Numerical simulation of involutes spline shaft in cold rolling forming

Design of forming dies and whole process of simulation of cold rolling involutes spline can be realized by using of CAD software of PRO-E and CAE software of DEFORM-3D. Software DEFORM-3D provides an automatic and optimized remeshing function, especially for the large deformation. In order to use this function sufficiently, simulation of cold rolling involutes spline can be implemented indirectly. The relationship between die and workpiece, forming force and characteristic of deformation in the forming process of cold rolling involutes spline are analyzed and researched. Meanwhile, reliable proofs for the design of dies and deforming equipment are provided.

TRANSMISSION MOMENTARY EFFICIENCY BASED ON THE D'ALEMBERT-LAGRANGE EQUATION FOR INVOLUTES GEARS

The D'Alembert-Lagrange equation is introduced and used to derive theformulas of momentary efficiency for external gearing of standard involutes spur gears. The gearingswith correct and increased center distance are discussed. The momentary efficiency formula iscalculated and analyzed using software Matlab. The derived formula of momentary efficiency is alsocompared with the traditional formula.

EXPERIMENTAL STUDY ON OPEN－DIE COLD EXTRUSION FORMING TECHNIQUE FOR INVOLUTESPLINE SHAFTS

The deformation principles of the steady- state and the unsteady一state of open- die cold extrusion for involute spline shafts are analyzed by means of experiments. On one hand,based on the deformation principles of the steady- state, data for determining structural parameters of the die, the size of the billet and the constraint condition of this technique are given. On the other hand, according to the principles of the unsteady- state, data for modifying the shapes and sizes of the bil- lets are provided.

基于改进YOLOv7-tiny的高空作业人员安防装备检测算法

针对现有高空作业人员安防装备检测算法参数量较大且检测目标相对单一,难以适应复杂的高空作业场景等问题,提出一种基于改进YOLOv7-tiny的高空作业人员安防装备检测算法。首先,将主干网络重新设计为更轻量的YOLOv7-FasterNet,并调整空间金字塔池化结构,实现模型参数量的压缩;其次,在ELAN-L模块中扩展梯度传输路径的分支,解决了模型压缩造成的通道信息缺失问题,提升了特征信息的提取能力;最后,将网络中下采样部分替换为Involution模块,降低参数冗余,增强网络对全局的捕获能力。实验结果表明,改进的YOLOv7-tiny算法能够更好地适应复杂高空作业场景,在开源数据集上具备良好的性能。该算法的平均检测精度达到94.7%,较原模型提升1.5%,参数量较原模型下降11.6%,实验结果验证了算法改进措施的有效性。

基于IViT的锂离子电池健康状态估计

准确预测锂离子电池的健康状态(SOH)至关重要。针对电池单个周期的不同阶段退化机制存在差异和实际运用场景下数据获取不完整等挑战,提出一种基于Involution-Vision Transformer(IViT)的锂离子电池SOH估计方法。从电压时间曲线中自动提取能有效表征锂离子电池退化信息的特征,使用Involution模块在不同位置上自适应地分配权重,利用Vision Transformer学习不同阶段的高级特征表示并捕获全局依赖关系。实验结果表明,IVIT的预测误差在0.5%左右,且当整体数据缺失50%的情况下误差仅为2%左右,证明了所提方法的有效性和稳定性。

基于Involution算子和协调反向注意力的息肉图像分割

结肠影像中的息肉存在形态多变、边缘粘膜模糊的特点。针对现有的结肠息肉分割网络因卷积算子的固有限制而导致的特征提取不充分,以及因区域和边界关系刻画不全导致的分割不完整的问题,提出一种基于Involution算子和协调反向注意力的网络模型IN-CRNet。在编码器部分,设计基于Involution算子的感受野模块InRFB,自适应地捕获不同尺度的上下文语义信息,增强模型对形态复杂的结肠息肉的识别能力;在解码器部分,设计协调反向注意力模块CRA,同时关注区域和边界的重要程度,并构建两者的关系,自底向上地逐渐完善边缘轮廓的分割细节。在5个结肠息肉数据集上的验证实验表明,IN-CRNet具有良好的分割精度和泛化能力。

Application of Isogeometric Analysis Method in Three-Dimensional Gear Contact Analysis

