相似文献
19.
基于现场实验数据集及人工神经网络技术,论文提出了一种从海中粒子吸收光谱提取浮游植物吸收光谱的方法。这个数据集包含了海中粒子吸收光谱和对应的浮游植物吸收光谱,并被分为三个子集:训练集、印证集和试验集。本研究所利用的人工神经网络系统为多层感知器,训练后的人工神经网络的性能由印证集和试验集来评价。实验结果表明,文中所提出的方法可成功地提取浮游植物的吸收光谱,其提取精度与传统的实验方法相当。 相似文献
20.
The offshore jacket platform is a complex and time-varying nonlinear system,which can be excited of harmful vibration by external loads.It is difficult to obtain an ideal control performance for passive control methods or traditional active control methods based on accurate mathematic model.In this paper,an adaptive inverse control method is proposed on the basis of novel rough neural networks (RNN) to control the harmful vibration of the offshore jacket platform,and the offshore jacket platform model is established by dynamic stiffness matrix (DSM) method.Benefited from the nonlinear processing ability of the neural networks and data interpretation ability of the rough set theory,RNN is utilized to identify the predictive inverse model of the offshore jacket platform system.Then the identified model is used as the adaptive predictive inverse controller to control the harmful vibration caused by wave and wind loads,and to deal with the delay problem caused by signal transmission in the control process.The numerical results show that the constructed novel RNN has advantages such as clear structure,fast training speed and strong error-tolerance ability,and the proposed method based on RNN can effectively control the harmfid vibration of the offshore jacket platform. 相似文献