近年来，我国综采工作面智能化快速发展，但是掘进工作面自动化程度不高，生产效率低，导致“采掘失衡”问题依然严峻。目前掘进装备轨迹规划和自动截割方面的研究不足，大多施工过程仍需工人在井下对设备进行手动操控完成，极易造成超挖、欠挖，影响巷道断面成形质量，且存在安全隐患。结合数字孪生、虚拟现实和碰撞检测等技术，论文提出了一种数字孪生驱动的悬臂式掘进机记忆截割控制方法，对掘进机虚拟示教轨迹规划和示教轨迹跟踪控制等关键技术进行研究，为少人甚至无人掘进工作面奠定理论和技术基础。

针对传统记忆截割井下人工示教困难，易发生超挖、欠挖，示教截割轨迹规划精度过度依赖工人经验等问题，提出了复杂工况环境下的掘进机虚拟示教轨迹规划方法。从几何模型、物理模型、行为模型、规则模型四个层次建立虚拟示教机理模型，基于Unity3D平台，通过人机交互的方式并结合工人经验，设计示教截割轨迹，记录轨迹关键点数据信息，使其作为记忆自动截割阶段轨迹跟踪的目标跟踪轨迹。

针对掘进机在井下复杂恶劣环境中控制难的问题，提出了基于迭代学习与滑膜控制相结合的轨迹跟踪控制方法。通过拉格朗日法建立掘进机截割部动力学模型，并设计迭代滑膜轨迹跟踪控制器，以“虚拟示教”所获得的轨迹作为控制器输入，构建基于机身和截割部位姿为反馈的巷道成形轨迹跟踪闭环控制系统，实现末端执行器——截割头对示教轨迹的精确跟踪，从而保证断面成形质量。

构建了掘进机记忆截割控制数字孪生模型，通过“虚拟工作面环境及虚拟样机模型建立、物理空间状态感知、孪生数据交互”将现实物理井下掘进工作面空间环境和设备实时状态映射在数字化的虚拟空间中，使掘进机运行状态透明化。开发数字孪生驱动的掘进机记忆截割控制平台，将轨迹规划与轨迹跟踪控制算法集成到系统中，以“虚拟示教记忆截割”的巷道断面成形截割新模式，在虚拟端实现示教轨迹的规划和记忆自动截割控制指令的生成和下发。

最后，搭建系统实验平台，分别对系统数据通讯性能、虚实一致性和同步性、虚拟示教轨迹规划功能、示教轨迹跟踪再现性能以及系统最终运行性能进行测试与验证。结果表明，系统数据通讯性能良好，能够保证虚实一致性和同步性，能够实时、准确对超、欠挖和异常碰撞情况进行检测和预警，虚拟示教轨迹规划方法能够保证截割轨迹的合理性和最优化，且示教轨迹跟踪控制精度满足实际使用要求。与传统掘进机记忆截割技术相比，该方法通过人机交互的方式，提高了示教过程的安全性，结果的合理性，轨迹规划的灵活性，以及示教轨迹跟踪控制精度，从而提高巷道断面成形质量和掘进效率，为掘进设备记忆截割与智能化控制提供了新的思路。

In recent years, China has witnessed its rapid development in the mechanized mining face, but there is still the relatively low automation degree of heading face and the production efficiency, leading to the serious problem of “mining imbalance”. At present, the research on trajectory planning and automatic cutting of tunneling equipment is insufficient. Most of the construction processes still require workers to manually control the equipment underground, which can easily cause over-excavation and under-excavation, affect the quality of roadway section forming, and have potential safety hazards. Combining with digital twin, virtual reality, collision detection and other technologies, this paper proposes a memory cutting control method of cantilever roadheader driven by digital twin, and studies the key technologies such as virtual teaching trajectory planning and teaching trajectory tracking control of roadheader, which lays a theoretical and technical foundation for few or even unmanned tunneling face.

In response to the difficulties of manual teaching of traditional memory cutting underground, the susceptibility to over excavation and under excavation, and over-reliance on workers’ experience in teaching cutting trajectory planning accuracy, a virtual teaching trajectory planning method for roadheader under complex working conditions is proposed. The virtual teaching mechanism model is established from four levels: geometric model, physical model, behavior model and rule model. Based on Unity3D platform, through human-computer interaction and combined with workers ' experience, the teaching cutting trajectory is designed, and the key point data information of the trajectory is recorded, which is used as the target tracking trajectory of the trajectory tracking in the memory automatic cutting stage.

