nav emailalert searchbtn searchbox tablepage yinyongbenwen piczone journalimg searchdiv qikanlogo popupnotification paper
2025 01 v.51 147-154
基于SC-TransUnet语义分割模型的焦炭基质提取
基金项目(Foundation): 福建省高校工程研究中心开放基金(MKF202202)
邮箱(Email): xiu.kan@sues.edu.cn;
DOI: 10.19886/j.cnki.dhdz.2024.0014
中文作者单位:

上海工程技术大学电子电气工程学院;安徽工业大学冶金工程学院;

摘要(Abstract):

焦炭基质的准确提取对于焦炭质量分析至关重要。针对焦炭基质结构复杂、边界不清晰以及显微图像含有白色光晕等问题,提出了一种基于SC-TransUnet语义分割模型的焦炭基质提取方法,模型通过CNN-Transformer混合结构进行高级语义信息提取,增强对焦炭基质不规则结构的表征能力,通过多种注意力机制融合增强对焦炭复杂纹理特征的感知能力。与目前主流的分割模型相比,所设计的模型在焦炭基质提取中取得了更好的分割效果。试验证明该模型的Acc、Miu和F1s分别达94.75%、89.96%和95.23%,可为焦炭基质自动提取提供一种可靠且高效的解决方案。

关键词(KeyWords): 焦炭基质提取;语义分割;SC-TransUnet;焦炭显微图像;CNN-Transformer;注意力机制
参考文献

[1] LI J L,WANG Y F,ZHU L C,et al.Experimental study on co-pyrolysis of petroleum coke and coals:Synergy effects and co-gasification reactivity[J].Fuel,2020,279:118368.

[2] SHEN F L,GUPTA S,LIU Y,et al.Effect of reaction conditions on coke tumbling strength,carbon structure and mineralogy[J].Fuel,2013,111:223-228.

[3] 杨子芹,刘卫卫,杨小兵,等.蒙脱土有机改性对丁基橡胶复合材料微观结构与性能的影响[J].高分子材料科学与工程,2011,27(9):52-55.YANG Z Q,LIU W W,YANG X B,et al.Influence of montmorillonite organic modification on the microstructure and properties of IIR composites[J].Polymer Materials Science & Engineering,2011,27(9):52-55.

[4] 丁子昭.焦炭溶损反应机理的分子动力学研究[D].唐山:华北理工大学,2021.DING Z Z.Molecular dynamics study on dissolution-loss reaction mechanism of coke[D].Tangshan:North China University of Science and Technology,2021.

[5] DONSKOI E,POLIAKOV A,MAHONEY M R,et al.Novel optical image analysis coke characterisation and its application to study of the relationships between coke Structure,coke strength and parent coal composition[J].Fuel,2017,208:281-295.

[6] 任世彪,张代林,蔡建安.图像分析在焦炭气孔结构参数测定中的应用[J].安徽工业大学学报(自然科学版),2003,20(1):66-68.REN S B,ZHANG D L,CAI J A.Application of image analysis in the determining of coke pore structure parameters[J].Journal of Anhui University of Technology (Natural Science),2003,20(1):66-68.

[7] 王培珍,毛雪芹,毛雪菲,等.基于均值偏移和边缘置信度的焦炭显微图像分割[J].中国图象图形学报,2010,15(10):1478-1484.WANG P Z,MAO X Q,MAO X F,et al.Coke micrograph segmentation based on mean shift and edge confidence[J].Journal of Image and Graphics,2010,15(10):1478-1484.

[8] DONSKOI E,POLIAKOV A,MANUEL J R.Automated optical image analysis of natural and sintered iron ore[M].Iron Ore.Amsterdam Elsevier,2015:101-159.

[9] SAID Y,ALSHEIKHY A A,SHAWLY T,et al.Medical images segmentation for lung cancer diagnosis based on deep learning architectures[J].Diagnostics,2023,13(3):546.

[10] 阮雨,孙韶媛,李佳豪,等.基于深度学习的夜间模式下自动驾驶场景预测[J].东华大学学报(自然科学版),2019,45(5):709-714.RUAN Y,SUN S Y,LI J H,et al.Automatic driving scene prediction based on deep learning in nighttime mode[J].Journal of Donghua University (Natural Science),2019,45(5):709-714.

[11] TIAN L,ZHONG X R,CHEN M.Semantic segmentation of remote sensing image based on GAN and FCN network model[J].Scientific Programming,2021,2021(1):9491376.

[12] SHELHAMER E,LONG J,DARRELL T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640-651.

[13] RONNEBERGER O,FISCHER P,BROX T.U-Net:convolutional networks for biomedical image segmentation[M]//Medical Image Computing and Computer-Assisted Intervention-MI(CAI 2015).Cham:Springer International Publishing,2015:234-241.

[14] VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[C]//The 31st Annual Conference on Neural Information Processing.2017.

[15] CHEN J N,LU Y Y,YU Q H,et al.TransUNet:transformers make strong encoders for medical image segmentation[EB/OL].2021:2102.04306.https://arxiv.org/abs/2102.04306v1.

[16] 金厚鑫,曹乐,阚秀,等.基于卷积神经网络的显微煤粒分类算法[J].电子显微学报,2022,41(2):137-147.JIN H X,CAO L,KAN X,et al.Microscopic coal grain classification algorithm based on convolutional neural network[J].Journal of Chinese Electron Microscopy Society,2022,41(2):137-147.

[17] HU J,SHEN L,SUN G.Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT,USA.IEEE,2018:7132-7141.

[18] WOO S,PARK J,LEE J Y,et al.CBAM:convolutional block attention module[C]//Computer Vison-ECCV2018.Cham:Springer International Publishing,2018:3-19.

[19] LI X Y,SUN X F,MENG Y X,et al.Dice loss for data-imbalanced NLP tasks[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.Online.Stroudsburg,PA,USA:Association for Computational Linguistics,2020:465-476.

[20] KINGMA D P,BA J,HAMMAD M M.Adam:a method for stochastic optimization[EB/OL].(2014-12-22)[2024-01-01].https://arxiv.org/abs/1412.6980v9.

[21] ZHOU Z W,SIDDIQUEE M M R,TAJBAKHSH N,et al.UNet++:redesigning skip connections to exploit multiscale features in image segmentation[J].IEEE Transactions on Medical Imaging,2020,39(6):1856-1867.

[22] CHEN L C,ZHU Y K,PAPANDREOU G,et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[M].Computer Vision ECCV 2018.Cham:Springer International Publishing,2018:833-851.

[23] VALANARASU J M J,PATEL V M.UNeXt:MLP-based rapid medical image segmentation network[C]//Medical Image Computing and Computer Assisted Intervention-MICCAI 2022:23-33.

基本信息:

DOI:10.19886/j.cnki.dhdz.2024.0014

中图分类号:TQ520.1;TP391.41

引用信息:

[1]张臻,阚秀,孙维周等.基于SC-TransUnet语义分割模型的焦炭基质提取[J].东华大学学报(自然科学版),2025,51(01):147-154.DOI:10.19886/j.cnki.dhdz.2024.0014.

基金信息:

福建省高校工程研究中心开放基金(MKF202202)

引用

GB/T 7714-2015 格式引文
MLA格式引文
APA格式引文
检 索 高级检索