Weak Texture Research Articles

Comparison of electron-beam-welded joints manufactured by rolled and selective laser melted reduced activation ferritic/martensitic steel

As the core component of China Fusion Engineering Test Reactor (CFETR), the forming and manufacturing of the first wall faces severe challenges due to the constraints of materials, service environment and geometric structure. The microstructure and mechanical properties of welded joints obtained by rolled and laser selective melted (SLMed) reduced activation ferritic/martensitic (RAFM) steel were investigated in depth. The microstructure analysis results showed that the weld metal (WM) was composed of coarse lath martensite and δ-ferrite, while the microstructure were mainly coarse grains in heat affected zone (HAZ) which was easy to break. The average grains size of SLMed RAFM steel (S-RAFMs) was smaller than that of rolled RAFM steel (R-RAFMs), since the rapid melting and solidification of laser in the additive manufacturing process prevented grains to grow. The microstructure of R-RAFMs joint was relatively more uniform and there was no obvious texture and preferred orientation, while the WM of S-RAFMs joint had a weak cubic texture. The results of mechanical properties showed that the S-RAFMs joints exhibited higher strength (UTS = 697.46 MPa) and the R-RAFMs joints exhibited better plasticity (EL = 13.49 %) under the same tensile conditions. The tensile and impact fracture morphologies showed that the fracture mechanism of two joints was ductile-brittle mixed fracture, and the dimples of R-RAFMs joints were finer and denser. It was clearly observed that the hardness of WM (∼390–430 HV0.3) was higher than that of the base metal (BM) (∼190–230 HV0.3) from the hardness distributions along the width directions. The average hardness of BM in R-RAFMs joint (227 HV0.3) was lower than S-RAFMs joint (197.3 HV0.3), which was mainly related to the fine grain strengthening effect during SLM forming. The above results may provide theoretical guidance for the high-performance manufacturing of the first wall and promote the application of SLM and EBW technology in the field of nuclear fusion.

Discontinuous dynamic recrystallization behavior and texture evolution of large-size pure titanium flat ingot via electron beam cold hearth melting during short process direct hot rolling

Large-size pure titanium ingots melted by single electron beam cold hearth melting (EBCHM)) could be rolled into large-width and heavy-weight titanium strip coils using short process without forging. It is crucial to study the large-span refinement mechanism from highly coarse grains, whose sizes are in the order of ∼cm, to micronmeter. In this study, the recrystallization mechanism and texture evolution of pure titanium with a size of 1570 × 200 × > 8000 mm was investigated by multi-pass simulated rolling and experimental rolling. The results indicated the hot deformation can result in marked reduction in grain size of the as-cast grain, from 3 to 5 cm to 17–23 μm. The discontinuous dynamic recrystallization (DDRX) mechanism of a pure titanium ingot during direct multi-pass hot deformation causes the reconstruction of as-cast microstructure and refinement of hot rolling microstructure. Furthermore, DDRX occurred, during hot deformation, and was accompanied with weakening of deformation texture. Raising the initial hot deformation temperature results in a modification of the texture type of the {0001} crystal plane. The strength of the texture experiences a decrease initially and then eventually an increase. This alteration in strength is inversely related to the degree of dynamic recrystallization. Based on the simulated rolling experiment, the results of experimental rolling also found the coarse as-cast grains was broken and reconstructed. It has strength (average yield strength: 334 MPa, ultimate tensile strength: 371 MPa), ductility (total elongation: 30 %). Such a combination of mechanical properties makes the hot rolling plate a potential choice for sheet practical application.

Dynamic Shear Texture Evolution during the Symmetric and Differential Speed Rolling of Al-Si-Mg Alloys Fabricated by Twin Roll Casting.