In response to the difficulty of difficult control of roadheader in complex and harsh underground environment, a trajectory tracking control method based on iterative learning and sliding mode control is proposed. The dynamic model of the cutting part of the roadheader is established by Lagrange method, and the iterative synovial trajectory tracking controller is designed. The trajectory obtained by ' virtual teaching ' is used as the input of the controller, and the closed-loop control system of the roadway forming trajectory tracking based on the posture of the fuselage and the cutting part is constructed to realize the accurate tracking of the teaching trajectory by the end effector-cutting head, so as to ensure the forming quality of the section.

The digital twin model of memory cutting control of roadheader is constructed. Through the establishment of virtual working face environment and virtual prototype model, physical space state perception, twin data interaction, the space environment of real physical underground tunneling working face and the real-time state of equipment are mapped in the digital virtual space to make the operation state of roadheader transparent. The memory cutting control platform of roadheader driven by digital twin is developed, and the trajectory planning and trajectory tracking control algorithm are integrated into the system. The new mode of roadway section forming and cutting of ' virtual teaching memory cutting ' is used to realize the planning of teaching trajectory and the generation and distribution of memory automatic cutting control instructions on the virtual end.

Finally, the system experimental platform is built to test and verify the system’s data communication performance, virtual and real consistency and synchronization, virtual teaching trajectory planning function, teaching trajectory tracking reproduction performance and system final operation performance. The results show that the system has good data communication performance, can ensure the consistency and synchronization of virtual and real, and can detect and warn the overbreak, underbreak and abnormal collision in real time and accurately. The virtual teaching trajectory planning method can ensure the rationality and optimization of the cutting trajectory, and the tracking control accuracy of the teaching trajectory meets the actual use requirements. Compared with the traditional roadheader memory cutting technology, this method improves the safety of the teaching process, the rationality of the results, the flexibility of the trajectory planning, and the accuracy of the teaching trajectory tracking control through the way of human-computer interaction, so as to improve the roadway section forming quality and tunneling efficiency, and provide a new idea for the memory cutting and intelligent control of tunneling equipment.

[1] 国家能源集团.《国家能源集团煤矿智能化建设指南（试行）》[Z].2021-02-09.

[2] 王虹,王步康,张小峰,等.煤矿智能快掘关键技术与工程实践[J].煤炭学报,2021,46(7): 2068-2083.

[3] 王国法,任怀伟,庞义辉,等.煤矿智能化(初级阶段)技术体系研究与工程进展[J].煤炭科学技术,2020,48(7):1-27.

[4] 张帆,葛世荣,李闯.智慧矿山数字孪生技术研究综述[J].煤炭科学技术,2020,48(7):168-176.7.

[5] 陶飞,张辰源,张贺,等.未来装备探索：数字孪生装备[J].计算机集成制造系统,2022,28(1):1-16.

[6] 丁恩杰,俞啸,夏冰,等.矿山信息化发展及以数字孪生为核心的智慧矿山关键技术[J].煤炭学报,2022,47(1):564-578.

[7] 张辰源,陶飞.数字孪生模型评价指标体系[J].计算机集成制造系统,2021,27(08):2171-2186.

[8] 陶飞,马昕,戚庆林,等.数字孪生连接交互理论与关键技术[J].计算机集成制造系统,2023,29(01):1-10.

[9] 葛世荣,张帆,王世博,等.数字孪生智采工作面技术架构研究[J].煤炭学报, 2020,45(06): 1925-1936.

[10] 葛世荣,胡而已,李允旺.煤矿机器人技术新进展及新方向[J/OL].煤炭学报:1-25[2023-02-22].

[11] 张旭辉,张超,王妙云,等.数字孪生驱动的悬臂式掘进机虚拟操控技术[J].计算机集成制造系统,2021,27(06):1617-1628.

[12] 王妙云,张旭辉,马宏伟,等.远程控制综采设备碰撞检测与预警方法[J].煤炭科学技术, 2021,49(09):110-116.

[13] 张旭辉,魏倩楠,王妙云,等.悬臂式掘进机远程虚拟操控系统研究[J].煤炭科学技术, 2020,48(11):44-51.

[14] 张旭辉,董润霖,马宏伟,等.基于虚拟现实的煤矿救援机器人远程控制技术[J].煤炭科学技术,2017,45(05):52-57.

