SAM Era:Can It Segment Any Industrial Surface Defects?

Segment Anything Model(SAM)is a cutting-edge model that has shown impressive performance in general object segmentation.The birth of the segment anything is a groundbreaking step towards creating a universal intelligent model.Due to its superior performance in general object segmentation,it quickly gained attention and interest.This makes SAM particularly attractive in industrial surface defect segmentation,especially for complex industrial scenes with limited training data.However,its segmentation ability for specific industrial scenes remains unknown.Therefore,in this work,we select three representative and complex industrial surface defect detection scenarios,namely strip steel surface defects,tile surface defects,and rail surface defects,to evaluate the segmentation performance of SAM.Our results show that although SAM has great potential in general object segmentation,it cannot achieve satisfactory performance in complex industrial scenes.Our test results are available at:https://github.com/VDT-2048/SAM-IS.

Printed Circuit Board (PCB) Surface Micro Defect Detection Model Based on Residual Network with Novel Attention Mechanism

Printed Circuit Board(PCB)surface tiny defect detection is a difficult task in the integrated circuit industry,especially since the detection of tiny defects on PCB boards with large-size complex circuits has become one of the bottlenecks.To improve the performance of PCB surface tiny defects detection,a PCB tiny defects detection model based on an improved attention residual network(YOLOX-AttResNet)is proposed.First,the unsupervised clustering performance of the K-means algorithm is exploited to optimize the channel weights for subsequent operations by feeding the feature mapping into the SENet(Squeeze and Excitation Network)attention network;then the improved K-means-SENet network is fused with the directly mapped edges of the traditional ResNet network to form an augmented residual network(AttResNet);and finally,the AttResNet module is substituted for the traditional ResNet structure in the backbone feature extraction network of mainstream excellent detection models,thus improving the ability to extract small features from the backbone of the target detection network.The results of ablation experiments on a PCB surface defect dataset show that AttResNet is a reliable and efficient module.In Torify the performance of AttResNet for detecting small defects in large-size complex circuit images,a series of comparison experiments are further performed.The results show that the AttResNet module combines well with the five best existing target detection frameworks(YOLOv3,YOLOX,Faster R-CNN,TDD-Net,Cascade R-CNN),and all the combined new models have improved detection accuracy compared to the original model,which suggests that the AttResNet module proposed in this paper can help the detection model to extract target features.Among them,the YOLOX-AttResNet model proposed in this paper performs the best,with the highest accuracy of 98.45% and the detection speed of 36 FPS(Frames Per Second),which meets the accuracy and real-time requirements for the detection of tiny defects on PCB surfaces.This study can provide some new ideas for other real-time online detection tasks of tiny targets with high-resolution images.

Development of vehicle-recognition method on water surfaces using LiDAR data:SPD^(2)(spherically stratified point projection with diameter and distance)

Swarm robot systems are an important application of autonomous unmanned surface vehicles on water surfaces.For monitoring natural environments and conducting security activities within a certain range using a surface vehicle,the swarm robot system is more efficient than the operation of a single object as the former can reduce cost and save time.It is necessary to detect adjacent surface obstacles robustly to operate a cluster of unmanned surface vehicles.For this purpose,a LiDAR(light detection and ranging)sensor is used as it can simultaneously obtain 3D information for all directions,relatively robustly and accurately,irrespective of the surrounding environmental conditions.Although the GPS(global-positioning-system)error range exists,obtaining measurements of the surface-vessel position can still ensure stability during platoon maneuvering.In this study,a three-layer convolutional neural network is applied to classify types of surface vehicles.The aim of this approach is to redefine the sparse 3D point cloud data as 2D image data with a connotative meaning and subsequently utilize this transformed data for object classification purposes.Hence,we have proposed a descriptor that converts the 3D point cloud data into 2D image data.To use this descriptor effectively,it is necessary to perform a clustering operation that separates the point clouds for each object.We developed voxel-based clustering for the point cloud clustering.Furthermore,using the descriptor,3D point cloud data can be converted into a 2D feature image,and the converted 2D image is provided as an input value to the network.We intend to verify the validity of the proposed 3D point cloud feature descriptor by using experimental data in the simulator.Furthermore,we explore the feasibility of real-time object classification within this framework.