The effects of a reduction in area (RA) and the speed ratio between the top and bottom rolls on a shear strain and the crystallographic texture evolution of Al-Si-Mg (1.0%Si-0.6%Mg) aluminum alloys fabricated by twin roll casting (TRC) were comprehensively examined experimentally and through numerical predictions. Initial twin-roll casted strips had a texture gradient from the surface to the center. ⟨111⟩//ND textures were found in the surface layer, and weak rolling textures existed in the center of the strip. The distributions of shear and plane strain compression (PSC) textures varied with the RA and differential speed ratio. Strong shear textures including a rotated cube, {100}⟨011⟩, were obtained from both the symmetric and differential speed rolling processes. Symmetric rolling with a different reduction in area (SRDRA) produced shear textures mainly in the surface layer. Differential speed rolling (DSR) caused dynamic shear textures along the thickness direction, not limited to the surface. Based on the finite element method and crystal plasticity, the effects of different RA values, differential speed ratios, and friction coefficients on shear strain and texture evolution are discussed in detail. Loads measured from work rolls during DSR decreased with an increase in the speed ratio.

Improving the tension-compression asymmetry of ZK61 magnesium alloy through texture optimization in combined extrusion

In order to improve the tension-compression asymmetry that exists widely in extruded magnesium alloys, ZK61 magnesium alloys with different texture characteristics were prepared by conventional extrusion, compression-extrusion, and cyclic extrusion compression. The effect of texture on the tension-compression asymmetry and associated deformation mechanisms of magnesium alloys was revealed based on the Sachs assumption. Subsequently, a texture-modified Hall-Petch relationship was used to quantify the combined effect of texture and grain on both tensile and compressive yield strengths. It is found that the slight weakening of the {0002}∥LD fiber texture was beneficial to the suppression of {10‐12} twinning and the activation of prismatic slip, which in turn significantly improved the tension-compression asymmetry without the obvious sacrifice of strength. However, excessive texture inclining can cause a striking decrease in strengths and even reverse tension-compression asymmetry due to the activation of basal slip and pyramidal slip. In conclusion, slight basal texture weakening was a texture optimization strategy to obtain tension-compression symmetry and high strength for wrought magnesium alloys.

Stereo matching algorithm based on improved census transform and minimum spanning tree cost aggregation

Existing stereo matching algorithms suffer from issues such as susceptibility to distortion, weak noise resistance, and a high rate of mismatches in regions with weak textures and discontinuous disparities. To address these challenges, this paper proposes a stereo matching algorithm based on an improved census transform and minimum spanning tree (MST) cost aggregation. In the cost calculation phase, we employ a Gaussian-weighted transformation window and incorporate gradient and edge information to perform weighted fusion of the results. In the cost aggregation process, we introduce a collaborative adaptive window. Each pixel acquires information from the support window of the guided filter (GF) and other pixels within the MST. Furthermore, we integrate the SLIC superpixel segmentation algorithm into MST construction. These two components work synergistically to assign appropriate adaptive weights to pixels, facilitating coordinated cost volume aggregation. Different optimization methods are applied to address mismatched points of various types in post-disparity processing.Performance evaluation using the Middlebury dataset and KITTI dataset demonstrates that our proposed algorithm not only enhances matching accuracy in regions with discontinuous disparities and weak textures but also exhibits significantly improved robustness to interference. Additionally, the resulting disparity map displays smoother edges.

Effect of laser scan rotation on the microstructure and mechanical properties of laser powder bed fused Haynes 282

Haynes 282 is a weldable, γ′ strengthened Ni-based superalloy and is a suitable candidate for aerospace and power-generation applications. Laser powder bed fusion (LPBF) of Haynes 282 is gaining attention recently due to its superior mechanical properties than its conventional counterparts. In spite of the superior mechanical properties, there are significant challenges concerning crystallographic anisotropy. One of the critical but less studied parameters that influence crystallographic anisotropy is the laser scan rotation angle. This study investigates the effect of laser scan rotation angle on the microstructure and subsequently on the mechanical properties. The samples fabricated with 90° scan rotation exhibited stronger texture while the samples with 137° rotation had weaker texture than samples with 67°. Further, three-dimensional Finite difference-Monte Carlo simulations were performed to understand the microstructure evolution with varying process parameters. The experimental and simulated microstructures are quantitatively compared using 2-point correlations. The texture and grain morphology evolution are explained based on melt pool morphology and microstructure simulations. Mechanical properties of as-built and aged samples are estimated using theoretical models and agree well with the experimental results.