[15] Grieves M. Digital twin: manufacturing excellence through virtual factory replication[J]. White paper, 2014, 1(2014): 1-7.

[16] 刘大同,郭凯,王本宽,等.数字孪生技术综述与展望[J].仪器仪表学报,2018, 39(11):1-10.

[17] 戴晟,赵罡,于勇,等.数字化产品定义发展趋势:从样机到孪生[J].计算机辅助设计与图形学报,2018,30(08):1554-1562.

[18] 陶飞,张辰源,张贺,等.未来装备探索:数字孪生装备[J].计算机集成制造系统,2022, 28(01):1-16.

[19] Wang YC, Tao F, Zhang M, et al. Digital twin enhanced fault prediction for the autoclave with insufficient data[J]. Journal of Manufacturing Systems, 2021, 60(2021): 350-359.

[20] 陶飞,张贺,戚庆林,等.数字孪生模型构建理论及应用[J].计算机集成制造系统,2021, 27(01):1-15.

[21] 侯正航,何卫平.基于数字孪生的飞机装配状态巡检机器人的建模与控制[J].计算机集成制造系统,2021,27(04):981-989.

[22] Gao Y, Chang D, Chen C H, et al. Design of digital twin applications in automated storage yard scheduling[J]. Advanced Engineering Informatics, 2022, 51: 101477.

[23] 李灿,侯兴明,祁启明,等.基于数字孪生的无人机平行作战仿真[J/OL].火力与指挥控制:1-8[2023-03-15].

[24] 汪浩,刘树青,贾茜等.基于数字孪生的数控机床自动上下料系统设计[J].机械制造与自动化,2021,50(04):101-103.

[25] 张帆,葛世荣.矿山数字孪生构建方法与演化机理[J].煤炭学报,2023,48(01):510-522.

[26] 张旭辉,杨文娟,薛旭升,等.煤矿远程智能掘进面临的挑战与研究进展[J].煤炭学报,2022,47(01):579-597.

[27] 杨健健,张强,吴淼,等.巷道智能化掘进的自主感知及调控技术研究进展[J].煤炭学报,2020,45(6):2045-2055.

[28] 张帆,王世雄,田睿芳.基于数字孪生的智能安全煤场管控系统设计[J].煤矿机械,2022,43(07):1-4.

[29] 张旭辉,吕欣媛,王甜,等.数字孪生驱动的掘进机器人决策控制系统研究[J].煤炭科学技术,2022,50(7):36-49.

[30] 李娟莉,沈宏达,谢嘉成,等.基于数字孪生的综采工作面工业虚拟服务系统[J].计算机集成制造系统,2021,27(02):445-455.

[31] 吴淼,李瑞,王鹏江,等.基于数字孪生的综掘巷道并行工艺技术初步研究[J].煤炭学报,2020,45(S1):506-513.

[32] 陈伟华,南鹏飞,闫孝姮,等.基于深度学习的采煤机截割轨迹预测及模型优化[J].煤炭学报,2020,45(12):4209-4215.

[33] 樊启高,李威,王禹桥,等.一种采用灰色马尔科夫组合模型的采煤机记忆截割算法[J].中南大学学报(自然科学版),2011,42(10):3054-3058.

[34] 王忠宾,徐志鹏,董晓军.基于人工免疫和记忆切割的采煤机滚筒自适应调高[J]煤炭学报,2009,34(10):1405-1409.

[35] 郭卫,薛红梅,王渊.基于Elman神经网络的采煤机自动调高控制策略研究[J].煤矿机械,2014,35(01):50-52.

[36] 王苏彧.悬臂式掘进机记忆截割及自动截割控制方法研究[D].中国矿业大学（北京）,2014.

[37] 王苏彧,田劼,吴淼.纵轴式掘进机截割轨迹规划及边界控制方法研究[J].煤炭科学技术,2016,44(4):89-94+118.

[38] 王苏彧,吴淼.基于PCC的纵轴式掘进机自主截割控制系统研究[J].煤炭工程,2016,48(6):132-135.

[39] 田劼,杨阳,陈国强,等.悬臂掘进机巷道自动截割成形控制方法的探索[J].煤炭工程,2008(12):83-85.

[40] 张德义,刘送永,贾新庆,等.基于红外热像的夹矸巷道断面记忆截割试验研究[J].煤炭学报,2021,46(10):3377-3385.

