基于平行融合图Transformer的岩爆烈度等级预测
DOI:
作者:
作者单位:

1.安徽理工大学计算机科学与工程学院;2.安徽理工大学机械工程学院

作者简介:

通讯作者:

中图分类号:

U451.2

基金项目:

安徽理工大学青年基金(重点项目);淮南市指导性科技计划项目;国家自然科学基金面上项目;安徽省自然科学基金(面上项目);安徽省高等学校自然科学研究项目(重大项目),安徽省高校中青年教师培养行动项目;安徽理工大学医学专项培育项目(重大项目);合肥综合性国家科学中心大健康研究院职业医学与健康联合研究中心项)


Rockburst Intensity Level Prediction Based on Parallel Fusion Graph Transformer
Author:
Affiliation:

1.School of Computer Science and Engineering, Anhui University of Science &2.Technology

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    岩爆是地下深部工程中的一种破坏性极强的地质灾害,为准确预测岩爆烈度等级,提出了一种基于平行融合图Transformer(parallel fusion graph Transformer, PFGT)的岩爆烈度等级预测方法。首先,该方法利用岩爆数据在欧氏空间中的相似性结构关系构建图结构数据,并通过多重岩爆判据来约束岩爆数据在欧式空间中结构的畸变构建另一种图结构数据,通过平行训练获得岩爆数据的单尺度特征。其次,该方法设计了一种特征融合图Transformer策略,通过融合基于欧式空间和基于岩爆判据的两种图结构数据特征,获得岩爆数据的多尺度特征。该方法能够同时利用单尺度特征和多尺度特征,增强了数据表示能力,在训练过程中使用Transformer进行特征融合使得模型能够更全面地捕捉岩爆数据的优化特征,提升模型性能。通过与传统神经网络和其它机器学习算法相比,PFGT模型的预测准确率为94.87%,优于其它算法,证明了该算法的有效性,为岩爆等级预测提供了一种新的方法。

    Abstract:

    Rockburst is an extremely destructive geological disaster in deep underground engineering. In order to accurately predict the intensity level of rockburst, a method for rockburst intensity level prediction based on parallel fusion graph Transformer (PFGT) is proposed. Firstly, the similarity structure relationship of rockburst data in Euclidean space was utilized to construct graph-structured data. Besides, another kind of graph-structured data was constructed by utilizing multiple rockburst criteria to constrain the structural distortion of rockburst data in European space. Single-scale features of rockburst data was obtained through parallel training. Secondly, a feature fusion graph Transformer strategy was designed, which obtains multi-scale features of rockburst data by fusing two types of graph-structured data features based on Euclidean space and based on rockburst criteria. The method improves the data representation capability by simultaneously utilizing single-scale features and multi-scale features. During the training process, using Transformer for feature fusion enables the model to more comprehensively capture the optimized features of rockburst data, thus improving model performance. Compared with traditional neural networks and other machine learning algorithms, the prediction accuracy of the PFGT model is 94.87%, which is superior to other algorithms, proving the effectiveness of this algorithm and providing a new method for rockburst level prediction.

    参考文献
    相似文献
    引证文献
引用本文

高天祥,朱彦敏,樊腾悦,等. 基于平行融合图Transformer的岩爆烈度等级预测[J]. 科学技术与工程, , ():

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2024-04-22
  • 最后修改日期:2024-05-21
  • 录用日期:2024-06-05
  • 在线发布日期:
  • 出版日期:
×
亟待确认版面费归属稿件,敬请作者关注