• 论文
主办单位:煤炭科学研究总院有限公司、中国煤炭学会学术期刊工作委员会
基于深度学习的大采高工作面矿压预测分析及模型泛化
  • Title

    Deep learning prediction and model generalization of ground pressure for deep longwall face with large mining height

  • 作者

    赵毅鑫杨志良马斌杰宋红华杨东辉

  • Author

    ZHAO Yixin,YANG Zhiliang,MA Binjie,SONG Honghua,YANG Donghui

  • 单位

    中国矿业大学(北京) 共伴生能源精准开采北京市重点实验室中国矿业大学(北京) 能源与矿业学院

  • Organization
    Beijing Key Laboratory for Precise Mining of Intergrown Energy and Resources,China University of Mining & Technology (Beijing); School of Energy & Mining Engineering,China University of Mining & Technology (Beijing)
  • 摘要

    综采工作面矿压显现的分析与预测对于复杂地质下工作面顶板管理,保证矿井生产安全具有重要意义。采用关系型数据库储存液压支架工作阻力数据以及利用工作面推进过程中矿压显现的时序特性,采用SQL语言,运用长短时记忆网络(Long Short Time Memory,LSTM)深度学习方法,以红庆河矿31101大采高综采工作面矿压规律为研究对象,对工作面支架工作阻力、支架不平衡力、支架安全阀开启情况及初次来压与周期来压等矿压显现规律进行分析;基于建立的数据库,预测了红庆河大采高工作面矿山压力,预测结果表明LSTM方法较BP神经网络预测更具准确性。为进一步讨论本研究采用的LSTM网络模型的泛化能力,在采用布尔台42103大采高工作面、上湾矿12401大采高工作面少量矿压数据的前提下,使用迁移学习方法,对矿压数据进行预测检验,结果表明:LSTM模型具有很好的泛化能力,相比于不使用迁移学习方法,迁移学习可提高模型的泛化能力。最后,探讨了模型在3个大采高工作面矿压预测表现的差别,发现数据量本身对模型预测行为影响较大,增大数据量可弥补原始数据缺失等问题。在预测模型基础上设计了周期来压预警模型,集成形成相应矿压分析与预警系统,经工程验证判定预警系统分析效果良好。

  • Abstract

    The analysis and prediction of the mining pressure in the fully mechanized mining face is of great signifi- cance for managing the roof of the working face under complex geology and ensuring the safety of mine production. In this paper,a relational database is used to store the mine pressure data generated by the hydraulic support and the time series characteristics of mine pressure during the process of working face advance. The Long Short Time Memory (LSTM) deep learning method is used to study the mining pressure law of Hongqinghe 31101 fully mechanized mining face. The support working resistance,the unbalanced pressure of support,the state of safety valve and the initial pres- sure,and the periodic pressure are analyzed. Based on the established database,the mine pressure of the working face is predicted. The prediction results show that the LSTM method has high accuracy compared with Back Propagation (BP) model. In order to discuss the generalization ability of the LSTM network model used in this study,based on a small amount of data obtained,the transfer learning method is used to predict and verify the mine pressure of the Buer- tai 42103 working face and the 12401 working face of the Shangwan Mine. The verification results show that the meth- od adopted in this study has a good generalization ability. The transfer learning can improve the generalization ability of the model. Finally,in order to improve the accuracy of the model,the large differences in the prediction performance of the model in the three working faces are discussed. It is found that the data itself have a great influence on the behav- ior of the model. Increasing the amount of data can make up for some of the original data itself. Finally,on the basis of the prediction model,a periodic weighting early warning model is designed,and the corresponding mine pressure analy- sis and early warning system is integrated. The results are verified by the in-situ engineering data.

  • 关键词

    大采高长壁开采深度学习矿压分析迁移学习

  • KeyWords

    large mining height,longwall mining,deep learning,mine pressure analysis,transfer learning

  • 基金项目(Foundation)
    国家自然科学基金资助项目(51874312,U1910206);国家重点研发计划资助项目(2016YFC0801401)
  • 文章目录

    1 矿压分析与预测模型

       1.1 工程背景

       1.2 数据库的建立

       1.3 预测网络模型构建

       1.4 预测模型数据处理

    2 工作面矿压分析与预测

       2.1 工作面矿压观测及分析

       2.2 基于LSTM模型的工作面矿压预测

    3 预测模型泛化

       3.1 迁移学习的引入

       3.2 泛化模型训练

    4 预警系统开发及工程验证

       4.1 矿压分析与预警系统搭建

       4.2 周期来压预警功能及工程验证

    5 结论

  • DOI
  • 引用格式
    赵毅鑫,杨志良,马斌杰,等. 基于深度学习的大采高工作面矿压预测分析及模型泛化[J]. 煤炭学报,2020,45(1):54-65.
  • Citation
    ZHAO Yixin,YANG Zhiliang,MA Binjie,et al. Deep learning prediction and model generalization of ground pressure for deep longwall face with large mining height [ J]. Journal of China Coal Society,2020,45 (1):54 - 65.
  • 相关专题
  • 图表
相关问题

主办单位:煤炭科学研究总院有限公司 中国煤炭学会学术期刊工作委员会

©版权所有2015 煤炭科学研究总院有限公司 地址:北京市朝阳区和平里青年沟东路煤炭大厦 邮编:100013
京ICP备05086979号-16  技术支持:云智互联