Spectral Reflectance Characteristics of Different Snow and Snow-Covered Land Surface Objects and Mixed Spectrum Fitting

The field spectroradiometer was used to measure spectra of different snow and snow-covered land surface objects in Beijing area.The result showed that for a pure snow spectrum,the snow reflectance peaks appeared from visible to 800 nm band locations;there was an obvious absorption valley of snow spectrum near 1 030 nm wavelength.Compared with fresh snow,the reflection peaks of the old snow and melting snow showed different degrees of decline in the ranges of 300～1 300,1 700～1 800 and 2 200～2 300 nm,the lowest was from the compacted snow and frozen ice.For the vegetation and snow mixed spectral characteristics,it was indicated that the spectral reflectance increased for the snow-covered land types(including pine leaf with snow and pine leaf on snow background), due to the influence of snow background in the range of 350～1 300 nm.However, the spectrum reflectance of mixed pixel remained a vegetation spectral characteristic.In the end,based on the spectrum analysis of snow,vegetation,and mixed snow/vegetation pixels,the mixed spectral fitting equations were established,and the results showed that there was good correlation between spectral curves by simulation fitting and observed ones(correlation coefficient R2=0.950 9).

An Objective Analysis Method for Surface Residual Current Field in the East China Seas

Since the volume transport across the pycnocline is much smaller than that in the mixed layer, the current in the mixed layer can be regarded as non-divergent. An objective analysis method is deduced based on this hypothesis. The linear combination method is used to solve the non-divergent component of the current field of an ocean basin containing islands,which is equivalent to a mathematical problem of solving a Poisson equation in a multi-connected domain. The method is applied to the Bohai Sea, the Yellow Sea and the East China Sea (ECS). The modeled result is consistent with the current maps constructed by other oceanographers.

Algorithm and System of Scanning Color 3D Objects

This paper presents a complete system for scanning the geometry and texture of a large 3D object, then the automatic registration is performed to obtain a whole realistic 3D model. This system is composed of one line strip laser and one color CCD camera. The scanned object is pictured twice by a color CCD camera. First, the texture of the scanned object is taken by a color CCD camera. Then the 3D information of the scanned object is obtained from laser plane equations. This paper presents a practical way to implement the three dimensional measuring method and the automatic registration of a large 3D object and a pretty good result is obtained after experiment verification.

A new GIS-compatible methodology for visibility analysis in digital surface models of earth sites

As a GIS tool,visibility analysis is used in many areas to evaluate both visible and non-visible places.Visibility analysis builds on a digital surface model describing the terrain morphology,including the position and shapes of all objects that can sometimes act as visibility barriers.However,some barriers,for example vegetation,may be permeable to a certain degree.Despite extensive research and use of visibility analysis in different areas,standard GIS tools do not take permeability into account.This article presents a new method to calculate visibility through partly permeable obstacles.The method is based on a quasi-Monte Carlo simulation with 100 iterations of visibility calculation.Each iteration result represents 1%of vegetation permeability,which can thus range from 1%to 100%visibility behind vegetation obstacles.The main advantage of the method is greater accuracy of visibility results and easy implementation on any GIS software.The incorporation of the proposed method in GIS software would facilitate work in many fields,such as architecture,archaeology,radio communication,and the military.

Analysis of Conductors＇ Surface Electric Field of UHVDC Transmission Lines Based on Optimized Charge Simulation Method

The choice of the UHV lines depends on surface electric field of the bundle conductors.Based on existing calculation methods,the optimized charge simulation method is used to calculate the conductors' surface electrical field of±800 kV UHVDC transmission lines in this paper.During calculation,the offset distance is set as the variance of the objective function,the position and the quantity of the simulation charges are optimized with the gold section method,and the surface electrical field is calculated when the charge is in the optimal position.The result shows that the distribution of the surface electrical field and its maximal value can be calculated accurately with this method,although less number of simulation charges is used in this proposed method and the calculation is simple.

