A High-Accuracy Curve Boundary Recognition Method Based on the Lattice Boltzmann Method and Immersed Moving Boundary Method

Applying numerical simulation technology to investigate fluid-solid interaction involving complex curved bound-aries is vital in aircraft design,ocean,and construction engineering.However,current methods such as Lattice Boltzmann(LBM)and the immersion boundary method based on solid ratio(IMB)have limitations in identifying custom curved boundaries.Meanwhile,IBM based on velocity correction(IBM-VC)suffers from inaccuracies and numerical instability.Therefore,this study introduces a high-accuracy curve boundary recognition method(IMB-CB),which identifies boundary nodes by moving the search box,and corrects the weighting function in LBM by calculating the solid ratio of the boundary nodes,achieving accurate recognition of custom curve boundaries.In addition,curve boundary image and dot methods are utilized to verify IMB-CB.The findings revealed that IMB-CB can accurately identify the boundary,showing an error of less than 1.8%with 500 lattices.Also,the flow in the custom curve boundary and aerodynamic characteristics of the NACA0012 airfoil are calculated and compared to IBM-VC.Results showed that IMB-CB yields lower lift and drag coefficient errors than IBM-VC,with a 1.45%drag coefficient error.In addition,the characteristic curve of IMB-CB is very stable,whereas that of IBM-VC is not.For the moving boundary problem,LBM-IMB-CB with discrete element method(DEM)is capable of accurately simulating the physical phenomena of multi-moving particle flow in complex curved pipelines.This research proposes a new curve boundary recognition method,which can significantly promote the stability and accuracy of fluid-solid interaction simulations and thus has huge applications in engineering.

Assessment of modification level of hypoeu- tectic Al-Si alloys by pattern recognition of cooling curves

Most evaluations of modification level are done according to a specific scale based on an American Foundry Society (AFS) standard wall chart as qualitative analysis in Al-Si casting production currently. This method is quite dependent on human experience when making comparisons of the microstructure with the standard chart. And the structures depicted in the AFS chart do not always resemble those seen in actual Al-Si castings. Therefore, this qualitative analysis procedure is subjective and can introduce human-caused errors into comparative metallographic analyses. A quantization parameter of the modification level was introduced by setting up the relationship between mean area weighted shape factor of eutectic silicon phase and the modification level using image analysis technology. In order to evaluate the modification level, a new method called "intelligent evaluating of melt quality by pattern recognition of thermal analysis cooling curves" has also been introduced. The results show that silicon modification level can be precisely assessed by comparison of the cooling curve of the melt to be evaluated with the one most similar to it in a database.

Pre-process algorithm for satellite laser ranging data based on curve recognition from points cloud

The satellite laser ranging （SLR） data quality from the COMPASS was analyzed, and the difference between curve recognition in computer vision and pre-process of SLR data finally proposed a new algorithm for SLR was discussed data based on curve recognition from points cloud is proposed. The results obtained by the new algorithm are 85 % （or even higher） consistent with that of the screen displaying method, furthermore, the new method can process SLR data automatically, which makes it possible to be used in the development of the COMPASS navigation system.

A fault recognition method based on clustering linear regression

Aiming at the problems of low accuracy,long time consumption,and failure to obtain quantita-tive fault identification results of existing automatic fault identification technic,a fault recognition method based on clustering linear regression is proposed.Firstly,Hough transform is used to detect the line segment of the enhanced image obtained by the coherence cube algorithm.Secondly,the endpoint of the line segment detected by Hough transform is taken as the key point,and the adaptive clustering linear regression algorithm is used to cluster the key points adaptively according to the lin-ear relationship between them.Finally,a fault is generated from each category of key points based on least squares curve fitting method to realize fault identification.To verify the feasibility and pro-gressiveness of the proposed method,it is compared with the traditional method and the latest meth-od on the actual seismic data through experiments,and the effectiveness of the proposed method is verified by the experimental results on the actual seismic data.

基于Curvelet稳定特征曲面的掌纹识别新方法

针对掌纹特征提取困难、稳定性较差以及特征维数较大的问题,提出一种基于Curvelet稳定特征曲面的掌纹识别方法.将掌纹图像经Curvelet变换得到稳定特征曲面,把该曲面作为特征进行匹配,不仅避免了特征提取或图像编码等传统繁琐操作,而且特征维数较低,在保证识别精度的同时,图像稳定性增强,识别速度较快.最后,采用归一化相关分类器对掌纹所属类别进行判定,通过PolyU掌纹库的验证,本文算法的等误率为1.769 0%,匹配时间为16.6 ms,表明了本文算法的有效性.

