Range estimation of few-shot underwater sound source in shallow water based on transfer learning and residual CNN

Taking the real part and the imaginary part of complex sound pressure of the sound field as features,a transfer learning model is constructed.Based on the pre-training of a large amount of underwater acoustic data in the preselected sea area using the convolutional neural network(CNN),the few-shot underwater acoustic data in the test sea area are retrained to study the underwater sound source ranging problem.The S5 voyage data of SWellEX-96 experiment is used to verify the proposed method,realize the range estimation for the shallow source in the experiment,and compare the range estimation performance of the underwater target sound source of four methods:matched field processing(MFP),generalized regression neural network(GRNN),traditional CNN,and transfer learning.Experimental data processing results show that the transfer learning model based on residual CNN can effectively realize range estimation in few-shot scenes,and the estimation performance is remarkably better than that of other methods.

Few-Shot Object Detection Based on the Transformer and High-Resolution Network

Now object detection based on deep learning tries different strategies.It uses fewer data training networks to achieve the effect of large dataset training.However,the existing methods usually do not achieve the balance between network parameters and training data.It makes the information provided by a small amount of picture data insufficient to optimize model parameters,resulting in unsatisfactory detection results.To improve the accuracy of few shot object detection,this paper proposes a network based on the transformer and high-resolution feature extraction(THR).High-resolution feature extractionmaintains the resolution representation of the image.Channels and spatial attention are used to make the network focus on features that are more useful to the object.In addition,the recently popular transformer is used to fuse the features of the existing object.This compensates for the previous network failure by making full use of existing object features.Experiments on the Pascal VOC and MS-COCO datasets prove that the THR network has achieved better results than previous mainstream few shot object detection.

Cryogenic amplifier with low input-referred voltage noise calibrated by shot noise measurement

A low-noise cryogenic amplifier for the bandwidth from 100 kHz to 2 MHz with commercially available components is presented. The amplifier is mounted on the cold finger of our home-made liquid helium dipstick. The input imp√edance of the amplifier is 2 k？. The input-referred voltage noise of the amplifier at approximately 2 MHz is around 1 n V/Hz^（1/2）. We demonstrate the performance of the amplifier by measuring shot noise on the Al/AlOx/Al tunneling junction with resistance about 17 k？ at liquid helium temperature.

Comparison of the effects of submerged laser peening,cavitation peening and shot peening on the improvement of the fatigue strength of magnesium alloy AZ31

To investigate the improvement in the fatigue strength of magnesium alloy by peening methods,magnesium alloy AZ31 was treated by submerged laser peening(SLP),cavitation peening(CP),and shot peening(SP),and the fatigue properties were evaluated by a plane bending fatigue test.In the case of SLP,both the impact induced by laser ablation(LA)and that caused by laser cavitation(LC),which developed after LA,were used.In the present study,the fatigue life at a constant bending stress was examined to determine the suitable coverage.It was found that the fatigue strengths at N=10^(7)for the SLP,CP,and SP specimens treated by each optimum condition were 56%,18%,and 16%higher,respectively,than that of the non-peened(NP)specimen,which was 97 MPa.The key factors in the improvement of fatigue strength by peening methods were work hardening and the introduction of compressive residual stress.

Effect of Shot Peening on Surface Damage Evolution Behavior of Cu-19Ni Alloy

Shot peening is a surface modification technology with the metal surface nano machine(SNC),which can modify the surface microstructure and extend the fatigue life of Cu-19Ni alloy.The hardness,damage evolution and mechanical properties were investigated and characterized by scanning electron microscope(SEM),laser confocal microscope(LSM)and material surface performance tester(CFT).The results showed that the surface roughness and friction coefficient of Cu-19Ni alloy decreased with the increase of shot peening duration and diameter,while the microhardness and strength increased.Moreover,with the increase in shot peening duration and diameter,SEM observation showed that the fracture dimples became smaller,meanwhile,with the increase of small cleavage planes,shear tearing ridges and the thickness of the surface nano layer,the fracture mode gradually evolved from plastic to brittle fracture.The uniaxial tensile test of shot peened Cu-19Ni alloy was carried out by MTS testing machine combined with digital image correlation technology(DIC).The evolution of Cu-19Ni surface damage was analyzed,and the evolution equations describing the damage of large deformation zone and small deformation zone were established.The effect of shot peening on the damage evolution behavior of Cu-19Ni alloy was revealed.

