Mechanical properties and deformation features of AZ31-0.84%Sb alloy

The mechanical properties and deformation features of AZ31-0.84% Sb alloy have been studied by means of the measurement of the properties and morphology observation. Results show that UTS of AZ31-0.84% Sb alloy at room temperature is 297MPa, a higher value of UTS is still maintained up to 189MPa as temperature elevated to 200℃. One of the main reasons for enhancing UTS of the alloy is attributed to the high volume fraction of the precipitates dispersed in the matrix, including Mg3Sb2 phase, which effectively hindered the movement of dislocations during the elevated temperature deformation. The deformation mechanisms of AZ31-0.84% Sb alloy are the twins and dislocations activated on basal and non-basal planes. a+c dislocations may be activated on the basal and non-basal planes in twins regions, and some of the thinner twins may shear through the dense dislocations within the thicker twins.

Multi-Layer Feature Extraction with Deformable Convolution for Fabric Defect Detection

In the textile industry,the presence of defects on the surface of fabric is an essential factor in determining fabric quality.Therefore,identifying fabric defects forms a crucial part of the fabric production process.Traditional fabric defect detection algorithms can only detect specific materials and specific fabric defect types;in addition,their detection efficiency is low,and their detection results are relatively poor.Deep learning-based methods have many advantages in the field of fabric defect detection,however,such methods are less effective in identifying multiscale fabric defects and defects with complex shapes.Therefore,we propose an effective algorithm,namely multilayer feature extraction combined with deformable convolution(MFDC),for fabric defect detection.In MFDC,multi-layer feature extraction is used to fuse the underlying location features with high-level classification features through a horizontally connected top-down architecture to improve the detection of multi-scale fabric defects.On this basis,a deformable convolution is added to solve the problem of the algorithm’s weak detection ability of irregularly shaped fabric defects.In this approach,Roi Align and Cascade-RCNN are integrated to enhance the adaptability of the algorithm in materials with complex patterned backgrounds.The experimental results show that the MFDC algorithm can achieve good detection results for both multi-scale fabric defects and defects with complex shapes,at the expense of a small increase in detection time.

Deformation-based freeform feature reconstruction in reverse engineering

For reconstructing a freeform feature from point cloud, a deformation-based method is proposed in this paper. The freeform feature consists of a secondary surface and a blending surface. The secondary surface plays a role in substituting a local region of a given primary surface. The blending surface acts as a bridge to smoothly connect the unchanged region of the primary surface with the secondary surface. The secondary surface is generated by surface deformation subjected to line constraints, i.e., character lines and limiting lines, not designed by conventional methods. The lines are used to represent the underlying informa-tion of the freeform feature in point cloud, where the character lines depict the feature’s shape, and the limiting lines determine its location and orientation. The configuration of the character lines and the extraction of the limiting lines are discussed in detail. The blending surface is designed by the traditional modeling method, whose intrinsic parameters are recovered from point cloud through a series of steps, namely, point cloud slicing, circle fitting and regression analysis. The proposed method is used not only to effectively and efficiently reconstruct the freeform feature, but also to modify it by manipulating the line constraints. Typical examples are given to verify our method.

Deformation features and tectonic transfer of the Gumubiezi Fault in the northwestern margin of Tarim Basin, NW China

Through field geologic survey,fine interpretation of seismic reflection data and analysis of well drilling data,the differential deformation,tectonic transfer and controlling factors of the differential deformation of the Gumubiezi Fault(GF)from east to west have been studied systematically.The study shows that GF started to move southward as a compressive decollement along the Miocene gypsum-bearing mudstone layer in the Jidike Formation at the Early Quaternary and thrust out of the ground surface at the northern margin of the Wensu Uplift,and the Gumubiezi anticline formed on the hanging wall of the GF.The displacement of the GF decreases gradually from 1.21 km in the east AA′transect to 0.39 km in the west CC′transect,and completely disappears in the west of the Gumubiezi anticline.One part of the displacement of the GF is converted into the forward thrust,and another part is absorbed by Gumubiezi anticline.The formation of the GF is related to the gypsum-bearing mudstone layer in the Jidike Formation and barrier of the Wensu Uplift.The differential deformation of the GF from east to west is controlled by the development difference of gypsum-bearing mudstone layer in the Jidike Formation.In the east part,gypsum-bearing mudstone layer in the Jidike Formation is thicker,the deformation of the duplex structure in the north of the profile transferred to the basin along gypsum-bearing mudstone layer;to the west of the Gumubiezi structural belt(GSB),the gypsum-bearing mudstone layer in Jidike Formation decreases in thickness,and the transfer quantity of deformation of the duplex structure along the gypsum-bearing mudstone layer to the basin gradually reduces.In contrast,on the west DD′profile,the gypsum-bearing mudstone is not developed,the deformation of the deep duplex structure cannot be transferred along the Jidike Formation into the basin,the deep thrust fault broke to the surface and the GF disappeared completely.The displacement of the GF to the west eventually disappeared,because the lateral ramp acts as the transitional fault between east and west part of GSB.