Evolution of microstructure and texture in Al-containing CoCrNi medium entropy alloys during severe warm-rolling

Al, as an alloying element, can influence the properties of the single-phase equiatomic CoCrNi MEA. In this study, different alloys of different Al concentrations added to CoCrNi MEA (AlxCoCrNi) were prepared by warm rolling to understand the effect of Al. The alloys were warm-rolled at 400 °C up to an 85% thickness reduction, followed by isochronal annealing at 700–1100 °C. The microstructure after deformation reveals the development of deformation heterogeneities such as shear bands and deformation nano-twins. The evolution of the weak brass component is seen after deformation. Different phases, such as BCC and sigma, evolve upon annealing treatment at different temperatures. The higher Al-content MEA (Al9.09) shows comparatively finer recrystallized microstructure irrespective of the annealing temperatures. Also, weak recrystallization texture develops after annealing, and the deformation texture components lying on α-fiber are preserved. This indicates the absence of preferential nucleation and growth during annealing. The hardness in the as-cast, deformed, and annealed conditions increases with increasing Al content, indicating the influence of Al in the strengthening of the AlxCoCrNi MEAs.

The synergistic and interactive effects of slip systems and dynamic recrystallization on the weakening basal texture of Mg-Y-Nd-Zr-Gd magnesium alloy

Magnesium (Mg) alloys are known to exhibit strong basal texture following large plastic deformation. However, recent experimental studies have revealed that the Mg-Y-Nd-Zr-Gd series alloy displays a weak texture after undergoing 60% compression at 500 °C. The overall deformation texture is similar to that of dynamic recrystallization (DRX) subsets, and the (0001) pole figure of the deformed grain subsets does not concentrate entirely in the compression direction due to the activation of non-basal slip systems. It should be noted that DRX and non-basal slip systems cannot independently account for the final deformation texture. In this case, continuous dynamic recrystallization (CDRX) occurs, where the segregation of rare earth (RE) elements at grain boundaries (GB) impedes the movement of existing GBs and prevents the occurrence of discontinuous dynamic recrystallization (DDRX). Low-angle grain boundaries (LAGB), which are subject to local strain-regulated distribution, continue to absorb dislocations and produce new CDRXed grains. Notably, non-basal slip systems play a role in the generation and subsequent orientation behavior of DRXed grains. As DRX progresses, complex crystal rotations occur on both sides of the newly formed DRX interfaces, causing the orientation of the DRXed grains to gradually deviate from that of the deformed parent grains.

Significant Texture Weakening of AZ91 Alloy by Asymmetric Hot Rolling

Significant Texture Weakening of AZ91 Alloy by Asymmetric Hot Rolling

Shear texture development and microstructural analysis of friction stir welded AA5754 sheets during forming at different strain paths

Modern automotive, marine, and aviation industries seek defect-free Al-Mg alloy welds for uniform strain distribution during complex shaping. Despite this critical need, limited research was done on the formability of friction stir welded blanks. This study aimed to examine the shear texture development and microstructural analysis of friction stir welded AA5754 sheets during forming at different strain paths. It is also sought to correlate the changes ensued before and after deformation with microstructures and formability. Four combinations of rotational speeds (1200 and 1600 rpm) and traverse speeds (90 and 150 mm/min) were used to produce 1.5 mm thick butt-welded AA5754 sheets. Limit Dome Height (LDH) experiments were performed for three different strain paths (uniaxial, plane, and biaxial) to assess the formability in terms of strain path diagram. Strain path curves and von Mises effective strains revealed that plane strain limits were lowest for most parameter combinations, except 1200 rpm - 150 mm/min and a peculiar behavior was observed in the minor strains of biaxial strain paths. The reason for this peculiar behavior was further confirmed by weak or absent texture C in biaxial strain paths and declining pole figure intensities at 1200 rpm - 150 mm/min across the strain paths during shear texture analysis. Grain orientation spread (GOS) maps differentiated deformed and recrystallized regions. The minimum average Taylor factor (M) in the biaxial strain path of deformed base material indicated maximum slip system activation. Moreover, for all the specimens the average M ranged between 3 and 4, which signified that the grains exhibited adequate amount of stress levels and high level of work hardening.