[41] 杨文娟,张旭辉,张超,等.悬臂式掘进机器人巷道成形智能截割控制系统研究[J].工矿自动化,2019,45(09):40-46.

[42] 杨士伟.悬臂式掘进机记忆截割及自动截割控制方法研究[J].机电工程技术,2021,50(02):196-198.

[43] 王福忠,张付凯.掘进机器人巷道断面记忆截割控制策略研究[J].计算机测量与控制,2014,22(03):737-740.

[44] 张爱红,张秋菊.基于虚拟现实技术的机器人示教方法[J].江南大学学报,2003(03):258-261.

[45] Aleotti J, Caselli S, Reggiani M. Leveraging on a virtual environment for robot programming by demonstration[J]. Robotics and Autonomous Systems, 2004, 47(2-3): 153-161.

[46] 李东阳,谢海龙,王清辉,等.基于力反馈的机器人砂带磨削虚拟示教轨迹规划方法[J].现代制造工程,2022,No.500(05):30-35.

[47] 潘俊浩,卓勇,侯亮,等.一种基于Unity3d的工业机器人示教系统设计方法[J].组合机床与自动化加工技术,2017,No.521(07):110-115.

[48] Fang H C, Ong S K, Nee A Y C. A novel augmented reality-based interface for robot path planning[J]. International Journal on Interactive Design and Manufacturing (IJIDeM), 2014, 8: 33-42.

[49] Chen L, Wei Z, Zhao F, et al. Development of a virtual teaching pendant system for serial robots based on ROS-I[C]//2017 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE Conference on Robotics, Automation and Mechatronics (RAM). IEEE, 2017: 720-724.

[50] Meza J L, Santibanez V, Soto R, et al. Fuzzy self-tuning PID semiglobal regulator for robot manipulators[J]. IEEE Transactions on Industrial Electronics, 2012, 59(6): 2709-2717.

[51] Wang H. Adaptive control of robot manipulators with uncertain kinematics and dynamics[J]. IEEE Transactions on Automatic Control, 2016, 62(2): 948-954.

[52] 李小华,杨瑞芳,刘辉,等.一类机械臂系统自适应有限时间有界[H]跟踪控制[J].控制理论与应用，2021,38(1):147-156.

[53] 刘金棍.滑模变结构控制MATLAB仿真[M].清华大学出版社，2015.

[54] 刘凌,李志成,张莹.面向双关节机械臂的参数可调RBF神经网络控制[J].西安交通大学学报，2021,55(4):1-7.

[55] Fan Y, An Y, Wang W, et al. TS fuzzy adaptive control based on small gain approach for an uncertain robot manipulators[J]. International Journal of Fuzzy Systems, 2020, 22(3): 930-942.

[56] Fu X, Peng J. Iterative learning control for UAVs formation based on point-to-point trajectory update tracking[J]. Mathematics and Computers in Simulation, 2023, 209: 1-15.

[57] 谢苗,李玉岐,侯文博,等.掘支锚联合机组双截割部截割轨迹控制方法[J].辽宁工程技术大学学报(自然科学版),2019,38(04):339-344.

[58] 王福忠,高颖.矿井巷道掘进机截割头运行轨迹跟踪策略[J].计算机仿真,2016,33(05):285-289.

[59] Maeda G J, Manchester I R, Rye D C. Combined ILC and disturbance observer for the rejection of near-repetitive disturbances, with application to excavation[J]. IEEE Transactions on Control Systems Technology, 2015, 23(5): 1754-1769.

[60] 张卉,朱永飞,刘雪飞,等.基于模糊迭代Q-学习的冶金工业机器人轨迹跟踪控制研究[J].工程设计学报,2022,29(05):564-571.

[61] 李志文,程志江,杜一鸣.优化自抗扰的移动清洁机械臂轨迹跟踪控制[J/OL].计算机集成制造系统:1-14[2023-03-18].

[62] 王刚,宋英杰,唐武生,等.基于迭代学习的三自由度机械臂轨迹跟踪控制[J].吉林大学学报(信息科学版),2021,39(04):389-396.

[63] 韩俊庆,吴爱国,董娜.基于滑模干扰观测器的机械臂终端滑模控制[J].中南大学学报(自然科学版),2020,51(10):2749-2757.

[64] 高为炳著.变结构控制理论及实现方法[M].北京：科学出版社，1998.