Reinforcement learning method for machining deformation control based on meta-invariant feature space

Precise control of machining deformation is crucial for improving the manufacturing quality of structural aerospace components.In the machining process,different batches of blanks have different residual stress distributions,which pose a significant challenge to machining deformation control.In this study,a reinforcement learning method for machining deformation control based on a meta-invariant feature space was developed.The proposed method uses a reinforcement-learning model to dynamically control the machining process by monitoring the deformation force.Moreover,combined with a meta-invariant feature space,the proposed method learns the internal relationship of the deformation control approaches under different stress distributions to achieve the machining deformation control of different batches of blanks.Finally,the experimental results show that the proposed method achieves better deformation control than the two existing benchmarking methods.

About the Features of Transient to Steady State Deformation of Solids

The features of transient to steady state deformation of solids are theoretically investigated.Modeling of various types of loading was carried out by the Movable Cellular Automata method.A stress state of material at the stage of transient to a steady state is shown to be essentially non-uniform, that may in its turn result in stable structures in velocity field of particles of the material. It may also influence development of deformation at the further stages.

Optical Flow with Learning Feature for Deformable Medical Image Registration

Deformable medical image registration plays a vital role in medical image applications,such as placing different temporal images at the same time point or different modality images into the same coordinate system.Various strategies have been developed to satisfy the increasing needs of deformable medical image registration.One popular registration method is estimating the displacement field by computing the optical flow between two images.The motion field(flow field)is computed based on either gray-value or handcrafted descriptors such as the scale-invariant feature transform(SIFT).These methods assume that illumination is constant between images.However,medical images may not always satisfy this assumption.In this study,we propose a metric learning-based motion estimation method called Siamese Flow for deformable medical image registration.We train metric learners using a Siamese network,which produces an image patch descriptor that guarantees a smaller feature distance in two similar anatomical structures and a larger feature distance in two dissimilar anatomical structures.In the proposed registration framework,the flow field is computed based on such features and is close to the real deformation field due to the excellent feature representation ability of the Siamese network.Experimental results demonstrate that the proposed method outperforms the Demons,SIFT Flow,Elastix,and VoxelMorph networks regarding registration accuracy and robustness,particularly with large deformations.

磁共振feature tracking初步评价终末期肾病患者心肌形变

目的采用心脏磁共振feature tracking(CMR-FT)技术初步分析终末期肾病患者左心室心肌形变各参数的变化情况。方法对10例正常志愿者和9例终末期肾病接受血液透析治疗的患者行1.5T心脏非对比增强、FIESTA序列电影成像,并采用feature tracking(FT)2D模型对左心室运动及整体心肌形变情况进行定量分析。结果终末期肾病患者左心室心肌质量[(132.70±44.44)g]大于正常志愿者[(80.00±11.29)g,P<0.05]。终末期肾病患者左心室心肌整体径向应变、环向应变、径向收缩期峰值运动速度、径向舒张期峰值运动速度均低于健康志愿者[(22.52±10.41)%vs(39.46±7.10)%,(-12.57±3.91)%vs(-19.80±2.11)%,(22.70±5.72)mm/s vs(34.77±3.81)mm/s,(-24.71±8.83)mm/s vs(-43.88±8.89)mm/s,P均<0.05)。而终末期肾病患者和正常志愿者的左心室射血分数、左心室舒张末期容积、左心室收缩末期容积差异无统计学意义(P均>0.05)。结论 CMR-FT技术能够定量评价终末期肾病患者左心室心肌运动及形变情况。