A Topology Mapping Method for Feature Extraction of Irregular Curve Shape

ＡＴｏｐｏｌｏｇｙＭａｐｐｉｎｇＭｅｔｈｏｄｆｏｒＦｅａｔｕｒｅＥｘｔｒａｃｔｉｏｎｏｆＩｒｒｅｇｕｌａｒＣｕｒｖｅＳｈａｐｅＧＵＯＺｉｈａｉ；ＷＡＮＧＷｅｉ；ＪＩＡＧｕａｎｇ郭子海，王薇，贾光（Ｄｅｐｔ．ｏｆＣｏｍｐｕｔｅｒＳｃｉｅｎｃｅａｎｄＥｎ...

Some Key Technologies of a New-type CNC Curve Grinding Machine

This paper presented a new-type CNC curve grinding machine, in order to conquer the disadvantages of conventional NC curve grinding machine and improve surface quality, dimensional accuracy and machining efficiency. The new-type grinder adopts some high and new technologies: ① the normal tracing device could make grinding wheel coincide with the normal direction of the machining points in work piece, and improve surface quality and dimensional accuracy; ② the digital image on-line recognition system could monitor machining process and compensate wheel wear in real time; ③ linear motor drive mechanism could realize the exact adjustment of the grinding head digitally and increase the machining efficiency. The math models of normal tracing and circular tolerance zone were presented. The experimental results show that the new-type CNC curve grinding machine equipped with the three devices mentioned above is easy to realize the precision grinding of any complex curve, and improve surface quality, dimensional accuracy and machining efficiency.

Recognition Methods of Geometrical Images of Automata Models of Systems in Control Problem

The laws of functioning of discrete deterministic dynamical systems are investigated,presented in the form of automata models defined by geometric images.Due to the use of the apparatus of geometric images of automata,developed by V.A.Tverdokhlebov,the analysis of automata models is carried out on the basis of the analysis of mathematical structures represented by geometric curves and numerical sequences.The purpose of present research is to further develop the mathematical apparatus of geometric images of automaton models of systems,including the development of new methods for recognizing automata by their geometric images,given both geometric curves and numerical sequences.

面向曲率及边界距离约束的弯曲管道内路径规划

弯曲管道结构是工业探测或医用诊察中常见的一种场景,传统机器人的路径规划大多基于管道中心线的提取,而忽略了在狭窄空间中作业的真实参数约束,易使得作业工具末端受到弯折或挤压,影响作业效率,增加作业风险.针对以上问题,提出了一种面向真实曲率和边界距离参数约束的路径规划方法,在可视化的三维模型中生成管道的中心稠密点集,针对该点集提出两步走的空间特征点识别策略.在选定作业路径的初始点、终止点后,依据邻近点间的曲率均值、极值及差分关系识别曲率极值点、分段点,通过对粗扫描特征点的遍历进一步识别出拐点和宽域节点以及过密点.将识别出的特征点作为型值点,反算得到NURBS曲线及对应插值点的曲率值,通过模型切片搜索得到曲线插值点的边界距离不合格点集.将极值点添加至特征点集中,再通过搜索得到的曲率不合格点集,将极值点进行拟合圆调整至后更新特征点集、在完成自适应轮次的特征点迭代后,检测并标记为空或连续不变的全区间参数不合格点区间集.实验结果证明:弯曲圆柱仿真模型和CT重建肾腔模型的规划路径经由迭代分别满足曲率10 mm^(-1)、8 mm^(-1)的约束.同时最短距离的全区间检测及标记结果也表明本文方法可以在满足曲率要求的前提下尽可能不碰撞管道内壁,验证了本文方法的有效性和可行性.