我国优秀女子铅球运动员宋××旋转投掷技术的加速特征研究

本文采用文献资料法、测试法、数理统计法等研究方法,选取宋××6场投掷比赛,对宋××旋转式投掷技术的速度特征进行研究,以期为提高我国女子旋转投掷技术提供参考。结果发现,(1)宋××旋转投掷过程时间节奏较稳定,但在腾空旋转阶段、最后用力阶段的时间节奏控制不稳定;(2)宋××在进入腾空旋转阶段时,身体重心速度低于器械速度,左侧轴的压紧效果较好;(3)在第二单支撑阶段结束阶段铅球速度未出现明显的“延缓器械速度”现象,器械速度起伏较大,对器械控制不稳定;(4)在左脚着地时刻,左肩速度迅速提高,右肩速度较稳定,有助于稳定器械速度;(5)在第一单支撑阶段两侧肩关节速度变化差值较大,不利于上肢稳定。

SHOTS模拟系统初体验

伴随着计算机技术的不断进步,与以往实物教学培训有着根本不同的模拟器培训已经在很多行业中得到了运用,致力于模拟器开发的法国Sinapse公司也开发出了适用于印刷的模拟器系统,但该模拟系统在国内的印刷行业还没有得到推广。

Video Summarization Approach Based on Binary Robust Invariant Scalable Keypoints and Bisecting K-Means

Due to the exponential growth of video data,aided by rapid advancements in multimedia technologies.It became difficult for the user to obtain information from a large video series.The process of providing an abstract of the entire video that includes the most representative frames is known as static video summarization.This method resulted in rapid exploration,indexing,and retrieval of massive video libraries.We propose a framework for static video summary based on a Binary Robust Invariant Scalable Keypoint(BRISK)and bisecting K-means clustering algorithm.The current method effectively recognizes relevant frames using BRISK by extracting keypoints and the descriptors from video sequences.The video frames’BRISK features are clustered using a bisecting K-means,and the keyframe is determined by selecting the frame that is most near the cluster center.Without applying any clustering parameters,the appropriate clusters number is determined using the silhouette coefficient.Experiments were carried out on a publicly available open video project(OVP)dataset that contained videos of different genres.The proposed method’s effectiveness is compared to existing methods using a variety of evaluation metrics,and the proposed method achieves a trade-off between computational cost and quality.

SHOTS系统在印刷专业教学中的应用探索

结合印刷技术专业实训操作过程中排除印刷故障耗时长、成本高及操作难度大的现状进行了深入的研究剖析,探索了应用SHOTS系统实现与传统印刷机同步模拟排除印刷故障的方式重构实训环节的总体框架,尝试和创新符合学校实际情况的实训教学模式。以真正实现“做中学、学中做”,将印刷理论与实际操作结合在一起,使学生对印刷机的操作更熟练,从而达到在提高教学效率和教学质量的同时又节约资源的目的。

SHOTS模拟培训的优势及其前景

随着计算机技术的不断进步,模拟器培训已经在各行各业中得到广泛的普及,从飞机操作到各种大型机械的培训,模拟器培训获得普遍好评。

第59届国际技术史学会(SHOT)年会综述

2016年6月22日-26日,国际技术史学会（Society for the History of Technology,SHOT）第59届年会在新加坡国立大学举行。法国哲学家和科学社会学家拉图尔（Bruno Latour）、美国技术史家露丝·史瓦兹·柯望（Ruth Schwartz Cowan）和英国爱丁堡大学社会人类学教授、本届SHOT主席白馥兰（Francesca Bray）女士,分别做了主旨报告。

