自适应截割技术是实现采煤机智能化的核心技术，对提升煤矿开采效率、提高安全性和资源利用率具有重要作用。因此，开展了自适应截割技术的综述研究，重点探讨了其技术原理及应用现状。根据核心功能和技术目标，将采煤机自适应截割技术划分为记忆截割、透明地质、煤岩识别和自适应控制4个研究内容。记忆截割通过记录历史数据来优化采煤路径，透明地质利用综合探测技术获取实时地质信息，煤岩识别技术根据不同的识别原理，可以分为基于物理参数的间接法、基于视觉的直接法、以及探地雷达和超声波等基于波动特性的探测法，以实现煤岩界面或煤岩性质的精确识别，自适应控制则通过自动化调节采煤机的运行参数。这些技术从多个角度提升了采煤机的智能化水平。然而，由于煤层地质条件及恶劣开采环境的影响，现有技术在适应性和经济性方面存在一些局限性。因此，针对未来采煤机自适应截割技术的发展趋势，提出了以下建议：促进记忆截割、透明地质与煤岩识别技术的融合，以实现更高效的煤层信息获取；采用多传感器融合技术，以提高煤岩识别的准确度和可靠性；发展基于大数据分析的智能决策支持系统，优化采煤机的运行策略，同时研究多领域协同仿真控制策略，以应对技术瓶颈并增强系统性能。

Adaptive cutting technology is crucial for enabling intelligent shearers, significantly improving mining efficiency, safety, and resource utilization. Therefore, a comprehensive review of adaptive cutting technology has been conducted, focusing on its technical principles and current applications. Based on core functions and technical objectives, adaptive cutting technology is categorized into four primary research areas: memory cutting, transparent geology, coal-rock identification, and adaptive control. Memory cutting enhance cutting paths by recording historical data, while transparent geology leverages integrated detection technologies to acquire real-time geological information. Coal-rock identification techniques are classified according to recognition principles: indirect methods based on physical parameters, direct methods relying on visual information, and wave-based detection methods such as ground-penetrating radar and ultrasound. Adaptive control automates the adjustment of shearer operating parameters. Collectively, these technologies advance the intelligence of coal mining machines from various perspectives. Nevertheless, due to geological complexities and challenging mining environments, existing technologies face limitations in adaptability and cost-effectiveness. Therefore, future development of adaptive cutting technology should focus on integrating memory cutting, transparent geology, and coal-rock identification technologies to enhance coal seam data acquisition. Implementing multi-sensor fusion technology to improve the accuracy and reliability of coal-rock identification. Developing intelligent decision-support systems based on big data analytics to optimize mining operations and researching multi-domain collaborative simulation control strategies to address technical challenges and improve system performance.