Gears are pivotal in mechanical drives,and gear contact analysis is a typically difficult problem to solve.Emerging isogeometric analysis(IGA)methods have developed new ideas to solve this problem.In this paper,a threedimensional body parametric gear model of IGA is established,and a theoretical formula is derived to realize single-tooth contact analysis.Results were benchmarked against those obtained from commercial software utilizing the finite element analysis(FEA)method to validate the accuracy of our approach.Our findings indicate that the IGA-based contact algorithmsuccessfullymet theHertz contact test.When juxtaposed with the FEA approach,the IGAmethod demonstrated fewer node degrees of freedomand reduced computational units,all whilemaintaining comparable accuracy.Notably,the IGA method appeared to exhibit consistency in analysis accuracy irrespective of computational unit density,and also significantlymitigated non-physical oscillations in contact stress across the tooth width.This underscores the prowess of IGA in contact analysis.In conclusion,IGA emerges as a potent tool for addressing contact analysis challenges and holds significant promise for 3D gear modeling,simulation,and optimization of various mechanical components.

基于改进SSD的钢材表面缺陷检测

工业生产过程中,钢材表面缺陷的检测对于钢材的质量控制发挥着十分重要的作用,针对钢材表面缺陷检测中存在的检测精度低、检测速度慢等问题,提出了一种钢材表面缺陷检测的改进SSD算法。在所提算法中,采用Transformer多头注意力机制模块代替原SSD结构中的Conv5_1层,以提高小目标检测的能力;原SSD结构中的Conv7操作替换为Involution算子操作,以减少运算的参数量;对网络结构进行特征融合处理,以更全面地检测特征图中所包含的信息。利用NEU-DET数据集进行实验,实验结果表明改进后的SSD算法是有效的,可以高效检测到钢材表面的小目标缺陷,相比改进前平均检测精度提高了4.5%,检测速度提高了13.6%。

雷峰塔下的张爱玲:《雷峰塔》、《易经》,与“回旋”和“衍生”的美学

本文通过张爱玲英文小说《雷峰塔》和《易经》及其它文本的比较阅读，提出以下观察：一、相对于写实／现实主义作为中国现代文学的主流形式，张爱玲穿越修辞、文类以及语言的界限，以重复书写发展出一种“衍生”（derivation）、“回旋”（involution）的美学。二、透过对自身故事的多重叙述，张爱玲颠覆传统家族历史的大叙事。通过书写，她化记忆为技艺，也重塑过往吉光片羽的存在与形式。三、张爱玲创作中回旋、衍生的倾向也带出了一种独特的（文学）史观。张的史观表明她后四十年的创作其实不只限于她以各种形式重写的自传故事，也同时包括另外两项计划：一是将吴语的《海上花列传》翻译为国语，再翻译成英文；另外则是通过细读文本、文献考证以及传记研究的方式参详《红楼梦》。

一种基于Involution卷积的三维人体重建方法

针对从视频中恢复三维人体模型运动序列时,由于图像特征提取能力有限而导致三维人体模型运动序列重建效果不佳的问题,提出了一种基于Involution卷积的三维人体重建方法。首先为了引入自注意力机制,在ResNet50网络结构中加入Involution算子,获取视频图像帧的特征向量,然后使用姿态估计网络和形状估计网络获取人体姿势以及形状参数,最后使用蒙皮多人线性模型(skinned multi-person linear model, SMPL)生成三维人体模型的运动序列。在三维姿态户外数据集(3D pose in the wild, 3DPW)上与视频人体姿态形状估计推理(video inference for body pose and shape estimation, VIBE)方法以及时间一致性网格恢复(temporally consistent mesh recovery, TCMR)方法进行对比实验,平均精度相比于VIBE、TCMR分别提升了3.1%、0.7%,能够为运动捕捉、三维人体动画制作等工作提供更为准确的三维人体模型。

