Search

Accurate segmentation of industrial CT images is of great significance in industrial fields such as quality inspection and defect analysis. However, reconstruction of industrial CT images often suffers from typical metal artifacts caused by factors like beam hardening, scattering, statistical noise, and partial volume effects. Traditional segmentation methods are difficult to achieve precise segmentation of CT images mainly due to the presence of these metal artifacts. Furthermore, acquiring paired CT image data required by fully supervised networks proves to be extremely challenging. To address these issues, this paper introduces an improved CycleGAN approach for achieving semi-supervised segmentation of industrial CT images. This method not only eliminates the need for removing metal artifacts and noise, but also enables the direct conversion of metal artifact-contaminated images into segmented images without the requirement of paired data. The average values of quantitative assessment of image segmentation performance can reach 0.96645 for Dice Similarity Coefficient(Dice) and 0.93718 for Intersection over Union(IoU). In comparison to traditional segmentation methods, it presents significant improvements in both quantitative metrics and visual quality, provides valuable insights for further research. [ABSTRACT FROM AUTHOR]

In the present study, magnetic composite graphene oxide/cellulose (GO/CM@Fe 3 O 4 ) microspheres were prepared as support material, which are cost-efficient, non-toxic and environmental friendly. The microspheres with higher adsorption capacity were further modified using triethylene tetramine (TETA), and H 3 PW 12 O 40 (HPW) was immobilized to form GO/CM-NH 2 @Fe 3 O 4 -HPW microspheres as heterogeneous catalyst for biodiesel production. The novel heterogeneous catalyst was characterized by scanning electron microscopy (SEM), Fourier transform infrared spectroscopy (FT-IR), Brunauer-Emmett-Teller (BET) and X-ray diffractometry (XRD). For the first time, GO/CM-NH 2 @Fe 3 O 4- -HPW was applied in the transesterification of highly-acidic Pistacia chinensis seed oil to biodiesel. Under optimal reaction conditions 80 °C, methanol/oil molar ratio 12:1, catalyst 15 wt% (w/w of oil) for 8 h, a 94% biodiesel yield was achieved. The heterogeneous catalyst could be easily separated from the reaction system by using magnetic field and efficiently recycled for at least six times. This novel procedure overcomes the disadvantages of the current catalyst support such as active site leaching, complicated preparation process and high costs. Therefore, it was a potential novel heterogeneous catalyst for biodiesel production. [ABSTRACT FROM AUTHOR]