铝合金铸件已经广泛应用于汽车、飞机等重要工业,其质量直接影响到机械零部件的安全使用。针对铝合金铸件的X射线图像表面和内部缺陷多样化和细微问题,提出了一种融合局部和全局特征的X射线图像铸造缺陷检测方法。首先,将高效通道注意...铝合金铸件已经广泛应用于汽车、飞机等重要工业,其质量直接影响到机械零部件的安全使用。针对铝合金铸件的X射线图像表面和内部缺陷多样化和细微问题,提出了一种融合局部和全局特征的X射线图像铸造缺陷检测方法。首先,将高效通道注意力模块和经典网络ResNet-50进行融合构成新的基础卷积神经网络,以新的网络为骨干构建双分支网络模型。然后,提出了细节信息定位提取(detailed information location and extraction,DILE)模块,该模块定位到包含丰富判别性信息的局部区域。最后,将由DILE得到的局部图像结合原始图像作为网络的输入,构建了一个融合局部和全局特征的双分支网络模型。对全局区域的学习有助于在复杂背景下提取有意义的细微信息,对局部区域的学习可以进一步提高分类效果。该方法在真实汽车铸件的X射线图像数据集上进行测试训练,测试集准确率达98.3%。实验结果表明,该方法相较于其他常规方法更有效。展开更多
Subsurface defects were fluorescently tagged with nanoscale quantum dots and scanned layer by layer using confocal fluorescence microscopy to obtain images at various depths. Subsurface damage depths of fused silica o...Subsurface defects were fluorescently tagged with nanoscale quantum dots and scanned layer by layer using confocal fluorescence microscopy to obtain images at various depths. Subsurface damage depths of fused silica optics were characterized quantitatively by changes in the fluorescence intensity of feature points. The fluorescence intensity vs scan depth revealed that the maximum fluorescence intensity decreases sharply when the scan depth exceeds a critical value. The subsurface damage depth could be determined by the actual embedded depth of the quantum dots. Taper polishing and magnetorheological finishing were performed under the same conditions to verify the effectiveness of the nondestructive fluorescence method. The results indicated that the quantum dots effectively tagged subsurface defects of fused-silica optics, and that the nondestructive detection method could effectively evaluate subsurface damage depths.展开更多
Carbon-fiber reinforced polymer composites have been widely used to achieve the light-weighted design and high performance due to superior performance. Internal defects in the composite materials are the main factors ...Carbon-fiber reinforced polymer composites have been widely used to achieve the light-weighted design and high performance due to superior performance. Internal defects in the composite materials are the main factors that determine their performance,which makes reliable and effective detection methods of internal defects essential. Nondestructive testing(NDT)methods are the most widely-used way due to their tremendous advantages. Though the theoretical background is found,experimental results could be quite complicated and confusing,especially for composite materials with complex defects characteristics. In this paper,experimental study on internal defects in composite materials based on the time of flight(ToF)are investigated. The Gaussian echo model and the parameter estimation methods are established to build a theoretical model for measurements. Then,the distance amplitude correction(DAC)method is proposed to effectively improve the signal-to-noise ratio(SNR)and to reduce distortion of the signal during measurements. Finally,the ToF is adopted to determine depth of internal defects. Experiment study is conducted to investigate the porosity defects and the anti-impact performance of composite materials,as well as defects in objects with various thicknesses. Experimental results show that the proposed method is quite helpful for obtaining the intuition and deep understanding of internal defects,thus contributing to the determination of product performance and its improvement.展开更多
With the increase of wood and wood products demands in the world, non-destructive evaluation techniques of wood are more and more important. This article clarifies the importance and present situation of non-destructi...With the increase of wood and wood products demands in the world, non-destructive evaluation techniques of wood are more and more important. This article clarifies the importance and present situation of non-destructive evaluation and introduces some instruments about non-destructive evaluation, and some advice and ideas are put forward.展开更多
文摘铝合金铸件已经广泛应用于汽车、飞机等重要工业,其质量直接影响到机械零部件的安全使用。针对铝合金铸件的X射线图像表面和内部缺陷多样化和细微问题,提出了一种融合局部和全局特征的X射线图像铸造缺陷检测方法。首先,将高效通道注意力模块和经典网络ResNet-50进行融合构成新的基础卷积神经网络,以新的网络为骨干构建双分支网络模型。然后,提出了细节信息定位提取(detailed information location and extraction,DILE)模块,该模块定位到包含丰富判别性信息的局部区域。最后,将由DILE得到的局部图像结合原始图像作为网络的输入,构建了一个融合局部和全局特征的双分支网络模型。对全局区域的学习有助于在复杂背景下提取有意义的细微信息,对局部区域的学习可以进一步提高分类效果。该方法在真实汽车铸件的X射线图像数据集上进行测试训练,测试集准确率达98.3%。实验结果表明,该方法相较于其他常规方法更有效。
基金Project(JCKY2016212A506-0503) supported by the Science Challenge Project of ChinaProject(51475106) supported by the National Natural Science Foundation of China
文摘Subsurface defects were fluorescently tagged with nanoscale quantum dots and scanned layer by layer using confocal fluorescence microscopy to obtain images at various depths. Subsurface damage depths of fused silica optics were characterized quantitatively by changes in the fluorescence intensity of feature points. The fluorescence intensity vs scan depth revealed that the maximum fluorescence intensity decreases sharply when the scan depth exceeds a critical value. The subsurface damage depth could be determined by the actual embedded depth of the quantum dots. Taper polishing and magnetorheological finishing were performed under the same conditions to verify the effectiveness of the nondestructive fluorescence method. The results indicated that the quantum dots effectively tagged subsurface defects of fused-silica optics, and that the nondestructive detection method could effectively evaluate subsurface damage depths.
文摘Carbon-fiber reinforced polymer composites have been widely used to achieve the light-weighted design and high performance due to superior performance. Internal defects in the composite materials are the main factors that determine their performance,which makes reliable and effective detection methods of internal defects essential. Nondestructive testing(NDT)methods are the most widely-used way due to their tremendous advantages. Though the theoretical background is found,experimental results could be quite complicated and confusing,especially for composite materials with complex defects characteristics. In this paper,experimental study on internal defects in composite materials based on the time of flight(ToF)are investigated. The Gaussian echo model and the parameter estimation methods are established to build a theoretical model for measurements. Then,the distance amplitude correction(DAC)method is proposed to effectively improve the signal-to-noise ratio(SNR)and to reduce distortion of the signal during measurements. Finally,the ToF is adopted to determine depth of internal defects. Experiment study is conducted to investigate the porosity defects and the anti-impact performance of composite materials,as well as defects in objects with various thicknesses. Experimental results show that the proposed method is quite helpful for obtaining the intuition and deep understanding of internal defects,thus contributing to the determination of product performance and its improvement.
文摘With the increase of wood and wood products demands in the world, non-destructive evaluation techniques of wood are more and more important. This article clarifies the importance and present situation of non-destructive evaluation and introduces some instruments about non-destructive evaluation, and some advice and ideas are put forward.