Deformation Localization-A Review on the Maximum-Effective-Moment(MEM) Criterion

The essential difference in the formation of conjugate shear zones in brittle and ductile deformation is that the intersection angle between brittle conjugate faults in the contractional quadrants is acute （usually ～60°） whereas the angle between conjugate ductile shear zones is obtuse （usually 110°）. The Mohr-Coulomb failure criterion, an experimentally validated empirical relationship, is commonly applied for interpreting the stress directions based on the orientation of the brittle shear fractures. However, the Mohr-Coulomb failure criterion fails to explain the formation of the low-angle normal fault, high-angle reverse fault, and the conjugate strike-slip fault with an obtuse angle in the ~1 direction. Although it is ten years since the Maximum-Effective-Moment （MEM） criterion was first proposed, and increasingly solid evidence in support of it has been obtained from both observed examples in nature and laboratory experiments, it is not yet a commonly accepted model to use to interpret these anti- Mohr-Coulomb features that are widely observed in the natural world. The deformational behavior of rock depends on its intrinsic mechanical properties and external factors such as applied stresses, strain rates, and temperature conditions related to crustal depths. The occurrence of conjugate shear features with obtuse angles of -110~ in the contractional direction on different scales and at different crustal levels are consistent with the prediction of the MEM criterion, therefore -110° is a reliable indicator for deformation localization that occurred at medium-low strain rates at any crustal levels. Since the strain-rate is variable through time in nature, brittle, ductile, and plastic features may appear within the same rock.

Research on extraction and reproduction of deformation camouflage spot based on generative adversarial network model

The method of describing deformation camouflage spots based on feature space has some shortcomings,such as inaccurate description and difficult reproduction.Depending on the strong fitting ability of the generative adversarial network model,the distribution of deformation camouflage spot pattern can be directly fitted,thus simplifying the process of spot extraction and reproduction.The requirements of background spot extraction are analyzed theoretically.The calculation formula of limiting the range of image spot pixels is given and two kinds of spot data sets,forestland and snowfield,are established.Spot feature is decomposed into shape,size and color features,and a GAN(Generative Adversarial Network)framework is established.The effects of different loss functions on network training results are analyzed in the experiment.In the meantime,when the input dimension of generator network is 128,the balance between sample diversity and quality can be achieved.The effects of sample generation are investigated in two aspects.Subjectively,the probability of the generated spots being distinguished in the background is counted,and the results are all less than 20% and mostly close to zero.Objectively,the features of the spot shape are calculated and the independent sample T-test is applied to verify that the features are from the same distribution,and all the P-Values are much higher than 0.05.Both subjective and objective methods prove that the spots generated by this method are similar to the background spots.The proposed method can directly generate the desired camouflage pattern spots,which provides a new technical method for the deformation camouflage pattern design and camouflage effect evaluation.

Room temperature tensile deformation behavior of a Ni-based superalloy with high W content

K416B Ni-based superalloy with high W content has good high temperature properties and low cost,which has a great development potential.To investigate the room temperature tensile property and the deformation feature of K416B superalloy,tensile testing at room temperature was carried out,and optical microscopy (OM),scanning electron microscopy (SEM) and transmission electron microscopy (TEM) were used to analyze the deformation and damage mechanisms.Results show that the main room temperature tensile deformation features of the K416B nickel-based superalloy are dislocations slipping in the matrix and shearing into γ’ phase.The <110> super-dislocations shearing into γ’ phase can form the anti-phase boundary two coupled (a/2)<110> partial-dislocations or decompose into the configuration of two (a/3)<112> partial dislocations plus stacking fault.In the later stage of tensile testing,the slip-lines with different orientations are activated in the grain,causing the stress concentration in the regions of block carbide or the porosity,and cracks initiate and propagate along these regions.

Active Shape Models Using Scale Invariant Feature Transform

A new active shape models (ASMs) was presented, which is driven by scale invariant feature transform (SIFT) local descriptor instead of normalizing first order derivative profiles in the original formulation, to segment lung fields from chest radiographs. The modified SIFT local descriptor, more distinctive than the general intensity and gradient features, is used to characterize the image features in the vicinity of each pixel at each resolution level during the segmentation optimization procedure. Experimental results show that the proposed method is more robust and accurate than the original ASMs in terms of an average overlap percentage and average contour distance in segmenting the lung fields from an available public database.