Ambiguous Cylinders: a New Class of Impossible Objects

This paper presents a new class of surfaces that give two quite different appearances when they are seen from two special viewpoints. The inconsistent appearances can be perceived by simultaneously viewing them directly and in a mirror. This phenomenon is a new type of optical illusion, and we have named it the ＂ambiguous cylinder illusion＂, because it is typically generated by cylindrical surfaces. We consider why this illusion arises, and we present a mathematical method for designing ambiguous cylinders.

横向沙丘表面与上方矩形截面柱复合电磁散射的FDTD研究

分别使用指数型分布和高斯型分布表示沙漠表面的高度起伏状况,采用蒙特卡罗方法模拟横向沙丘表面和沙丘与沙丘间平坦沙漠表面,运用Herkelrath提出的土壤湿度与介电常数的通用式计算沙土的介电常数,选用FDTD数值计算方法分析高度起伏均方根、入射角度、目标长度、目标宽度、目标高度、横向沙丘的高度和横向沙丘迎风坡坡底到坡顶的水平距离的变化对散射系数的影响,得到横向沙丘表面与上方目标的复合电磁散射特性。分析了粗糙面为指数型分布和高斯型分布时散射系数的角分布曲线的不同之处。

基于点云目标检测算法的船体分段合拢面构件识别方法

在船体分段合拢面精度检测方面,三维激光扫描仪相比全站仪具有高效、高精度和操作便捷等优势。但扫描点云往往数据量庞大且会包含大量与设计模型无关的周围空间点,不仅增加运算时间而且影响配准精度。基于显著构件的点云配准方法能解决该问题,但实现显著构件的智能识别,还需要一种针对船体分段合拢面构件的智能识别算法。采用深度学习方法,构建一种基于点的、无锚点单阶段目标检测神经网络模型,其适用于船体分段合拢面点云数据,基本实现了对船体分段合拢面上构件的智能识别。使用ADAM优化器对网络进行优化训练,在测试集上获得了平均精确度均值P_(A-m)为64.36%的效果。研究成果可用于改进点云粗配准方法,为实现船体分段合拢面精度的智能高效检测提供帮助。

基于改进YOLOX的水库水面漂浮物目标检测算法

针对目前水库水面小目标漂浮物检测识别精度低的问题,提出基于改进YOLOX的水库水面漂浮物目标检测算法。此算法引入新型dark2模块融入主干网络并拓展主干网络的分支输出结构,提升主干网络对图片的特征提取能力。在此基础上,提出改进特征融合模块(ZL-FPN),用于增强特征图信息融合,提高对水库水面小目标漂浮物的检测精度。结果表明:改进后算法的mAP值比YOLOv4和原YOLOX算法分别提升了29.93%和12.11%,有效提升了水库水面漂浮物检测精度。研究成果可为提升水库智能化管理水平提供有效技术支撑。

盾构法隧道开挖面稳定性下的多目标优化研究

盾构法隧道开挖过程中开挖面稳定性保持非常重要,开挖面稳定性下提升工程进度、保障工程质量等目标具有重要的工程意义。目前,针对开挖面稳定性下的多目标优化控制的研究不足。选择掘进效率作为工程进度的指标,选择掘进过程引起的最大地表沉降作为工程质量指标。采用分层序列法和NSGA-II多目标优化算法,将盾构开挖面稳定作为第一层优化目标,工程进度与工程质量作为第二层优化目标,研究盾构开挖面稳定下多目标优化。在一段连续穿越堤坝、空地、敏感建筑三个场景的施工隧道中应用本研究方法,结果表明,优化后的盾构推力维持在上下限区间内,提高了施工效率和减少了地表沉降。本文方法能够根据实际工况自适应的调整和优化控制策略,提高了在实际工程中的适应性和灵活性。为类似盾构隧道工程提供了参考和指导。