Effect of temperature on superplastic deformation behavior of 2198 Al–Cu–Li alloy

Al–Li alloy possesses remarkable advantages such as low density, high specific strength and specific elastic modulus, making it an exceptional aerospace structural material with considerable application potential. However, Al–Li alloy suffers from poor formability, which restricts its broader engineering applications. Alternatively, superplastic forming at high temperatures is widely applied for producing such components. Temperature is a key factor affecting the thermal deformation properties of Al–Li alloy. In this study, tensile tests of 2198 Al–Cu–Li alloy were conducted at different temperatures, and dedicated characterizations were performed to reveal the underlying mechanisms responsible for the hot deformation behavior. Results reveal that three distinct stages are observed in the superplastic deformation process of this alloy. Specifically, in the initial low-temperature range (400 °C–450 °C), incomplete dynamic recrystallization (DRX), accompanied by grain rotation and elongation plays a dominant role in the hot deformation mechanism. In the middle temperature stage (450 °C–500 °C), both DRX and grain boundary sliding (GBS) occur. At the high-temperature stage (500 °C–550 °C), diffusion creep emerges as the prominent mechanism. Moreover, optimum superplasticity is achieved at 500 °C, which results from a synergistic combination of several factors, including grain refinement by DRX, an increased fraction of high-angle grain boundaries (HAGBs), reduced dislocation density and weak texture.

A novel continues multi-shear extrusion process on the microstructure and mechanical property evolution of AZ31 magnesium alloys

This study presents a novel technology in the fabrication of AZ31 Mg alloy sheets using continuous shear extrusion (CSE) with multiple shear platforms at 340 °C. Compared with the conventional extrusion (CE), an asymmetric shear deformation was introduced so that the basal texture deflects towards to extrusion direction. Through finite element simulation, it was found that the differences in flow velocity and strain distributions along the thickness direction can be achieved by introducing the shear strain through CSE technology. Finer grains and more uniform microstructure were obtained in CSEed Mg samples compared to conventional extrusion. The average grain size decreased from 6.33 μm in CE samples to 3.94 μm in CSE samples, and 3.39 μm in CSE-II samples. The continuous asymmetric shear force also led to the basal plane inclining approximately 15° towards the extrusion direction, leading to a weakening of basal texture intensity. In terms of mechanical properties, the CSE Mg plates exhibited higher yield strength (YS), ultimate tensile strength (UTS), and fracture elongation (FE) along the extrusion direction. These improvements in mechanical performance can be attributed to enhanced work hardening ability, texture weakening, finer grains generation, and the dislocation strengthening induced by shear strain.

Strain rate dependence of dynamic recrystallization and texture evolution in hot compressed Mg-Gd-Er-Zr alloy