一种基于ISS-SHOT特征的点云配准算法

针对点云配准过程中易产生错误对应点、收敛速度慢、配准时间长等问题,提出了一种基于内部形态描述子(ISS)及方向直方图描述子(SHOT)特征的点云配准算法。运用体素格网法下采样后,采用ISS算法提取特征点,并用SHOT对特征点进行描述,利用余弦相似度匹配对应点对,再采用RANSAC算法剔除错误对应点对,使得两片点云获得良好的初始位姿,最后采用点到平面的ICP算法进行精确配准。试验结果表明,与传统ICP算法及基于ISS的SAC-IA+ICP算法相比,本文算法配准精度及配准效率更高,对数据量大、重叠率较低点云具有很好的稳健性。

基于SHOT、PPF特征的遮挡目标识别研究

针对机器人无序工件分拣过程中在遮挡情况下不同外形工件识别率差异较大的问题,对全局特征描述子和局部特征描述子的描述及投票过程进行详细地分析,分别选取其中实时性较好的PPF(Point Pair Feature)和SHOT(Signature of Histograms of OrienTations)描述子在不同程度遮挡情况下使用不同外形工件进行识别实验,有针对性地对机器人无序分拣中不同外形工件适用的算法进行实验对比和总结,使在不同外形工件上的识别率达到最大化,实验结果表明:PPF全局描述子对工件点云模型的外形特征和遮挡较为敏感,特征不明显工件的识别率为0%,对于外形特征明显、无遮挡的点云模型工件识别速度较快(1 s内)且准确率较高,SHOT局部描述子对遮挡的鲁棒性较强,并且对外形特征不明显工件有一定的识别能力,特征明显与特征不明显工件的识别率均保持在90%以上。

技术史学会(SHOT)年会信息统计分析及启示:2000~2019年

以技术史学会(SHOT)2000~2019年年会日程信息为主要数据源,对会议基本信息进行梳理统计,包括对学者、所属机构和国家、担任重要角色次数进行排序,运用共现方法和聚类分析展示参会者及其所在机构和国家组成的网络,对标题进行词频和时段统计,以及通过对比方式量化显示中国大陆学者和学术机构在年会中的参与情况。统计结果显示了技术史学会年会逐渐增加的规模、年会网络中日趋紧密的学者社区及参会机构存在历时性变化、各国参与程度分组后逐渐递减、会议重视现当代议题等特点,为中国技术史学界的未来发展提供借鉴意义。

Numerical Calculation and Experimental Research on Residual Stresses in Precipitation-hardening Layer of NAK80 Steel for Shot Peening

Shot peening can improve fatigue strength of materials by creating compressive residual stress field in their surface layers,and offers a protection against crack initiation and propagation,corrosion,etc.And fatigue fracture and stress corrosion cracking of NAK80 steel parts are improved effectively.Currently there lacks in-depth research in which the beneficial effect of the residual stress may be offset by the surface damage associated with shot peening,especially in terms of the research on the effective control of shot peening intensity.In order to obtain the surface residual stress field of NAK80 steel after shot peening,the samples are shot peened by pneumatic shot peening machine with different rules.The residual stress in the precipitation-hardening layer of NAK80 steel is measured before and after a shot peening treatment by X-ray diffraction method.In order to obtain true residual stress field,integral compensation method is used to correct results.By setting up analytical model of the residual stress in the process of shot peening,the surface residual stress is calculated after shot peening,and mentioning the reason of errors occurred between calculated and experimental residual stresses,which is mainly caused by the measurement error of the shoot arc height.At the same time,micro hardness,microstructure and roughness in the precipitation-hardening layer of NAK80 steel before and after shot peening were measured and surveyed in order to obtain the relation between shot peening strength and surface quality in the precipitation-hardening layer.The results show that the surface quality of NAK80 steel is significantly improved by shot peening process.The over peening effect is produced when the shot peening intensity is too high,it is disadvantageous to improve sample＇s surface integrity,and leading to reduce the fatigue life.When arc high value of optimal shot peening is 0.40 mm,the surface quality is the best,and the depth of residual stress in the precipitation-hardening layer reaches to about 450 μm.Numerical calculation is very useful to define the process parameters when a specific residual stress profile is intended,either to quantify the benefits on a specific property like fatigue life or to help on modeling a forming process like shot peen forming.In particular,the proposed parameter optimization in the progress of shot peening and effective control of the surface texture provide new rules for the quantitative evaluations of shot peening surface modification of NAK80 steel.

