煤矿智能化的核心是综采工作面的智能化，综采工作面智能化的关键是数字化。为了提高综采工作面的智能化水平，提出了“采煤就是采数据”的煤矿综采工作面智能化开采学术思想，凝练了数字工作面构建、精准截割、设备位姿检测与控制、设备群速度控制和设备群协同控制等五大关键技术，阐述了基于五大关键技术的学术思想内涵，构建了基于数字工作面智能开采的学术思想体系架构。针对综采工作面数字煤层构建问题，融合数字煤层数据、设备群数据等，利用空间插值算法、数字孪生技术等构建数字工作面，构建了包括数字煤层数据、历史截割位姿和速度数据、采煤量数据、设备群协同数据等的数据库，阐述了多源数据融合的数字工作面动态更新方法，提高数字工作面模型的精度；针对综采工作面精准截割问题，阐述了融合数字煤层驱动的截割轨迹规划数据和历史截割位姿数据的轨迹规划方法，以及基于规划轨迹数据的智能插补轨迹跟踪控制方法，利用人工智能算法对规划截割轨迹数据和轨迹跟踪控制的位姿插补数据进行迭代优化，提高截割轨迹规划和轨迹跟踪控制精度；针对综采工作面设备位姿检测与控制问题，阐述了基于多传感器融合数据的工作面装备位姿精准检测方法，以及基于神经网络算法的位姿控制方法，通过位姿感知数据和位姿控制数据的深度融合与迭代优化，实现综采工作面设备群位姿的精准检测与控制；针对综采工作面设备群速度控制问题，提出力−电耦合的截割载荷测量方法，以及基于人工智能寻优算法的速度智能控制方法，融合截割载荷数据和采煤量数据，利用人工智能寻优算法决策最优的牵引速度、截割速度、运煤速度，实现基于设备群速度匹配的高效智能截割控制；针对综采工作面设备群协同控制问题，阐述了基于人工智能算法的设备群主从协同控制方法，以采煤机位姿与速度控制数据作为主导者，刮板输送机和液压支架控制数据作为跟随者，利用人工智能神经网络算法求解最优的设备群位移与速度协同控制参数，实现设备群智能高效安全作业。“采煤就是采数据”五大关键技术，已经在煤矿中得到应用，验证了学术思想的可行性。“采煤就是采数据”的学术思想，为突破煤炭智能开采的关键技术难题奠定了理论基础。

The core of coal mine intelligence is the intelligence of comprehensive mining face, and the key to the intelligence of comprehensive mining face is digitalisation. In order to improve the intelligent level of comprehensive mining face, the academic idea of intelligent mining of comprehensive mining face of ‘coal mining is data mining’ is put forward, and five key technologies such as digital working face construction, precise cutting, equipment position detection and control, equipment group speed control and equipment group co-control are condensed, and the academic thought connotation of the idea based on the five key technologies is elaborated. It elaborates the connotation of academic ideas based on the five key technologies, and constructs the academic idea system architecture based on digital working face intelligent mining. With regard to the construction of the digital coal seam in the comprehensive mining face, it integrates the digital coal seam data, equipment group data, etc., and uses spatial interpolation algorithm and digital twin technology to construct the digital working face, constructs a database including digital coal seam data, historical cutting position and speed data, coal mining data, equipment group cooperative data, etc., and elaborates the dynamic updating method of the digital working face by integrating data from multiple sources, so as to improve the accuracy of the digital working face model. For the problem of accurate cutting in comprehensive mining face, the trajectory planning method that integrates the cutting trajectory planning data driven by digital coal seam and historical cutting position data, as well as the intelligent interpolation trajectory tracking control method based on the planning trajectory data are elaborated, and the artificial intelligence algorithm is used to carry out iterative optimization on the planning cutting trajectory data and the position interpolation data for trajectory tracking control, so as to increase the accuracy of the planning of the cutting trajectory and the control precision of the trajectory tracking. For the problem of detecting and controlling the position of the equipment in the comprehensive mining face, a precise detection method of the position of the equipment in the face based on the fusion of multi-sensor data and a position control method based on the neural network algorithm are elaborated, and the accurate detection and control of the position of the equipment group of the comprehensive mining face is achieved by the in-depth fusion of the position perception data and the position control data and iterative optimization; For the problem of controlling the speed of the equipment group of the comprehensive mining face, a force-electricity coupling method is proposed. For the speed control problem of the equipment group in the comprehensive mining face, the force-electricity coupling cutting load measurement method and the speed intelligent control method based on the artificial intelligence optimisation algorithm are proposed, which integrate the cutting load data and coal mining data, and use the artificial intelligence optimisation algorithm to make decisions on the optimal hauling speed, cutting speed and coal transporting speed, so as to realise the efficient and intelligent cutting control based on the speed matching of the equipment group. For the problem of cooperative control of equipment group in comprehensive mining face, the master-slave cooperative control method of equipment group based on artificial intelligence algorithm is elaborated, taking the position and speed control data of coal mining machine as the dominant, and the control data of scraper conveyor and hydraulic support as the follower, and solving the optimal cooperative control parameter of the displacement and speed of the equipment group by using the neural network algorithm of artificial intelligence, so as to realise the intelligent, efficient and safe operation of the equipment group. The five key technologies of ‘coal mining is data mining’ have been applied in coal mines, verifying the feasibility of the academic idea. The academic idea of ‘coal mining is data mining’ has laid an important theoretical foundation for breaking through the key technical problems of intelligent coal mining.