Reconstruction and classification of 3D burden surfaces based on two model drived data fusion

被引：5
作者：
Sun, Shaolun
Yu, Zejun
Zhang, Sen [1 ]
Xiao, Wendong
Yang, Yongliang
机构：
[1] Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China
来源：
EXPERT SYSTEMS WITH APPLICATIONS | 2023年 / 215卷
基金：
中国国家自然科学基金;
关键词：
Burden surface; Charging mechanism model; GPR; CNN;
D O I：
10.1016/j.eswa.2022.119406
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Blast furnace (BF) burden surface modeling is the basis for automating precise charging operations of BFs, and it can also be used to predict gas flow distributions based on a burden profile. In this paper, first, a mechanism model is established according to the charging operation, and it is convenient for predicting the burden profile after the charging operation. Then, the Gaussian process regression (GPR) algorithm is used to fuse the charging mechanism model and the radar detection data to better reconstruct the burden profile. Finally, the traditional shape of a burden surface is researched based on the point cloud data of a phased array radar, and 4 classes of burden surfaces are defined and reconstructed. The reconstructed burden surface is classified by expert-defined features and deep features extracted by convolutional neural networks (CNNs).
引用
收藏
页数：14
相关论文
共 50 条
[41]   DTV-CNN: Neural network based on depth and thickness views for efficient 3D shape classification [J].
Xia, Qingfeng .
HELIYON, 2023, 9 (11)
[42]   Reconstructing 3D Lung Shape from a Single 2D Image during the Deaeration Deformation Process using Model-based Data Augmentation [J].
Wu, Shuqiong ;
Nakao, Megumi ;
Tokuno, Junko ;
-Yoshikawa, Toyofumi Chen ;
Matsuda, Tetsuya .
2019 IEEE EMBS INTERNATIONAL CONFERENCE ON BIOMEDICAL & HEALTH INFORMATICS (BHI), 2019,
[43]   3D model retrieval based on multi-view attentional convolutional neural network [J].
An-An Liu ;
He-Yu Zhou ;
Meng-Jie Li ;
Wei-Zhi Nie .
Multimedia Tools and Applications, 2020, 79 :4699-4711
[44]   View-Based 3D Model Retrieval via Multi-graph Matching [J].
Weizhi Nie ;
Anan Liu ;
Yahui Hao ;
Yuting Su .
Neural Processing Letters, 2018, 48 :1395-1404
[45]   3D robotic navigation using a vision-based deep reinforcement learning model [J].
Zielinski, P. ;
Markowska-Kaczmar, U. .
APPLIED SOFT COMPUTING, 2021, 110
[46]   3D model retrieval based on multi-view attentional convolutional neural network [J].
Liu, An-An ;
Zhou, He-Yu ;
Li, Meng-Jie ;
Nie, Wei-Zhi .
MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (7-8) :4699-4711
[47]   View-Based 3D Model Retrieval via Multi-graph Matching [J].
Nie, Weizhi ;
Liu, Anan ;
Hao, Yahui ;
Su, Yuting .
NEURAL PROCESSING LETTERS, 2018, 48 (03) :1395-1404
[48]   3DInvNet: A Deep Learning-Based 3D Ground-Penetrating Radar Data Inversion [J].
Dai, Qiqi ;
Lee, Yee Hui ;
Sun, Hai-Han ;
Ow, Genevieve ;
Yusof, Mohamed Lokman Mohd ;
Yucel, Abdulkadir C. .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
[49]   A 3D reconstruction method based on multi-views of contours segmented with CNN-transformer for long bones [J].
Ge, Yunfei ;
Zhang, Qing ;
Shen, Yidong ;
Sun, Yuantao ;
Huang, Chongyang .
INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, 2022, 17 (10) :1891-1902
[50]   A 3D reconstruction method based on multi-views of contours segmented with CNN-transformer for long bones [J].
Yunfei Ge ;
Qing Zhang ;
Yidong Shen ;
Yuantao Sun ;
Chongyang Huang .
International Journal of Computer Assisted Radiology and Surgery, 2022, 17 :1891-1902
12345