随着现代信息技术特别是新一代人工智能技术的发展，智能机床技术迎来了新的发展机遇。本文在中国工程院定义的智能制造三个范式的基础上，系统地阐述了智能机床的概念、内涵、特征和体系架构。揭示了机床从手动机床演化到智能机床的三个阶段（数控机床、互联网+ 机床以及智能机床），详细分析了智能机床的自主感知与连接、自主学习与建模、自主优化与决策和自主控制与执行这四项智能化控制的实现原理，提出了智能机床通过数据学习形成并积累知识的本质特征，独创发明了指令域分析方法、物理和大数据混合建模技术、i 代码和双码联控等关键使能技术。基于以上研究，研制了智能数控系统和智能机床工业样机。通过基于Cyber NC 和双码联控的加工质量优化、基于大数据建模的工艺参数优化和基于深度学习的机床进给系统建模及误差补偿这三个智能化技术应用案例的实践，验证了新一代人工智能技术与制造技术的深度融合，是机床实现从“互联网+ 机床”向“智能+ 机床”演化的便捷有效途径。

With the development of modern information technology—and particularly of the new generation of artificial intelligence (AI) technology—new opportunities are available for the development of the intelligent machine tool (IMT). Based on the three classical paradigms of intelligent manufacturing as defined by the Chinese Academy of Engineering, the concept, characteristics, and systemic structure of the IMT are presented in this paper. Three stages of machine tool evolution—from the manually operated machine tool (MOMT) to the IMT—are discussed, including the numerical control machine tool (NCMT), the smart machine tool (SMT), and the IMT. Furthermore, the four intelligent control principles of the IMT—namely, autonomous sensing and connection, autonomous learning and modeling, autonomous optimization and decision-making, and autonomous control and execution—are presented in detail. This paper then points out that the essential characteristic of the IMT is to acquire and accumulate knowledge through learning, and presents original key enabling technologies, including the instruction-domain-based analytical approach, theoretical and big-data-based hybrid modeling technology, and the double-code control method. Based on this research, an intelligent numerical control (INC) system and industrial prototypes of IMTs are developed. Three intelligent practices are conducted, demonstrating that the integration of the new generation of AI technology with advanced manufacturing technology is a feasible and convenient way to advance machine tools toward the IMT.