针对采用理想化信号模拟滚筒受载进行采煤机调高液压系统性能分析准确性差、基于传统 优化控制算法难以实现对采煤机滚筒调高的自适应控制、响应速度和跟踪性能不好等问题，提出一 种基于深度确定性策略梯度算法 DDPG(Deep Deterministic Policy Gradient)的采煤机滚筒自适应调 高控制策略，并利用虚拟样机技术、深层卷积神经网络( DCNN) 与深度强化学习等机器学习算法搭 建了采煤机自适应调高机-液-控一体化系统。 利用 Pro / E 及 RecurDyn 建立采煤机调高系统刚柔 耦合动力学仿真模型，根据某采煤工作面实际赋存条件，利用 EDEM 建立离散元煤壁模型，基于 DEM-MFBD 接口构建 EDEM-RecurDyn 双向耦合调高机构机械系统模型，基于 AMEsim 建立调高 机构液压系统模型，利用 Simulink 搭建了集信号处理模块(Signal processing)、时频谱图生成模 块(Continuous wavelet transform System)、数据样本扩充模块(Fancy PCA System)、截割状态识别模 块(Alexnet Transfer Learning System)、调高控制决策模块(Height Control decision)和 DDPG 高度调 节模型模块(DDPG Height Adjustment Model)6 个模块于一体的采煤机自适应调高控制系统模型， 基于接口技术搭建 EDEM-RecurDyn-AMEsim-Simulink 多领域协同仿真的采煤机自适应调高机- 液-控一体化系统模型。 利用该系统模型进行仿真并对其调高性能分析，研究结果表明:基于连续 小波变换、Fancy PCA 和 Alexnet 网络迁移学习能够实现煤岩截割状态的精准识别，识别准确率可 达95.58%，所搭建系统的仿真过程能够更真实地模拟采煤机截割煤岩破碎过程，系统仅经 0.6 s 左 右即能感知到截割工况的变化，且能够快速识别出煤岩截割状态并准确地将滚筒调整至目标高度， 响应速度快，能够根据工况变化自适应调节活塞运动速度;相比于模糊 PID 控制，基于 DDPG 控制 的采煤机自适应调高系统的活塞缩回位移稳态误差最大仅为 0.002 1 mm，为前者的 0.66%;对比调 高前后稳定阶段的控制性能，模糊 PID 控制的系统活塞运动速度和液压缸腔室流量波动显著增 大，而 DDPG 控制的系统则差别较小，表明后者具备更强的自适应性，更适于复杂煤层赋存条件下 采煤机调高液压系统的自适应控制;通过试验验证了采煤机自适应调高控制策略及仿真结果的正 确性，可有效提高采煤机对复杂煤层的适应性，促进煤矿智能化的发展进程。

In view of the poor accuracy of performance analysis of shearer drum height adjustment hydraulic system by using idealized signal to simulate drum load， it is difficult to realize self⁃adaptive control of shearer drum height ad⁃ justment， poor response speed and tracking performance based on traditional optimization control algorithm.A self⁃ adaptive height adjustment control strategy of shearer drum based on depth deterministic gradient algorithm DDPG is proposed，and using virtual prototype technology， deep convolutional neural network and deep reinforcement learning and other machine learning algorithms to build an integrated hydraulic control system for shearer self⁃adaptive height adjustment.The rigid flexible coupling dynamic simulation model of shearer height adjustment system is established by using Pro / E and RecurDyn. According to the actual occurrence conditions of a coal face， the discrete coal wall model is established by using EDEM， the mechanical system model of EDEM⁃RecurDyn bi⁃directional coupling height ad⁃ justment mechanism is constructed based on DEM⁃MFBD interface， and the hydraulic system model of height adjust⁃ ment mechanism is established based on AMESim. A self⁃adaptive height adjustment control system model of shearer is built by using Simulink， which integrates six modules: signal processing module(Signal processing)， time spec⁃ trum diagram generation module(Continuous wavelet transform System)， data sample expansion module(Fancy PCA System)， cutting state identification module(Alexnet Transfer Learning System)， height adjustment control deci⁃ sion module(Height Control decision) and DDPG height adjustment model module(DDPG Height Adjustment Model). Based on the interface technology， the integrated hydraulic control system model of shearer self⁃ adaptive height regulator based on EDEM⁃RecurDyn⁃AMESim⁃Simulink multi domain collaborative simulation is built. The system model is used to simulate and analyze its height adjustment performance. The research results show that the accurate identification of coal and rock cutting state can be realized based on continuous wavelet transform， fancy PCA and Alex net network transfer learning，and the recognition accuracy rate can reach 95.58%.The simulation process of the built system can more truly simulate the coal and rock cutting and crushing process of the shearer. The sys⁃ tem can perceive the change of the cutting working condition after only about 0.6 s， quickly identify the coal and rock cutting state， accurately adjust the drum to the target height， and has fast response speed， It can adaptively ad⁃ just the piston speed according to the change of working conditions.Compared with fuzzy PID control， the maximum steady⁃state error of piston retraction displacement of self⁃adaptive height adjustment system of shearer based on DDPG control is only 0.002 1 mm， only 0.66% of the former. Compared with the control performance in the stable stage before and after height adjustment， the fluctuation of piston movement speed and hydraulic cylinder chamber flow of fuzzy PID control system increases significantly， while the difference of DDPG control system is small， It shows that the latter has stronger adaptability and is more suitable for the self⁃adaptive control of shearer height adjust⁃ ment hydraulic system under the condition of complex coal seam.The test verifies the feasibility and correctness of the shearer’s adaptive height adjustment control strategy and simulation results， which effectively improves the shearer’s adaptability to complex coal seams and promotes the development of coal mine intelligence.