基于小波变换和CNN-Transformer模型的测井储层流体识别

针对具有复杂储集空间和极强的非均质性的低孔低渗储层,常规测井响应特征不够明显,使用传统解释手段难以有效识别储层流体的问题,提出了一种基于小波变换和CNN-Transformer混合模型的储层流体识别方法。首先,使用小波变换将测井信号从时域扩展到时频域,并生成时频谱图以增强信号特征,然后使用滑动时窗沿着测井曲线深度方向滑动采样,获取代表解释深度处地层信息的频谱特征图,最后,通过训练CNN-transformer模型深度挖掘特征图信息,实现储层流体识别。混合模型在利用储层对应深度处测井数据的同时,又兼顾测井曲线随深度的变化趋势和地层前后信息的关联性,挖掘时频谱图的局部细节和全局特征表示,自动识别流体类型。将模型应用于大港油田22口实测测井资料中,并与CNN和BiLSTM等多个模型的流体识别效果进行对比分析,基于小波变换和CNN-Transformer模型识别效果明显优于其他方法,在测试集上识别准确率达到了92.7%。研究结果表明该方法可以作为低孔渗油藏常规测井资料识别储层流体的有效手段,为流体评价提供了新思路。

时序数据图像化:战术意图识别及可移植框架

通过将时序编码为图像,提出了一种结合曲线滤波技术和EfficientNetV2图像识别网络的鲁棒且可移植的战术意图识别框架。曲线滤波技术可以有效地减少大量时域特征、模型参数和训练时间的冗余,基于此,提出了一种改进的格拉姆角场方法将时序编码为图像,提高了卷积神经网络的特征提取能力。EfficientNetV2网络能够有效地处理意图图像,并成为预训练模型,使得在不同系统之间进行迁移学习成为可能。实验结果表明,所提框架相对于机器学习及深度学习等方法提高了0.99%以上的准确率,具有更好的性能、可扩展性、鲁棒性和可迁移性。

基于转向架航向角的既有铁路平面线形识别方法研究

轨道平面线形识别是解算轨道不平顺的基础。针对外挂式动态轨道检查仪的实际需要,提出一种基于转向架航向角的铁路平面线形识别方法。首先,通过分段试拟合判定准则自动识别各测点所属线元类型和特征点数量;然后,建立基于转向架航向角的平面线形特征点优化模型;最后,结合云模型改进传统遗传算法的搜索策略提出云遗传算法,实现铁路平面线形精确识别。研究表明,平面线路曲线特征点识别偏差在4 m以内,线形识别准确度均达到97%以上,满足外挂式动态轨道检查仪对轨道不平顺解算的精度要求。

选煤厂大煤块智能图像识别方法研究

针对现有选煤厂大煤块识别受到大煤块与矸石线性不可分影响,导致识别效率低、识别精度差的问题,设计了一种选煤厂大煤块智能图像识别方法。首先,应用图像采集设备获取煤块混合图像,并对图像进行增强、去噪等操作,以完成图像预处理。然后,计算煤块的面积和厚度,以获取煤块与矸石的物质特征。最后,基于煤块与矸石的X射线衰减曲线完成识别阈值的设定,并结合最小二乘支持向量机解决煤块与矸石的线性不可分问题,从而完成大煤块图像的智能识别。对比试验结果表明,所提方法应用效果较好、识别率及识别精度较高、识别速度较快,总体性能优于对比方法。该方法可大幅提升大煤块图像识别效果,有较高的应用价值。

V2X环境下基于圆风险域的交通冲突识别模型

为提高快速路匝道区域合流冲突的识别精度,并缓解合流冲突提供决策依据,提出一种V2X(vehicle to everything)环境下基于圆风险域的交通冲突识别模型.通过V2X技术实时获取车辆位置和速度,以冲突风险时间为关键参数,分析主线车辆和匝道车辆的不同运动状态特性;引入风险域概念,结合车辆运动学,构建基于圆风险域冲突识别模型,进而通过两圆的位置关系表征两车之间的运动关系,实现交通冲突的识别;为细化冲突风险程度,采用累计频率曲线法判定冲突风险程度等级.仿真结果表明,采用冲突识别模型的识别率相比未采用时提高25.81%,说明该模型能有效识别匝道合流冲突,提高通行效率,并可为V2X环境下匝道合流车辆提供安全预警.