基于弱监督数据集的猪只图像实例分割

在智慧养殖研究中,基于深度学习的猪只图像实例分割方法,是猪只个体识别、体重估测、行为识别等下游任务的关键。为解决模型训练需要大量的逐像素标注图像,以及大量的人力和时间成本的问题,采用弱监督猪只分割策略,制作弱监督数据集,提出一种新的特征提取骨干网络RdsiNet:首先在ResNet-50残差模块基础上引入第2代可变形卷积,扩大网络感受野;其次,使用空间注意力机制,强化网络对重要特征的权重值;最后引入involution算子,借助其空间特异性和通道共享性,实现加强深层空间信息、将特征映射同语义信息连接的功能。通过消融实验和对比实验证明了RdsiNet对于弱监督数据集的有效性,实验结果表明其在Mask R-CNN模型下分割的mAP_(Semg)达到88.6%,高于ResNet-50、GCNet等一系列骨干网络;在BoxInst模型下mAP_(Semg)达到95.2%,同样高于ResNet-50骨干网络的76.7%。而在分割图像对比中,使用RdsiNet骨干网络的分割模型同样具有更好的分割效果:在图像中猪只堆叠情况下,能更好地分辨猪只个体;使用BoxInst训练的模型,测试图像中掩码具有更高的精细度,这更有利于开展下游分析。

Renovation and Involution — Paradox of Chinese Literature in Modernity

With a special matter, Chinese literature has differences with traditional theories from western countries in essence, so that Chinese literature demonstrates its renovation and involution. The main reason is its trends of modernity. The transformation from oversea exchange is very important. This paper mainly explains the specific content of paradox of Chinese literature in mo dernity, and explores the reasons for differences between China and western countries.

基于小波变换和Involution卷积神经网络的滚动轴承故障诊断方法

传统卷积神经网络在滚动轴承故障诊断中存在梯度扩散、参数爆炸和训练时间长等缺点,为此提出一种基于Involution卷积神经网络的滚动轴承故障诊断方法。首先,通过小波变换将原始数据转换为时频图,经过数据预处理后送入基于Involution的神经网络模型;然后,经过不同Convolution卷积核对原始图像的局部区域特征进行不同方式的提取,扩展输入图像通道数;最后,通过Involution对特征图的每个像素点进行进一步特征提取,经过softmax层输出分类结果。CWRU轴承数据集和试验轴承数据集的分析结果表明,基于Involution卷积的神经网络模型所包含的参数较少,训练时间短,故障分类准确率可达99.75%,优于传统的CNN,DBN,自编码器等模型。

轻量化篮球裁判手势识别算法

针对一般手势识别算法的参数量、计算量和精度难以平衡的问题,提出一种轻量化篮球裁判手势识别算法。该算法在YOLOV5s(You Only Look Once Version 5s)算法的基础上进行重构:首先,用Involution算子替代CSP1_1的卷积算子,以扩大上下文信息捕获范围并减少核冗余;其次,在C3模块后加入协同注意力(CA)机制,以得到更强的手势特征提取能力;然后,用轻量化内容感知上采样算子改进原始上采样模块,并将采样点集中在目标区域而忽略背景部分;最后,利用以SiLU作为激活函数的Ghost-Net进行轻量化剪枝。在自制的篮球裁判手势数据集上的实验结果表明,该轻量化篮球裁判手势识别算法的计算量、参数量和模型大小分别为3.3 GFLOPs、4.0×10^(6)和8.5 MB,与YOLOV5s算法相比,分别减少了79%、44%和40%,mAP@0.5为91.7%,在分辨率为1920×1280的比赛视频上的检测帧率达到89.3 frame/s,证明该算法能满足低误差、高帧率和轻量化的要求。

基于改进YOLOv5算法的火灾图像检测研究

针对传统的火灾检测系统检测时间长、容易误报等问题,提出了一种基于改进YOLOv5的火灾检测算法.首先,针对卷积操作受到感受野的限制,增加Involution算子来扩大感受野;其次,在模型中引入CA(coordinate attention)注意力机制,重新分配特征图高度和宽度上的权重;最后,使用定位损失函数α-CIoU替换CIoU,以提高模型回归精度.改进的YOLOv5算法的平均精度达到了68.4%,相较于标准算法的平均精度提高了3.9%,定位框更加准确,且检测速度提高了14%.实验结果表明改进后的算法模型明显提高了火灾检测的准确性和实时性.