Simulation on Residual Stress of Shot Peening Based on a Symmetrical Cell Model

The symmetrical cell model is widely used to study the residual stress induced by shot peening. However, the correlation between the predicted residual stresses and the shot peening coverage, which is a big challenge for the researchers of the symmetrical cell model, is still not established. Based on the dynamic stresses and the residual stresses outputted from the symmetrical cell model, the residual stresses corresponding to full coverage are evalu- ated by normal distribution analysis. The predicted nodal dynamic stresses with respect to four corner points indicate that the equi-biaxial stress state exists only for the first shot impact. Along with the increase of shot number, the interactions of multiple shot impacts make the fluctuation of the nodal dynamic stresses about an almost identical value more and more obvious. The mean values and standard deviations of the residual stresses gradually tend to be stable with the increase of the number of shot peening series. The mean values at each corner point are almost the same after the third peening series, which means that an equi-biaxial stress state corresponding to the full coverage of shot peening is achieved. Therefore, the mean values of the nodal residual stresses with respect to a specific transverse cross-section below the peened surface can be used to correlate the measured data by X-ray. The predicted residual stress profile agrees with the experimental results very well under 200% peening coverage. An effective correlation method is proposed for the nodal residual stresses predicted by the symmetrical cell model and the shot peening coverage.

基于SHOT特征融合的散乱工件点云配准算法

针对随机箱体抓取过程中目标识别和定位问题,提出一种基于SHOT特征融合的点云配准方法.对结构光三维测量获取的点云进行预处理和分割,得到去除噪声点后的多个工件点云数据集;提出基于方向包围盒裁剪的方法,得到去除稀疏边缘点后的工件点云,结合均匀采样算法获取关键点集;通过改进SHOT特征描述子对关键点进行唯一性描述;采用最小方差法查找工件点云的关键点在模板点云中的对应点,根据对应关系求解初始变换矩阵;最后,使用ICP算法进行精确配准,得到工件的精确位姿信息.实验结果表明,将本文算法与基于FPFH特征配准、SHOT特征配准算法进行对比,配准精度分别提高了30. 07%和37. 10%,配准速度分别提高了35. 64%和21. 21%.

基于SHOTS的印刷竞赛训练题库设计与实现

设计与开发印刷竞赛训练题库,为参加印刷行业职业技能等相关竞赛的学生及从业人员提供训练平台。以法国Sinapse公司推出的SHOTS单张纸胶印模拟系统为开发平台,按照印刷故障类别进行分类,划分为容易、中等、较难3个等级,设置相关题库,实现题目测试功能。应用SHOTS软件的Trainer模块完成竞赛题目设计与制作,共分为10个单元,均通过功能测试。该系统模拟从输纸到收纸的六色印刷全部过程,仿真再现真实印刷机工作过程,有助于印刷相关技术人员培训与辅助教学。

The tribological behavior of a surface-nanocrystallized magnesium alloy AZ31 sheet after ultrasonic shot peening treatment

A magnesium alloy AZ31 sheet was processed by ultrasonic shot peening treatment to fabricate a surface nanocrystalline,and a ball-on-disk dry sliding wear test was performed to evaluate the tribological behavior after treatment.The microstructure observation indicated a gradient nanocrystalline structure was formed after USSP treatment.The microhardness at the top surface was improved from 60 HV to 145 HV after treatment.The formed nanocrystalline resulted in an easy formation of MgO patches on the surface and reduced the coefficient of friction.Moreover,the formed nanocrystalline leaded to a retard of delamination with increasing the sliding speed and applied load,which was due to its stronger sub-surface.Under high sliding speed(0.5 m/s)and high applied load(50 N),it was firstly found that the formed nanocrystalline prevented the happening of thermal softening and melting.The possible reasons accounting for the prevention of thennal softening and melting were discussed accordingly.