Hot deformation with high strain rate has been paid more attention due to its high efficiency and low cost, however, the strain rate dependent dynamic recrystallization (DRX) and texture evolution in hot deformation process, which affect the formability of metals, are lack of study. In this work, the DRX behavior and texture evolution of Mg-8Gd-1Er-0.5Zr alloy hot compressed with strain rates of 0.1 s−1, 1 s−1, 10 s−1 and 50 s−1 are studied, and the corresponding dominant mechanisms for DRX and texture weakening are discussed. Results indicated the DRX fraction was 20 % and the whole texture intensity was 16.89 MRD when the strain rate was 0.1 s−1, but they were 76 % and 6.55 MRD, respectively, when the strain rate increased to 50 s−1. The increment of DRX fraction is suggested to result from the reduced DRX critical stress and the increased dislocation density as well as velocity, while the weakened whole texture is attributed to the increased DRX grains. At the low strain rate of 0.1 s−1, discontinuous DRX (DDRX) was the dominant, but the whole texture was controlled by the deformed grains with the preferred orientation of {0001}⊥CD, because the number of DDRX grains was limited. At the high strain rate of 50 s−1, continuous DRX (CDRX) and twin-induced DRX (TDRX) were promoted, and more DRX grains resulted in orientation randomization. The whole texture was mainly weakened by CDRX and TDRX grains, in which CDRX plays a major role. The results of present work are significant for understanding the hot workability of Mg-RE alloys with a high strain rate.

Multi-View Stereo Network Based on Attention Mechanism and Neural Volume Rendering

Due to the presence of regions with weak textures or non-Lambertian surfaces, feature matching in learning-based Multi-View Stereo (MVS) algorithms often leads to incorrect matches, resulting in the construction of the flawed cost volume and incomplete scene reconstruction. In response to this limitation, this paper introduces the MVS network based on attention mechanism and neural volume rendering. Firstly, we employ a multi-scale feature extraction module based on dilated convolution and attention mechanism. This module enables the network to accurately model inter-pixel dependencies, focusing on crucial information for robust feature matching. Secondly, to mitigate the impact of the flawed cost volume, we establish a neural volume rendering network based on multi-view semantic features and neural encoding volume. By introducing the rendering reference view loss, we infer 3D geometric scenes, enabling the network to learn scene geometry information beyond the cost volume representation. Additionally, we apply the depth consistency loss to maintain geometric consistency across networks. The experimental results indicate that on the DTU dataset, compared to the CasMVSNet method, the completeness of reconstructions improved by 23.1%, and the Overall increased by 7.3%. On the intermediate subset of the Tanks and Temples dataset, the average F-score for reconstructions is 58.00, which outperforms other networks, demonstrating superior reconstruction performance and strong generalization capability.

Stereo Matching Algorithm of Multi-Feature Fusion Based on Improved Census Transform

This article proposes an improved stereo matching algorithm in order to address the issue that the conventional Census transform is overly dependent on the center pixel of the window, which makes the algorithm susceptible to noise interference and results in low matching accuracy in regions with weak texture and complex texture. In the cost calculation stage, the noise threshold is set utilizing the absolute difference detection approach, and pixels that exceed the threshold are replaced with the mean gray values of the neighboring pixels in the 3 × 3 window. This stage also includes the introduction of the gradient cost, which is coupled with the edge and feature point information to provide the final matching cost. The cross approach is employed to build the adaptive support domain and aggregate the costs during the cost aggregation stage. The disparity is finally calculated using the WTA technique, and a multi-step refinement process is employed to produce the final disparity map. The experiments demonstrate that the proposed algorithm has good anti-noise performance. Compared with other improved algorithms or composite algorithms, the average matching rate of the four standard images on the Middlebury test platform is 5.53%, which is higher than the remaining algorithms, indicating that the matching accuracy is high. The proposed algorithm provides ideas for subsequent improved algorithms.