改进人脸特征矫正网络的遮挡人脸识别方法

现有人脸识别模型受口罩等遮挡因素影响导致准确率无法提升。当前主流研究方法将有无遮挡场景分开训练后,整合应用于多场景。针对遮挡人脸识别模型的局限性,提出一种改进人脸特征矫正网络(FFR-Net)模型。该模型可同时用于有无遮挡人脸识别并应用于口罩与眼镜遮挡两种识别场景中。人脸特征矫正网络模型提出了一种人脸特征矫正模块,为保证充分利用无遮挡区域特征信息,在该模块中的空间分支引入involution算子扩大图像信息交互区域,增强在空间范围内面部特征信息;在通道分支引入坐标注意力机制,捕获跨通道信息以增强特征表示,利于模型准确地定位识别目标区域;将Meta-ACON作为该模块新的动态激活函数,通过动态调整线性或非线性程度以提高模型泛化能力和计算准确度。最后,利用改进的人脸特征矫正网络模型在CASIA-Webface经处理的有无口罩遮挡人脸数据集上进行训练,其在LFW经处理的有无口罩遮挡数据集、Meglass数据集上的测试结果准确率分别达到了82.50%和89.75%,优于现有算法,验证了所提方法的有效性。

The Involutive Solutions of the Representation Equation Associated with the Bargmann System

In this paper, by a nonlinear procedure of a eigenvalue problem, we get a Bargmann system and prove it is a completely in tegrable system in the meanning of Liouville. By the way, the involutive solutio n of the representation equation is given.

Metal Flowing of Involute Spline Cold Roll-beating Forming

The present research on involute spline cold roll-beating forming is mainly about the principles and motion relations of cold roll-beating,the theory of roller design,and the stress and strain field analysis of cold roll-beating,etc.However,the research on law of metal flow in the forming process of involute spline cold roll-beating is rare.According to the principle of involute spline cold roll-beating,the contact model between the rollers and the spline shaft blank in the process of cold roll-beating forming is established,and the theoretical analysis of metal flow in the cold roll-beating deforming region is proceeded.A finite element model of the spline cold roll-beating process is established,the formation mechanism of the involute spline tooth profile in cold roll-beating forming process is studied,and the node flow tracks of the deformation area are analyzed.The experimental research on the metal flow of cold roll-beating spline is conducted,and the metallographic structure variation,grain characteristics and metal flow line of the different tooth profile area are analyzed.The experimental results show that the particle flow directions of the deformable bodies in cold roll-beating deformation area are determined by the minimum moving resistance.There are five types of metal flow rules of the deforming region in the process of cold roll-beating forming.The characteristics of involute spline cold roll-beating forming are given,and the forming mechanism of involute spline cold roll-beating is revealed.This paper researches the law of metal flow in the forming process of involute spline cold roll-beating,which provides theoretical supports for solving the tooth profile forming quality problem.

EFFECT OF INVOLUTE CONTACT RATIO ON THE DYNAMIC PERFORMANCE OF SPUR GEAR WITH NOTOOTH PROFILE MODIFICATION

The effect of involute contact ratio on the torsional vibration behavior ofspur gear-pair is studied analytically through a mass-spring model. The tooth stiffness in model notonly has a relation with time, as many prior studies presented, but, more important, with involutecontact ratio (ICR) as well. The ICR embodies its impact on the spur gear's dynamic performancethrough changing the proportion of tooth stiffness when there are n+1 teeth in contact to toothstiffness when there are n teeth in contact. A couple of curves about impact of ICR on the gear'sdynamic performance are presented, and they clearly demonstrate that the model can accuratelydescribe the effects of ICR on dynamic transmission error. Finally, some conclusions useful toreduce vibration and noise of gear-pair are proposed.

双线性内卷神经网络用于眼底疾病图像分类

由于眼底图像具有复杂程度高、个体差异弱、类间距离短等特点,纯卷积神经网络(CNN)和基于注意力的网络并不能在眼底疾病图像分类任务上达到令人满意的精度。因此,采用involution算子实现了注意力双线性内卷神经网络(ABINN)模型用于眼底疾病图像分类。ABINN模型的参数量仅是传统双线性卷积神经网络(BCNN)模型的11%,并提取了眼底图像的底层语义信息和空间结构信息进行二阶特征融合,是CNN和注意力方法的有效并联。此外,提出了两种基于involution算子实现注意力计算的实例化方法:基于图块的注意力子网络(AST)和基于像素的注意力子网络(ASX),这两种方法可以在CNN的基础结构内完成注意力的计算,从而使双线性子网络能在同一个架构下训练并进行特征融合。在公开眼底图像数据集OIA-ODIR上进行实验,结果显示ABINN模型的精度为85%,比通用BCNN模型提高了15.8个百分点,比TransEye模型提高了0.9个百分点。