Optimal orepass selection model based on graph neural network

被引：0
|
作者：
Qiao, Haiqing [1 ,2 ,3 ,4 ]
Lü, Xiao [1 ,2 ,3 ,4 ]
Zhang, Yuansheng [1 ,2 ,3 ,4 ]
Li, Ruoxi [1 ,2 ,3 ,4 ]
Wang, Xianlong [1 ,2 ,3 ,4 ]
机构：
[1] BGRIMM Technology Group, Beijing,102628, China
[2] Beijing Key Laboratory of Nonferrous Intelligent Mining Technology, Beijing,102628, China
[3] State Key Laboratory of Automatic Control Technology for Mining and Metallurgy Process, Beijing,102628, China
[4] BGRIMM Intelligent Technology, Beijing,102628, China
来源：
Gongcheng Kexue Xuebao/Chinese Journal of Engineering | 2024年 / 46卷 / 12期
关键词：
Overdependence on manual experience frequently leads to the irrational selection of orepass. Therefore; a scheduling model needs to be established to make sound decisions on orepass selection; increase the efficiency of underground rail transport; and improve production efficiency in metal mines. In this study; the −495 level of the Baixiangshan iron mine in Anhui Province is used as a research object. Orepass information; tunnel information; and historical mining; loading; and transporting data are collected. The data are then preprocessed to obtain a 130-order matrix that can describe the rail transit topology. Several vectors containing road/orepass basic information; road/orepass trajectory information; and orepass chronological material-level information are used for model training and validation. Time-series transformer graph convolutional network; which is denoted as T-TransGCN; is a temporal graph neural network that integrates orepass features; road features; and rail topology information. T-TransGCN is proposed to determine the optimal orepass selection. It enhances performance through splitting temporal features; fine-tuning the pooling layer architecture; and embedding edge features. Validated results show that (1) the T-TransGCN model is better than the Time-series multi-layer perceptron (T-MLP) and the Time-series graph convolutional network (T-GCN). The label accuracy; F1; score; and Top-3 accuracy of T-TransGCN improve by 7.33%; 17.00%; and 14.26% compared with those of T-MLP; which indicates that T-TransGCN can effectively integrate node attributes and topology information. Moreover; T-TransGCN has a relatively higher number of model parameters; more complex model structure; greater stability; and stronger fitting capability than T-GCN. (2) The addition of chronological material-level features to T-TransGCN increases its F1 score and Top-3 accuracy by 11.75% and 17.02%; while the addition of trajectory features improves them by 11.83% and 10.01%. Both new data preprocessing methods are effective in enhancing the generalization ability of T-TransGCN. The chronological material-level features help T-TransGCN understand the recent state of orepass; while the trajectory features reflect the importance of different orepasses dynamically. The trajectory features help the model understand structural information; such as the similarity of adjacent nodes or the similarity of forked nodes. (3) The addition of edge features further distinguishes orepass nodes from road nodes. The optimization of the outputs of the pooling layer helps avoid the distraction of unimportant information. When chronological features are split; the F1 score and Top-3 accuracy of T-TransGCN improve by 15.94% and 12.34%. This increment enhances the focus of the model on the chronological material-level information. The integration of the abovementioned model improvements further increases the fitting capability; generalization ability; and stability of T-TransGCN. © 2024 Science Press. All rights reserved;
D O I：
10.13374/j.issn2095-9389.2024.01.17.003
中图分类号：
学科分类号：
摘要：
引用
收藏
页码：2169 / 2180
相关论文
共 50 条
  • [21] Optimal fusion operator selection - A neural network technique based approach
    Chebira, A
    Madani, K
    APPLICATIONS AND SCIENCE OF COMPUTATIONAL INTELLIGENCE, 1998, 3390 : 451 - 460
  • [22] Functional graph model of a neural network
    Podolak, IT
    IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 1998, 28 (06): : 876 - 881
  • [23] Model Selection Using Graph Neural Networks
    Napoles, Gonzalo
    Grau, Isel
    Guven, Cicek
    Salgueiro, Yamisleydi
    INTELLIGENT SYSTEMS AND APPLICATIONS, VOL 2, INTELLISYS 2024, 2024, 1066 : 332 - 347
  • [24] Hierarchical Model Selection for Graph Neural Networks
    Oishi, Yuga
    Kaneiwa, Ken
    IEEE ACCESS, 2023, 11 : 16974 - 16983
  • [25] AN INFORMATION CRITERION FOR OPTIMAL NEURAL NETWORK SELECTION
    FOGEL, DB
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 1991, 2 (05): : 490 - 497
  • [26] Robust Graph Neural Network based on Graph Denoising
    Tenorio, Victor M.
    Rey, Samuel
    Marques, Antonio G.
    FIFTY-SEVENTH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, IEEECONF, 2023, : 578 - 582
  • [27] Graph neural network based on graph kernel: A survey
    Xu, Lixiang
    Peng, Jiawang
    Jiang, Xiaoyi
    Chen, Enhong
    Luo, Bin
    PATTERN RECOGNITION, 2025, 161
  • [28] Bayesian Graph Convolutional Neural Network based Patent Valuation Model
    Liu, Weidong
    Liu, Xin
    Qiao, Wenbo
    2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
  • [29] A Dilated Recurrent Neural Network-Based Model for Graph Embedding
    Han, Xiao
    Zhang, Chunhong
    Ji, Yang
    Hu, Zheng
    IEEE ACCESS, 2019, 7 : 32085 - 32092
  • [30] External information enhancing topic model based on graph neural network
    Song, Jie
    Lu, Xiaoling
    Hong, Jingya
    Wang, Feifei
    EXPERT SYSTEMS WITH APPLICATIONS, 2025, 263
12345