The Plumb-Line Matching Algorithm for UAV Oblique Photographic Photos

Building facades has always been a challenge for feature matching in oblique photogrammetry due to weak textures, non-Lambertian objects, severe occlusion, and distortion. Plumb lines are essential building geometry structural feature lines in building facades, which show strong spatial relevance to these problems. Achieving plumb line matching has great application potential for optimizing the process and products of oblique photogrammetry. Thus, we proposed a novel matching algorithm for plumb lines based on spatial and color hybrid constraints according to its central projection imaging characteristics. Firstly, based on vanishing point theory, the plumb lines from photos were back-calculated to determine the matching target set; secondly, the property of its large elevation ranges was exploited to calculate the homonymous points as spatial constraints by projecting plumb lines onto the stratified spatial planes; thirdly, the neighboring primary colors on both sides of the plumb lines were extracted as feature descriptors and compared by colorimetry; then, the greedy strategy was employed to successively filter out the locally optimal solutions satisfying the spatial and color hybrid constraints to complete the initial matching; finally, the intersection-over-union analysis of the solution plane and the verticalness evaluation of the matching results were implemented to eliminate errors. The results show that the proposed algorithm can achieve an average accuracy of 97.29% and 78.41% in the forward and lateral overlap experiments from multi-scenes, respectively, displaying a strong adaptability to poor texture, inconsistency, and distortion. In conclusion, thanks to the plumb-line-oriented matching strategy, this algorithm owns inherent advantages in theory and computational complexity. It is suitable for all building-oriented oblique photogrammetry tasks and is highly worthy of promotion and application.

Dehydroxylation of Kaolinite and Halloysite-Rich Samples: An In Situ Study of the Texture and Structural Evolutions

Halloysite and kaolinite are dioctahedral TO phyllosilicates that drive the interest of scientists for formulating environmentally friendly materials, and consequently in the field of ceramics. The main scope of this study was the understanding of the texture evolution upon the dehydroxylation reaction and the influence of the presence of halloysite. In situ synchrotron (002) and (111) poles figures were recorded on the DiffAbs beamline at SOLEIL Synchrotron, from room temperature to 1000 °C, on kaolinite and/or halloysite-rich samples shaped by tape casting. Commercial kaolins and halloysite provided by Imerys company were used. The samples were labeled KRG100, KCS100, H100, KRG50H50 and KRG59H50 in relation with the wt. % of kaolin (KRG, KCS) or halloysite (H) clays. In samples KCS100 and KRG100, a strong texture was observed until in situ annealing at 700 °C, with respect to the c-axis of kaolinite. On the contrary, the texture with respect to the c-axis of halloysite for the sample H100 was weak whatever the temperature was. Moreover, this weak texture disappeared before the complete dehydroxylation of halloysite. This is due to the opening of some halloysite tubes. When considering the samples KRG50H50 and KCS50H50, a significant texture was observed with the c-axis preferentially oriented perpendicular to the sample surface. The presence of kaolinite platelets predominated onto the alignment of halloysites tubes. Furthermore, it was noted that the halloysite influenced the (002) diffracted intensity into the temperature range 20 °C to 400 °C. Above 400 °C, the behavior obtained for the (002) reflection in samples KRG50H50 and KCS50H50 was similar to the behavior noticed for pure kaolins KRG100 and KCS100, respectively. The dehydroxylation temperature range appeared to be relevant with combined effect of kaolinite and halloysite transformations arising from KRG100 or KCS100 and H100 samples. Therefore, the onset point of dehydroxylation is 550 °C ± 25 °C for KRG100, KCS100, KRG50H50 and KCS50H50. For the pure halloysite H100 sample, the dehydroxylation starts at the lower temperature 475 °C. It was also noted that during the dehydroxylation of kaolinite, the characteristic portion of ring related to the diffracted intensity of the (111) reflection located at χ = 45° tended to disappear above 550 °C and led to the formation of a new transitory phase with a (111) reflection with perpendicular alignment to the c-axis. Indeed, an epitaxial relationship with the (111) kaolinite reflection could be assumed. Further X-ray scattering experiments allowed highlighting the effective offset temperature of the dehydroxylation, which was identified as close to 720 °C. The metakaolinite achieved structural transformation to another transitory phase at 1000 °C.

