Bimetallic additively manufactured structures(BAMSs)can replace traditionally-fabricated functionallygraded-components through fusion welding processes and can eliminate locally-deteriorated mechanical properties aris...Bimetallic additively manufactured structures(BAMSs)can replace traditionally-fabricated functionallygraded-components through fusion welding processes and can eliminate locally-deteriorated mechanical properties arising from post-processing.The present work fabricates a BAMS by sequentially depositing the austenitic stainless-steel and Inconel625 using a gas-metal-arc-welding(GMAW)-based wire+arc additive manufacturing(WAAM)system.Elemental mapping shows a smooth compositional transition at the interface without any segregation.Both materials being the face-center-cubic(FCC)austenite,the electron backscattered diffraction(EBSD)analysis of the interface shows the smooth and cross-interfacecrystallographic growth of long-elongated grains in the<001>direction.The hardness values were within the range of 220-240 HV for both materials without a large deviation at the interface.Due to the controlled thermal history,mechanical testing yielded a consistent result with the ultimate tensile strength and elongation of 600 MPa and 40%,respectively,with the failure location on the stainless-steel side.This study demonstrates that WAAM has the potential to fabricate BAMS with controlled properties.展开更多
BAM (Bidirectional Associative Memory)神经网络以其双向异联想性、较强的学习和自适应能力以及噪声容忍性好等特点,在模式分类和识别等方面具有广泛的应用前景。与实值神经网络相比,复值神经网络是一种基于复数运算的神经网络模型,...BAM (Bidirectional Associative Memory)神经网络以其双向异联想性、较强的学习和自适应能力以及噪声容忍性好等特点,在模式分类和识别等方面具有广泛的应用前景。与实值神经网络相比,复值神经网络是一种基于复数运算的神经网络模型,可以有效地刻画如图像、声音等具有多个维度的信号,减少对信号的近似,从而提高模型的精度。因此,本文主要研究了一类比例时滞复值BAM神经网络的全局指数稳定性,利用Banach不动点定理,给出了这类神经网络全局指数稳定的充分条件。最后,举出具体的数值算例验证了结果的有效性。BAM (Bidirectional Associative Memory) neural networks have significant potential for applications in pattern classification and recognition due to their bidirectional associations, robust learning and adaptive capabilities, and excellent noise tolerance. Compared with real-valued neural networks, complex-valued neural networks, which are based on complex operations, can more effectively represent multi-dimensional signals such as images and sounds. They reduce signal approximation errors and enhance model accuracy. Consequently, this paper primarily focuses on the global exponential stability of a class of proportional delay complex-valued BAM neural networks. By applying the Banach fixed point theorem, the sufficient conditions for the global exponential stability of these neural networks are given. Finally, a numerical example is provided to demonstrate the effectiveness of the results.展开更多
5-Aminolevulinic acid(ALA)is a novel plant growth regulator that has shown outstanding capability to promote stomatal opening.Starch degradation,catalyzed byβ-amylase(EC3.2.1.2,BAM),plays an important role in stomata...5-Aminolevulinic acid(ALA)is a novel plant growth regulator that has shown outstanding capability to promote stomatal opening.Starch degradation,catalyzed byβ-amylase(EC3.2.1.2,BAM),plays an important role in stomatal opening.However,whether the starch breakdown is involved in ALA-regulating stomatal movement is unclear.In the current study,we found that exogenous ALA effectively stimulated the starch breakdown in guard cells,increasedβ-amylase activity and promoted stomatal opening in leaves