This work establishes a temperature-controlled sequence function, and a new multi-phase-field model, for liquid- solid-solid multi-phase transformation by coupling the liquid-solid phase transformation model with the ...This work establishes a temperature-controlled sequence function, and a new multi-phase-field model, for liquid- solid-solid multi-phase transformation by coupling the liquid-solid phase transformation model with the solid-solid phase transformation model. Taking an Fe-C alloy as an example, the continuous evolution of a multi-phase transformation is simulated by using this new model. In addition, the growth of grains affected by the grain orientation of the parent phase (generated in liquid-solid phase transformation) in the solid-solid phase transformation is studied. The results show that the morphology of ferrite grains which nucleate at the boundaries of the austenite grains is influenced by the orientation of the parent austenite grains. The growth rate of ferrite grains which nucleate at small-angle austenite grain boundaries is faster than those that nucleate at large-angle austenite grain boundaries. The difference of the growth rate of ferrites grains in different parent phase that nucleate at large-angle austenite grain boundaries, on both sides of the boundaries, is greater than that of ferrites nucleating at small-angle austenite grain boundaries.展开更多
近年来,Transformer在众多监督式计算机视觉任务中取得了显著进展,然而由于高质量医学标注图像的缺乏,其在半监督图像分割领域的性能仍有待提高。为此,提出了一种基于多尺度和多视图Transformer的半监督医学图像分割框架:MSMVT(multi-sc...近年来,Transformer在众多监督式计算机视觉任务中取得了显著进展,然而由于高质量医学标注图像的缺乏,其在半监督图像分割领域的性能仍有待提高。为此,提出了一种基于多尺度和多视图Transformer的半监督医学图像分割框架:MSMVT(multi-scale and multi-view transformer)。鉴于对比学习在Transformer的预训练中取得的良好效果,设计了一个基于伪标签引导的多尺度原型对比学习模块。该模块利用图像金字塔数据增强技术,为无标签图像生成富有语义信息的多尺度原型表示;通过对比学习,强化了不同尺度原型之间的一致性,从而有效缓解了由标签稀缺性导致的Transformer训练不足的问题。此外,为了增强Transformer模型训练的稳定性,提出了多视图一致性学习策略。通过弱扰动视图,以校正多个强扰动视图。通过最小化不同视图之间的输出差异性,使得模型能够对不同扰动保持多层次的一致性。实验结果表明,当仅采用10%的标注比例时,提出的MSMVT框架在ACDC、LIDC和ISIC三个公共数据集上的DSC图像分割性能指标分别达到了88.93%、84.75%和85.38%,优于现有的半监督医学图像分割方法。展开更多
Taking Fe-C binary alloy as an example,based on the multi-phase field model,the nucleation and growth ofδphase,peritectic reaction,peritectic transformation,and the growth of subsequent austenite are simulated.Effect...Taking Fe-C binary alloy as an example,based on the multi-phase field model,the nucleation and growth ofδphase,peritectic reaction,peritectic transformation,and the growth of subsequent austenite are simulated.Effects of the nucleation site of austenite on the peritectic reaction rate and the starting time of the peritectic transformation were studied.The simulation results show that theγphase,as a shell,surrounds theδphase and grows rapidly when the peritectic reaction occurs between the dendriticδgrains,and a layer ofγphase shell is formed aroundδphase after the peritectic reaction.After theδphase is surrounded byγphase completely,the membrane shell separates the L phase from theδphase,so that the phase transfers from peritectic reaction to peritectic transformation.During the peritectic transformation,since the solute diffusion coefficient of the liquid phase is much greater than that of the solid phase,the average growth rate of austenite in the liquid phase is visibly higher than that of theδphase.The peritectic reaction rate is related to the curvature of the nucleation site of theγphase on theδphase grains.The peritectic reaction rate at the large curvatures is faster than that at small curvatures.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.51661020,11504149,and 11364024)
文摘This work establishes a temperature-controlled sequence function, and a new multi-phase-field model, for liquid- solid-solid multi-phase transformation by coupling the liquid-solid phase transformation model with the solid-solid phase transformation model. Taking an Fe-C alloy as an example, the continuous evolution of a multi-phase transformation is simulated by using this new model. In addition, the growth of grains affected by the grain orientation of the parent phase (generated in liquid-solid phase transformation) in the solid-solid phase transformation is studied. The results show that the morphology of ferrite grains which nucleate at the boundaries of the austenite grains is influenced by the orientation of the parent austenite grains. The growth rate of ferrite grains which nucleate at small-angle austenite grain boundaries is faster than those that nucleate at large-angle austenite grain boundaries. The difference of the growth rate of ferrites grains in different parent phase that nucleate at large-angle austenite grain boundaries, on both sides of the boundaries, is greater than that of ferrites nucleating at small-angle austenite grain boundaries.
文摘近年来,Transformer在众多监督式计算机视觉任务中取得了显著进展,然而由于高质量医学标注图像的缺乏,其在半监督图像分割领域的性能仍有待提高。为此,提出了一种基于多尺度和多视图Transformer的半监督医学图像分割框架:MSMVT(multi-scale and multi-view transformer)。鉴于对比学习在Transformer的预训练中取得的良好效果,设计了一个基于伪标签引导的多尺度原型对比学习模块。该模块利用图像金字塔数据增强技术,为无标签图像生成富有语义信息的多尺度原型表示;通过对比学习,强化了不同尺度原型之间的一致性,从而有效缓解了由标签稀缺性导致的Transformer训练不足的问题。此外,为了增强Transformer模型训练的稳定性,提出了多视图一致性学习策略。通过弱扰动视图,以校正多个强扰动视图。通过最小化不同视图之间的输出差异性,使得模型能够对不同扰动保持多层次的一致性。实验结果表明,当仅采用10%的标注比例时,提出的MSMVT框架在ACDC、LIDC和ISIC三个公共数据集上的DSC图像分割性能指标分别达到了88.93%、84.75%和85.38%,优于现有的半监督医学图像分割方法。
基金the National Natural Science Foundation of China(Grant Nos.:11504149,51661020)Natural Science Foundation of Gansu Province of China(Grant No.:18JR3RA147).
文摘Taking Fe-C binary alloy as an example,based on the multi-phase field model,the nucleation and growth ofδphase,peritectic reaction,peritectic transformation,and the growth of subsequent austenite are simulated.Effects of the nucleation site of austenite on the peritectic reaction rate and the starting time of the peritectic transformation were studied.The simulation results show that theγphase,as a shell,surrounds theδphase and grows rapidly when the peritectic reaction occurs between the dendriticδgrains,and a layer ofγphase shell is formed aroundδphase after the peritectic reaction.After theδphase is surrounded byγphase completely,the membrane shell separates the L phase from theδphase,so that the phase transfers from peritectic reaction to peritectic transformation.During the peritectic transformation,since the solute diffusion coefficient of the liquid phase is much greater than that of the solid phase,the average growth rate of austenite in the liquid phase is visibly higher than that of theδphase.The peritectic reaction rate is related to the curvature of the nucleation site of theγphase on theδphase grains.The peritectic reaction rate at the large curvatures is faster than that at small curvatures.