RealFuVSR:Feature enhanced real-world video super-resolution

Background Recurrent recovery is a common method for video super-resolution(VSR)that models the correlation between frames via hidden states.However,the application of this structure in real-world scenarios can lead to unsatisfactory artifacts.We found that in real-world VSR training,the use of unknown and complex degradation can better simulate the degradation process in the real world.Methods Based on this,we propose the RealFuVSR model,which simulates real-world degradation and mitigates artifacts caused by the VSR.Specifically,we propose a multiscale feature extraction module(MSF)module that extracts and fuses features from multiple scales,thereby facilitating the elimination of hidden state artifacts.To improve the accuracy of the hidden state alignment information,RealFuVSR uses an advanced optical flow-guided deformable convolution.Moreover,a cascaded residual upsampling module was used to eliminate noise caused by the upsampling process.Results The experiment demonstrates that RealFuVSR model can not only recover high-quality videos but also outperforms the state-of-the-art RealBasicVSR and RealESRGAN models.

基于改进Deformable DETR的无人机视频流车辆目标检测算法

针对无人机视频流检测中小目标数量多、因图像传输质量较低而导致的上下文语义信息不充分、传统算法融合特征推理速度慢、数据集类别样本不均衡导致的训练效果差等问题,提出一种基于改进Deformable DETR的无人机视频流车辆目标检测算法。在模型结构方面,该算法设计了跨尺度特征融合模块以增大感受野,提升小目标检测能力,并采用针对object_query的挤压-激励模块提升关键目标的响应值,减少重要目标的漏检与错检率;在数据处理方面,使用了在线困难样本挖掘技术,改善数据集中类别样本分布不均的问题。在UAVDT数据集上进行了实验,实验结果表明,改进后的算法相较于基线算法在平均检测精度上提升了1.5%,在小目标检测精度上提升了0.8%,并在保持参数量较少增长的情况下,维持了原有的检测速度。

Feature deformation network with multi-range feature enhancement for agricultural machinery operation mode identification

Utilizing the spatiotemporal features contained in extensive trajectory data for identifying operation modes of agricultural machinery is an important basis task for subsequent agricultural machinery trajectory research.In the present study,to effectively identify agricultural machinery operation mode,a feature deformation network with multi-range feature enhancement was proposed.First,a multi-range feature enhancement module was developed to fully explore the feature distribution of agricultural machinery trajectory data.Second,to further enrich the representation of trajectories,a feature deformation module was proposed that can map trajectory points to high-dimensional space to form feature maps.Then,EfficientNet-B0 was used to extract features of different scales and depths from the feature map,select features highly relevant to the results,and finally accurately predict the mode of each trajectory point.To validate the effectiveness of the proposed method,experiments were conducted to compare the results with those of other methods on a dataset of real agricultural trajectories.On the corn and wheat harvester trajectory datasets,the model achieved accuracies of 96.88%and 96.68%,as well as F1 scores of 93.54%and 94.19%,exhibiting improvements of 8.35%and 9.08%in accuracy and 20.99%and 20.04%in F1 score compared with the current state-of-the-art method.

一种针对SAR图像的舰船目标检测算法

由于环境复杂、舰船目标散焦和尺度的多样性,基于SAR图像的舰船目标检测仍然存在一些问题。提出了一种针对SAR图像的舰船目标检测算法。首先,基于可变形卷积构建舰船目标特征细化模块,提高对大长宽比姿态的舰船目标的特征提取能力;其次,在主干网络末尾引入了舰船空间金字塔聚合结构,增强对舰船目标的全局特征提取能力;最后,设计了尺度扩展特征金字塔网络,增强舰船浅层和深层特征信息的交互,提高对多尺度舰船目标的检测能力。实验结果表明,所提算法在HRSID数据集上的mAP达到了93.72%,F1分数达到了89.70%,优于所有比较算法,具有良好的检测效果。

Using multi-matching system based on a simplified deformable model of the human iris for iris recognition

A new method for iris recognition using a multi-matching system based on a simplified deformable model of the human iris was proposed. The method defined iris feature points and formed the feature space based on a wavelet transform. In the matching stage it worked in a crude manner. Driven by a simplified deformable iris model, the crude matching was refined. By means of such multi-matching system, the task of iris recognition was accomplished. This process can preserve the elastic deformation between an input iris image and a template and improve precision for iris recognition. The experimental results indicate the va- lidity of this method.