基于CatBoost-MOEAD的大直径泥水盾构施工多目标预测优化

为有效优化盾构施工参数,实现在大直径泥水盾构掘进过程中安全、高效和节能的目标,提出分类助推(CatBoost)和基于分解的多目标进化算法(MOEAD)相结合的混合智能算法;综合考虑盾构施工参数与地质条件,以主要的盾构施工参数为研究对象,选择地表沉降、贯入度和掘进比能为预测和控制目标;优化调控选择的盾构施工参数,并以武汉市轨道交通某号线为例,验证该混合算法的有效性。结果表明:采用CatBoost算法建立的预测模型在大直径泥水盾构上表现出来的预测性能良好,对3个控制目标的拟合精度(R 2)均达到0.9以上;预测模型的重要性排序表明:大直径泥水盾构的总推进力和推进速度对地表沉降、贯入度和掘进比能有显著影响;所提出的CatBoost-MOEAD混合智能算法对3个控制目标的优化效果明显,地表沉降、贯入度和掘进比能分别达到12.35%、7.47%和10.70%的优化幅度,并给出相应盾构施工参数的控制范围。

采用改进多目标粒子群算法的斜拉桥阻尼器参数优化

为克服大跨度斜拉桥黏滞阻尼器优化设计效率低、多个相互制约的减震控制目标的问题难以权衡,基于遗传算法的“变异”方法,提出了改进多目标粒子群算法来进行阻尼器参数优化设计。建立大跨度斜拉桥的有限元模型,开展了全桥地震响应分析,根据抗震需求在桥梁纵向设置黏滞阻尼器;分别建立了塔底弯矩、阻尼力和梁端位移的减震响应与阻尼器参数之间的响应面数学模型;以减震响应面模型为研究对象,通过该算法进行阻尼器参数全局自动寻优分析,确定了阻尼器的最优参数,并与采用参数敏感性分析方法确定的一组阻尼参数进行对比分析。研究结果表明:该优化方法具有计算精度好、优化效率高和更好地权衡多个相互制约的减震控制目标的优点;通过优化算法获得的阻尼器参数组合相比采用参数敏感性分析方法获得的阻尼参数组合的减震响应,塔底弯矩增大1.73%,阻尼力减小5.97%,梁端位移减小1.66%;在无需多次有限元试算的基础上确定了更高精度的阻尼器优化参数组合,在提高减震效果的同时大大提升了计算效率。

基于Vague集和响应面模型的注塑工艺多目标优化

针对注塑工艺多目标优化问题,以塑件的翘曲变形量、顶出时体积收缩率和缩痕深度作为优化目标,选取熔体温度、模具温度、注射时间、保压压力、保压时间等工艺参数为试验因素,采用中心复合试验设计结合模流分析建立试验样本,利用Vague集方法计算各优化目标相似度,通过指标相关性的指标权重确定(CRITIC)法确定各优化目标影响权重,得到综合相似度;建立综合相似度与各工艺参数之间的响应面模型,运用灰狼算法进行工艺参数寻优,得到最优工艺参数组合。结果表明,将Vague集和响应面模型相结合的优化结果显著,为实际生产过程提供了有益参考。