基于W几何形的恒星光谱分子带检测

研究关注由分子内部能级变化引起的光谱分子带的识别和检测,有助于研究恒星光谱类型和参数估计。首先从分子带的曲线趋势出发,运用曲线分析对分子带进行识别,并剔除具备W形但下降趋势明显的伪分子带。借鉴多类型多分类准则的识别思路,将检测出的分子带尖峰深度、W形宽度、曲线趋势和回升趋势四个参数作为训练特征。这四个参数综合考虑了始点变化速率、曲线变化趋势、极值点分布和曲线形状因素。其次,为了验证该方法的可行性与可靠性,利用LightGBM(light gradient boosting machine)模型分别对F型恒星光谱和分子带特征参数进行识别,准确率分别为97.62%和99.16%,进一步验证了所提取分子带的准确性。本工作不仅能挖掘出晚期恒星,提高数据标签的准确性,还能在准确识别的基础上,利用LightGBM机器学习模型检测未知型光谱自动识别晚期恒星,提高了识别效率并且减少了内存占用。

驾驶人弯道行车生理特性研究进展

文章为探究驾驶人弯道行车时生理特性所发生的变化,从驾驶人的脑电、心电、肌电、眼动及视认行为四个方面入手,总结了弯道行车对驾驶人生理特性的影响,梳理了国内外弯道行车驾驶人生理特性研究现状。结果表明,与直线路段相比,驾驶人在弯道路段行驶时,生理特性会发生显著变化,包括心率加快、脑电β波增长、颈部肌电信号变化和眼动变化。此外,文章还分析了道路不良线形组合导致弯道事故的驾驶人视认原因,以期为弯道路段车辆运行风险防控的相关研究提供参考。

基于Stacking多模型融合的电力负荷曲线识别

精准识别电力负荷曲线类型对于保障电网安全稳定运行和优化能源利用效率尤为重要。针对现有的时序数据识别方法在电力负荷曲线识别任务中准确率低、鲁棒性差等问题,提出了一种多模型融合集成学习的电网负荷曲线识别方法。首先,适应性改进了时序卷积网络、Transformer和Light GBM 3种基础模型,利用负荷曲线的局部、全局和结构信息预测负荷曲线类别;然后,通过Stacking集成学习自适应融合3种模型预测,用以进一步优化识别结果;此外,提出一种基于截断高斯分布的类内时段信号波动建模数据增广策略,旨在解决数据类别不平衡问题,提升识别模型的鲁棒性。仿真结果表明,相较于XG Boost、LSTM和MLP等方法,提出的方法对电网负荷曲线识别的准确率有显著的提高,满足了实际工程的需求。

光刻法制备正方薄片状粒子及其识别算法优化

非球形胶体粒子在凝聚态物理、新型智能材料研发等领域均具有重要的研究价值,其中,正方薄片状胶体粒子由于具有形状简单、可周期性密铺、自组装形成的结构多样等特点,得到了广泛关注。采用光刻法制备了SU-8环氧树脂正方薄片状胶体粒子,粒子的平均边长为2.3μm、平均厚度为1.2μm,顶点在光刻精度影响下,发生小幅度圆角化。通过分析光刻前后粒子的红外吸收光谱发现,光刻后,粒子内部的SU-8环氧树脂交联程度较高。通过计算粒子相互作用势与粒子间距离的关系,证明了粒子间的相互作用为近硬球相互作用。同时,基于正方薄片状胶体粒子在平面及球面的单粒子运动图像,提出了一种新的粒子顶点识别算法,该算法可以避免由图像不清晰导致的粒子错误识别问题。

南海西部海域复杂流体识别方法研究及应用

在研究南海西部复杂流体性质测井、录井响应特征的基础上,优选识别流体性质的敏感参数,编制交会图版,定性识别复杂流体性质;根据敏感参数,形成多条曲线交会,分析层内流体的变化规律;同时通过气测参数计算气油比,定量识别复杂流体性质。

场景图像弯曲文本检测与识别

随着深度学习技术的发展,场景文本检测与识别在近几年取得了巨大的进步,场景文本检测与识别的实现方式也越来越具有多样性。然而,场景文本的表示方式仍然以矩形和旋转矩形居多,该类文本表示方式难以精准表示弯曲的文本实例。为了解决弯曲文本的表示问题,论文提出了一种参数化的弯曲文本表示法,并且基于参数化表示法设计了弯曲文本纠正算法,实现了弯曲文本的形态纠正,降低了识别的难度。通过引入该方法,实现了功能完善的场景文本检测与识别系统。实验结果表明,此方法可以有效完成场景文本的检测与识别任务。