DB-DCAFN:dual-branch deformable cross-attention fusion network for bacterial segmentation

Sputum smear tests are critical for the diagnosis of respiratory diseases. Automatic segmentation of bacteria from spu-tum smear images is important for improving diagnostic efficiency. However, this remains a challenging task owing to the high interclass similarity among different categories of bacteria and the low contrast of the bacterial edges. To explore more levels of global pattern features to promote the distinguishing ability of bacterial categories and main-tain sufficient local fine-grained features to ensure accurate localization of ambiguous bacteria simultaneously, we propose a novel dual-branch deformable cross-attention fusion network (DB-DCAFN) for accurate bacterial segmen-tation. Specifically, we first designed a dual-branch encoder consisting of multiple convolution and transformer blocks in parallel to simultaneously extract multilevel local and global features. We then designed a sparse and deformable cross-attention module to capture the semantic dependencies between local and global features, which can bridge the semantic gap and fuse features effectively. Furthermore, we designed a feature assignment fusion module to enhance meaningful features using an adaptive feature weighting strategy to obtain more accurate segmentation. We conducted extensive experiments to evaluate the effectiveness of DB-DCAFN on a clinical dataset comprising three bacterial categories: Acinetobacter baumannii, Klebsiella pneumoniae, and Pseudomonas aeruginosa. The experi-mental results demonstrate that the proposed DB-DCAFN outperforms other state-of-the-art methods and is effective at segmenting bacteria from sputum smear images.

细化多尺度感知与优化轮廓的自适应道路场景语义分割网络

语义分割通常被描述为像素级的分类任务,而集成卷积神经网络与Transformer的MaskFormer网络则将其描述为掩模级的分类任务.为了解决语义分割形变建模能力差、物体轮廓分割模糊和收敛速度慢的问题,提出一种细化多尺度感知与优化轮廓的自适应道路场景语义分割网络.在编码器中,采用标准卷积与可变形卷积堆叠形成的瓶颈结构提高网络的形变建模能力;在解码器中,采用特征细化模块过滤无关特征,进一步提高特征金字塔网络的解码能力;针对特征金字塔网络进行多层级特征融合时上采样特征出现像素点错位的问题,引入特征校准模块优化物体轮廓的分割效果;最后在Transformer模块中采用Miti-DETR解码器加快网络的训练速度,提升分割精度.实验结果表明,所提网络在Cityscapes和Mapillary Vistas数据集上以较大的优势超过了现有的语义分割网络.

关家崖煤矿重复采动巷道变形特征及控制对策研究

针对重复采动巷道围岩变形严重、无法复用,重复采动巷道在服务期内具有明显的叠加演化特征的问题,以关家崖煤矿13092巷道为研究背景,采用现场实测、数值模拟和理论分析的方法,对重复采动巷道变形的叠加扩展特征和控制对策进行了研究。重复采动巷道变形特征分析结果表明:①一次回采扰动下,重复采动巷道变形呈现分区和非对称破坏特征,可划分为快速变形区、强烈变形区和缓慢变形区;裂纹破坏主要在煤壁帮和煤柱帮,而顶底板较少,表现为巷道两帮显著片帮和内移;煤壁帮与顶板、煤柱帮与底板交汇处变形严重。②二次采动巷道在一次破坏基础上叠加扩展,使得非对称破坏更加显著,形成巷道围岩蝶形叠加塑性破坏区。③重复采动巷道围岩控制的重点时间为一次回采阶段,重点区域为强烈变形区和缓慢变形区的巷道煤柱帮一侧。通过分析采动巷道蝶形变形特征和破坏分区规律,提出了重复采动巷道多层次耦合控制技术,采用浅低压−深高压注浆提高煤柱支撑力,采用锚索补强提高支护体支撑力,实现耦合控制。通过加固前后变形量对比分析验证了多层次耦合控制满足巷道复用要求。