School of Mechanical and Information Engineering,China University of Mining and Technology⁃Beijing
School of Informationand Control Engineering,China University of Mining and Technology
Jinneng Holding Group Changzhi company
Institute of Intelligent Mines & Robotics,China University of Mining and Technology⁃Beijing

构建煤矿智采工作面数字孪生系统需要挖掘“环-机-物”孪生体之间的隐含知识链和操作人员的决策控制经验,并建立虚实空间之间合理的信息交互方式。但是,物理空间与虚拟空间目前仅采用单一的被动信息交互机制。为解决生产运行控制与安全管理决策对开采过程不确定性的适应能力不足、虚拟空间对物理空间的综合管控鲁棒性不强、物理空间设备协同利用率不高等问题,提出一种新型的知识驱动虚实空间主动管控模式。构建了智采工作面五维数字孪生模型,并给出各个维度的具体含义;采用知识工程理论,给出智采工作面全工艺流程中的知识属性划分,建立3类先验知识的规则和模型表达;深入剖析“环-机-物”之间的多层次、多能流关联耦合关系,构建相应的知识动态演化模型;引入机器学习和决策优化方法,建立知识引导的虚实空间信息主动管控机制,从而形成数字孪生智采工作面的知识提取、知识迁移与知识利用新范式。通过提出的虚实空间新型主动管控模式,能够更好地应对煤矿地质条件的不确定性、开采环境的时空动态性,以及开采过程设备群的多样性,为煤矿高效、低碳的智能化开采提供技术支撑,实现平行矿山建设中的“信息可见、轨迹可循、状态可查”提供知识层面的高保真映射框架和决策控制机制。

In the previous digital twin system of smart coal mining face,the knowledge chain embedded in ‘environ⁃ment⁃equipment⁃material’ twins is not fully excavated, and the experiences of operators for determining andcontrolling the mining operation are not exploited. Especially,a rational information interaction mode between physicalspace and virtual space is necessary. However,a signal passive information interaction method is now employed. All a⁃bove weaknesses lead to the inefficient adaptability of operation control and safety decision⁃making for the uncertaintyof mining process,and the poor robustness of comprehensive control from virtual space to physical space,even the lowutilization of cooperative physical entities. To address the above issues,a new active control and management mode forvirtual spaces is proposed to deeply mining and utilizing knowledge from smart intelligent face with digital twin. Thefive⁃dimensional digital twin framework of smart mining face is constructed. The specific meaning of each dimension isillustrated in detail. Following that,the knowledge is classified in terms of their attributes along the whole process ofsmart mining face. More especially,three kinds of prior knowledge are described by rules and models. After analy⁃zing coupling relationship among multi⁃energy flows of ‘ environment⁃machine⁃thing’,the dynamic evolution modelof twin knowledge is built. Finally, a knowledge⁃guided active control mechanism for virtual and real spatialinformation is developed. It is solved by machine learning and optimization methods,which provides a new paradigm ofextracting,transferring and utilizing knowledge in the digital twin smart mining face. The proposed new activecontrol mode can cope with the uncertainty of geological conditions, the spatio⁃temporal dynamics of environmentand the diversity of equipment during the mining process. This provides a technical support for the efficient low⁃carbonintelligent mining,and the high⁃fidelity mapping framework and decision⁃making control mechanism at the knowledgelevel to promote “information visible,track traceable and state traceable”in parallel mine.

国家自然科学基金资助项目(61973305,52121003);国家重点研发计划资助项目(2022YFB4703701)

郭一楠,杨帆,葛世荣,等. 知识驱动的智采数字孪生主动管控模式[ J]. 煤炭学报,2023,48( S1):334-344.

GUO Yinan,YANG Fan,GE Shirong,et al.Novel knowledge⁃driven active management and control scheme ofsmart coal mining face with digital twin [J]. Journal of China Coal Society,2023,48(S1):334-344