基于双流YOLOv4的金属表面缺陷检测方法

目前有许多学者使用深度学习进行表面缺陷检测研究,由于这些研究大都沿用主流目标检测算法的思路,注重高级语义特征,而忽视了低级语义信息(色彩、形状)对表面缺陷检测的重要性,因此导致缺陷检测效果不够理想。为解决上述问题,提出了一种金属表面缺陷检测网络——双流YOLOv4网络,骨干网络分成两个分支,输入分为高分辨率图像和低分辨率图像,浅分支负责从高分辨率图像中提取低级特征,深分支负责从低分辨率图像中提取高级特征,通过削减两分支的层数和通道数来减少模型总参数量;为了强化低级语义特征,提出了一种树形多尺度融合方法(Tree-structured Multi-scale Feature Fusion Me-thod,TMFF),并设计了一个结合极化自注意力机制和空间金字塔池化的特征融合模块(Feature Fusion Module with Polarized Self-Attention Mechanism and Spatial Pyramid Pooling,FFM-PSASPP)应用到TMFF中。在东北大学热轧带表面缺陷数据集NEU-DET、金属表面缺陷数据集GC10-DET和伊莱特电饭煲内胆缺陷数据集Enaiter的测试集上对所提算法进行了测试,测得的map@50结果分别为0.80,0.66和0.57,相比大部分主流的用于缺陷检测的目标检测算法均有提升,且模型参数量仅为原YOLOv4的一半,速度与YOLOv4接近,可满足实际使用需求。

气体辅助注射成型时间参数的CCD响应面法多目标优化

相比于传统塑料注射成型,延迟时长和注气时长是气体辅助注射成型(简称气辅成型)特有的工艺参数,增加了气辅成型的复杂性。为了精确设计延迟时长和注气时长的取值,获得理想的气体穿透效果和气指幅度,以具有典型气辅结构的塑件为研究对象,首先采用气辅成型全三维CAE研究了延迟时长和注气时长对气辅成型质量的影响。结果表明,适当增加延迟时长,可以减小或消除气指缺陷,提高气体穿透深度行程,但过长的延迟时长会导致“短射”,过短的延迟时长则会导致严重的气指缺陷;增加注气时长可以提高气体穿透效果,减少表面缺陷,降低内应力和翘曲变形,但注气时长过长时,气指内部的高压氮气会导致其撕裂而形成严重的气指缺陷,更甚者会使气辅塑件膨胀而报废。采用CCD响应面法进行多目标优化,精确设计了延迟时长和注气时长的取值,延迟时长为4 s、注气时长为10.37 s。通过CAE分析和成型试验验证,精确取值下成型的气辅塑件的气体穿透效果和气辅成型质量良好,提高了气辅成型质量和效率,可用于气辅成型实际生产。

多绳摩擦提升机多连杆锁绳装置的设计与优化

针对现有锁绳装置锁绳低效、松绳困难、锁绳力不足等问题,设计出一种能够实现在各种载荷工况(尤其重载)下安全、高效地进行锁绳作业的提升钢丝绳锁紧装置(简称锁紧装置)。使用SolidWorks对锁绳装置进行三维建模,采用ANSYS对锁绳装置进行有限元分析;然后对锁绳装置关键部位第一连杆进行优化设计,采用中间复合材料设计方法获得初始优化数据组,并且使用Kriging模型建立响应面模型;最后采用多目标遗传算法进行优化。优化结果显示:第一连杆变形量减小17.46%,最大等效应力减小16.18%,显著提高了锁绳装置的综合性能,为矿井的安全、高效生产提供了保障。

基于RSM-正交法的磁障式直线永磁游标电机的设计与优化

针对直线永磁游标电机的损耗问题,提出一种磁障式拓扑结构。通过在次级的凸极齿加入隔磁磁障,使次级对磁通的流动具有导向作用,减少涡流损耗,提高电机的磁场调制能力。在此基础上,设计一种磁障式直线永磁游标电机,采用响应面(RSM)-正交法对电机的推力性能进行优化。首先,通过对电机进行灵敏度分析,确定显著变量。其次,根据RSM法建立优化目标响应与显著变量之间的拟合模型,并对其拟合精度进行评估。最后,基于该模型进行正交试验,根据正交试验的数据进行极差分析,得到电机的最优结构参数。有限元实验结果表明,采用RSM-正交优化方法的电机性能得到大幅提高,并且可以节省优化时间,提高优化效率,对直线永磁游标电机的设计与优化有重要的参考价值。