of apple(Malus×domestica).Based on genome-wide identification,we identified a total of 119 members of BAM gene family in ten commonly Rosaceae crops.Analyses of gene structure,motif identification,and gene pair collinearity revealed relative conservation among members within the same group or subgroup.Among these genes,MdBAM17 and other 12 genes were identified as the orthologous genes of AtBAM1,which is responsible for starch degradation to modulate the stomatal movement in Arabidopsis.qRT-PCR analysis revealed a positive correlation between the expressions of MdBAM17 and stomatal aperture,as well asβ-amylase activity,whereas a negative correlation was observed with the starch content.Subcellular localization analysis confirmed that MdBAM17 is a chloroplast protein,consistent with the AtBAM1.MdBAM17 was mainly expressed in guard cells and responsive to exogenous ALA.Overexpressing MdBAM17 increasedβ-amylase activity and promoted starch breakdown,leading to stomatal opening,which was further strengthened by ALA.RNA-interfering MdBAM17 decreasedβ-amylase activity,resulting in starch accumulation,and impairing the stomatal opening by ALA.However,modulation of MdBAM17 expression did not affect the levels of flavonols and H_(2)O_(2)in guard cells,suggesting that MdBAM17-promoted starch degradation may function at downstream of ROS signaling in the ALAregulated stomatal opening.Our findings provide new insights into the mechanisms of ALA-regulated stomatal movement.展开更多
马铃薯叶部病害的准确检测和识别对于精准防治病虫害至关重要,能够有效提高马铃薯产量,但由于马铃薯叶部的早疫病和晚疫病在早期表现上非常相似,很难区分。为了更准确地对马铃薯叶部病害进行检测识别,本文提出了一种基于位置编码和并行...马铃薯叶部病害的准确检测和识别对于精准防治病虫害至关重要,能够有效提高马铃薯产量,但由于马铃薯叶部的早疫病和晚疫病在早期表现上非常相似,很难区分。为了更准确地对马铃薯叶部病害进行检测识别,本文提出了一种基于位置编码和并行注意力机制的Conv Ne Xt模型。首先对数据集进行位置编码预处理,使网络模型无需加载预训练权重即可获取病害部位的位置信息,提高学习能力;其次针对不同病害空间分布位置不同以及形态特征的细微差异,添加并行注意力机制BAM模块增强对病害特征的提取能力。实验结果表明:优化后的ConvNeXt模型能够准确检测并对不同病害进行分类识别,较原ConvNeXt模型Top-1准确率最高提高约5个百分点,能够满足目前马铃薯叶部病害准确识别方面的需求,有良好的鲁棒性,可以泛化在其他植物种类上。展开更多
基金This study has been conducted with the support of the Korea Institute of Industrial Technology as a project on the development of metal 3D printing materials and process optimization technology for medium-and large-sized transportation part mold manufacturing(KITECH JE200008).
文摘Bimetallic additively manufactured structures(BAMSs)can replace traditionally-fabricated functionallygraded-components through fusion welding processes and can eliminate locally-deteriorated mechanical properties arising from post-processing.The present work fabricates a BAMS by sequentially depositing the austenitic stainless-steel and Inconel625 using a gas-metal-arc-welding(GMAW)-based wire+arc additive manufacturing(WAAM)system.Elemental mapping shows a smooth compositional transition at the interface without any segregation.Both materials being the face-center-cubic(FCC)austenite,the electron backscattered diffraction(EBSD)analysis of the interface shows the smooth and cross-interfacecrystallographic growth of long-elongated grains in the<001>direction.The hardness values were within the range of 220-240 HV for both materials without a large deviation at the interface.Due to the controlled thermal history,mechanical testing yielded a consistent result with the ultimate tensile strength and elongation of 600 MPa and 40%,respectively,with the failure location on the stainless-steel side.This study demonstrates that WAAM has the potential to fabricate BAMS with controlled properties.
