Advance Search
Volume 50 Issue 1
Jan.  2022
Turn off MathJax
Article Contents
WANG Peizhen, YU Chen, XUE Zihan, ZHANG Dailin. Transfer learning based identification model for macerals of exinite in coal[J]. COAL SCIENCE AND TECHNOLOGY, 2022, 50(1): 220-227.
Citation: WANG Peizhen, YU Chen, XUE Zihan, ZHANG Dailin. Transfer learning based identification model for macerals of exinite in coal[J]. COAL SCIENCE AND TECHNOLOGY, 2022, 50(1): 220-227.

Transfer learning based identification model for macerals of exinite in coal

Funds: 

National Natural Science Foundation of China (51574004); Key Natural Science Research Project of Anhui Provincial Department of Education (KJ2019A0085); Academic Key Funding Project for Top Disciplines in Anhui Province (gxbjZD2016041)

More Information
  • Available Online: April 02, 2023
  • Published Date: January 24, 2022
  • To improve the identification accuracy of exinite macerals in coal and avoid the manual intervention in the feature extraction stage of classifier construction, the deep learning method was employed for the automatic identification of macerals of exinite in coal. Owing to the limiting of sample number of exinite maceral in coal, the classifier constructed with the conventional convolutional neural network tends to be over-fitting and the poor generalization ability. To solve this problem, an identification model (classifier), which is based on transfer learning, was proposed. Based on conventional convolution neural network model, this method shared the weight parameters of convolution layer and pooling layer with the pre-training network model by transfer learning, optimized the network model structure and full connection layer parameters with samples of exinite macerals, and constructed a new deep learning network model for the maceral identification of exinite of coal. The experimental results show that, compared with that of the conventional neural network, the transfer learning based identification model proposed in this paper is more effective, and the classifier with VGG16 as pre-training network is of best performance on this dataset, with identification accuracy of 98.10% for test samples; owing to the reduction of parameter number, the training time is obviously shortened, and the convergence is achieved in a short training period with a stable identification accuracy, indicating that the classifier based on VGG16 as the pre training model has better performance in the identification of macerals of exinite in coal.
  • Cited by

    Periodical cited type(9)

    1. 李炜,刘耕,葛云峰,张占荣,黄国良. 基于深度学习的钻孔图像岩体结构面识别. 应用基础与工程科学学报. 2024(03): 702-720 .
    2. 刘大锰,王子豪,陈佳明,邱峰,朱凯,高羚杰,周柯宇,许少博,孙逢瑞. 基于ResNet残差神经网络识别的深部煤层显微组分和微裂缝分类——以鄂尔多斯盆地石炭系本溪组8~#煤层为例. 石油与天然气地质. 2024(06): 1524-1536 .
    3. 季菁菁,奚峥皓,李忠峰. 基于深度迁移学习的煤岩显微组分识别算法. 智能计算机与应用. 2023(02): 92-97+102 .
    4. 王小令,王绍清,陈昊,赵云刚,沙吉顿,李慷. 不同镜惰比低阶煤的结构特征及其热解行为. 煤炭科学技术. 2023(05): 294-301 . 本站查看
    5. 束振宇,徐祥,魏迎春,王安民,王路,刘志飞,陈高建,曹代勇. 不同类型接触变质煤大分子结构差异性研究. 煤炭科学技术. 2023(06): 147-157 . 本站查看
    6. 马羊,马笑. 矿浆pH对煤岩显微组浮选分离效果的影响. 洁净煤技术. 2023(S1): 24-27 .
    7. 袁懿琳,赵荣焕,何坤,黄秀,王洪栋,邹亮. 基于随机森林和树突网络的煤镜质组反射率估计. 工矿自动化. 2023(08): 148-155 .
    8. 张倩如,王云飞,吕帅朝,宋磊,尚钰莹,宋怀波. 基于改进GhostNet的小麦秸秆表皮结构完整性分类方法. 南京农业大学学报. 2022(04): 788-798 .
    9. 曾烃详,刘岩,文志刚,樊云鹏,冯兴强,季长军,史旭凯,高变变,武远哲. 基于迁移学习的全岩光片有机显微组分识别与定量——以皖泾地1井下三叠统殷坑组烃源岩为例. 科学技术与工程. 2022(35): 15485-15493 .

    Other cited types(3)

Catalog

    Article views (115) PDF downloads (264) Cited by(12)
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return