A deep learning-based local feature extraction method for improved image matching and surface reconstruction from Yutu-2 PCAM images on the Moon

Topographic reconstruction of the lunar surface or other planets is important to engineering applications and scientific research in a planetary exploration mission. The typical methods of terrain reconstruction are usually based on photogrammetry techniques. Structure-from-Motion (SfM) is one of the most effective and commonly used photogrammetric technologies that estimate three-dimensional structures from two-dimensional image sequences. To find correspondences and align photos, SfM approaches require invariant features, such as Scale Invariant Feature Transform (SIFT). The hand-crafted features, however, seriously degrade performance due to weak texture and low light conditions causing image matching failure, which will directly affect the accuracy and robustness of reconstruction. Robust local descriptors based on deep learning outperform hand-crafted descriptors since convolutional neural networks are more robust than hand-engineered representations. Therefore, a novel and robust deep learning-based local feature extraction method is proposed, comprising two branch networks integrated with attention mechanisms for generating reliable keypoints and descriptors, respectively. Furthermore, a 3D terrain surface reconstruction workflow is constructed by combining it with the modern advanced image matching method and SfM system. The effectiveness of the proposed method and the workflow were verified in experiments using Panoramic Camera (PCAM) images acquired from three waypoints explored by the Yutu-2 lunar rover during the Chang’e-4 mission. We also illustrate how our approach supports other applications, such as creating panoramic mosaics of surface imagery. This provides a new and powerful method for planetary terrain reconstruction at a high spatial resolution that can meet the requirements for rover navigation and positioning, as well as geological analysis of the Moon and other planets. The source codes developed in this study are openly available at https://github.com/Atypical-Programmer/Deep_Reconstruction_Workflow.

UAV remote sensing image stitching via improved VGG16 Siamese feature extraction network

UAV remote sensing image stitching can provide a more comprehensive and continuous area by stitching several overlapping region images. It has been widely used in many fields, such as airborne reconnaissance and surveillance tasks, agriculture production, geological disaster monitoring, and so on. However, traditional feature-based image stitching methods often require hand-crafted features and multiple execution steps, which could extract many redundant feature points in non-overlapping regions and may fail to stitch images with weak textures. To solve this problem, we propose an improved VGG16 Siamese network for the UAV remote sensing image stitching model to achieve end-to-end stitching. The first 13 layers of the VGG16 network were intercepted to form a shared weights feature extraction network, and an improved Squeeze-and-Excitation module was introduced to effectively extract the features of the overlapping areas of the images. A network of regressing affine matrix was designed by using the LeakyReLu activation function to protect the relevant feature maps after feature fine matching, which improves the accuracy of image stitching. Besides, we constructed datasets to train our network: a single UAV remote sensing image was used to form a training image pair based on a limited degree of affine transformation, and the real label of affine transformation between the image pairs was obtained. We compared the SIFT+RANSAC, APAP, and deep homography estimation-based image stitching algorithm on the UAV remote sensing datasets. Experiments show the value of structural similarity(SSIM) increased by 24.1%, and the root mean square error(RMSE) was reduced by 14.69%. Moreover, the proposed stitching model also has good stitching results for UAV remote sensing images as well as weak texture images in subjective visual effects.

Microstructural and textural gradients in SLM-manufactured AlSi10Mg after low-draught cold-rolling and heat treatment

Additively manufactured AlSi10Mg is often subject to a two-stage heat treatment, namely solid solution treatment followed by artificial aging, to achieve optimal properties. Before such heat treatments, slight surface plastic deformation may be applied to modify the surface quality and properties. However, gradients in microstructure and texture near the surface introduced by the plastic deformation may cause undesired microstructural and textural evolutions during subsequent heat treatment. In this work, we introduce plastic deformation in the surface layer in an SLM-manufactured AlSi10Mg sample by relatively low-draught cold rolling and we investigate the through-thickness variations in microstructure and texture in the deformed state and after heat treatment. The SLM-manufactured AlSi10Mg sample has a fine-scale microstructure and a weak texture, and is rather thermally stable during subsequent heat treatments. Applying 10% low-draught cold rolling to the SLM-manufactured AlSi10Mg sample is found to introduce a near Goss texture in the surface layer, while little change is observed in the center layer. After subsequent solution treatment and aging, abnormal grain growth occurred in the surface layer resulting in remarkable through thickness gradients in microstructure and texture.