文摘BAM (Bidirectional Associative Memory)神经网络以其双向异联想性、较强的学习和自适应能力以及噪声容忍性好等特点,在模式分类和识别等方面具有广泛的应用前景。与实值神经网络相比,复值神经网络是一种基于复数运算的神经网络模型,可以有效地刻画如图像、声音等具有多个维度的信号,减少对信号的近似,从而提高模型的精度。因此,本文主要研究了一类比例时滞复值BAM神经网络的全局指数稳定性,利用Banach不动点定理,给出了这类神经网络全局指数稳定的充分条件。最后,举出具体的数值算例验证了结果的有效性。BAM (Bidirectional Associative Memory) neural networks have significant potential for applications in pattern classification and recognition due to their bidirectional associations, robust learning and adaptive capabilities, and excellent noise tolerance. Compared with real-valued neural networks, complex-valued neural networks, which are based on complex operations, can more effectively represent multi-dimensional signals such as images and sounds. They reduce signal approximation errors and enhance model accuracy. Consequently, this paper primarily focuses on the global exponential stability of a class of proportional delay complex-valued BAM neural networks. By applying the Banach fixed point theorem, the sufficient conditions for the global exponential stability of these neural networks are given. Finally, a numerical example is provided to demonstrate the effectiveness of the results.
基金supported by the Natural Science Foundation of China(Grant No.32172512)the Jiangsu Special Fund for Frontier Foundation Research of Carbon Peaking and Carbon Neutralization(Grant No.BK20220005)a project funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions。
文摘5-Aminolevulinic acid(ALA)is a novel plant growth regulator that has shown outstanding capability to promote stomatal opening.Starch degradation,catalyzed byβ-amylase(EC3.2.1.2,BAM),plays an important role in stomatal opening.However,whether the starch breakdown is involved in ALA-regulating stomatal movement is unclear.In the current study,we found that exogenous ALA effectively stimulated the starch breakdown in guard cells,increasedβ-amylase activity and promoted stomatal opening in leaves of apple(Malus×domestica).Based on genome-wide identification,we identified a total of 119 members of BAM gene family in ten commonly Rosaceae crops.Analyses of gene structure,motif identification,and gene pair collinearity revealed relative conservation among members within the same group or subgroup.Among these genes,MdBAM17 and other 12 genes were identified as the orthologous genes of AtBAM1,which is responsible for starch degradation to modulate the stomatal movement in Arabidopsis.qRT-PCR analysis revealed a positive correlation between the expressions of MdBAM17 and stomatal aperture,as well asβ-amylase activity,whereas a negative correlation was observed with the starch content.Subcellular localization analysis confirmed that MdBAM17 is a chloroplast protein,consistent with the AtBAM1.MdBAM17 was mainly expressed in guard cells and responsive to exogenous ALA.Overexpressing MdBAM17 increasedβ-amylase activity and promoted starch breakdown,leading to stomatal opening,which was further strengthened by ALA.RNA-interfering MdBAM17 decreasedβ-amylase activity,resulting in starch accumulation,and impairing the stomatal opening by ALA.However,modulation of MdBAM17 expression did not affect the levels of flavonols and H_(2)O_(2)in guard cells,suggesting that MdBAM17-promoted starch degradation may function at downstream of ROS signaling in the ALAregulated stomatal opening.Our findings provide new insights into the mechanisms of ALA-regulated stomatal movement.
文摘马铃薯叶部病害的准确检测和识别对于精准防治病虫害至关重要,能够有效提高马铃薯产量,但由于马铃薯叶部的早疫病和晚疫病在早期表现上非常相似,很难区分。为了更准确地对马铃薯叶部病害进行检测识别,本文提出了一种基于位置编码和并行注意力机制的Conv Ne Xt模型。首先对数据集进行位置编码预处理,使网络模型无需加载预训练权重即可获取病害部位的位置信息,提高学习能力;其次针对不同病害空间分布位置不同以及形态特征的细微差异,添加并行注意力机制BAM模块增强对病害特征的提取能力。实验结果表明:优化后的ConvNeXt模型能够准确检测并对不同病害进行分类识别,较原ConvNeXt模型Top-1准确率最高提高约5个百分点,能够满足目前马铃薯叶部病害准确识别方面的需求,有良好的鲁棒性,可以泛化在其他植物种类上。
