传统磨削技术受磨粒随机切削、接触时变、磨具磨损及力热耦合等因素影响，存在过程状态难感知、异常风险难识别、质量结果难预测和参数调控难闭环等瓶颈，难以满足工艺自生成、状态自感知、参数自决策和过程自适应的高质高效智能制造需求。首先，面向难加工材料、复杂型面、弱刚性结构和高一致性制造4类典型任务主导场景，系统综述了人工智能方法(Artificial Intelligence，AI)与数字孪生技术(Digital Twin，DT)赋能磨前规划、磨中执行和磨后反馈3阶段全任务链的智能磨削技术研究进展。其次，讨论了多源数据底座与统一状态表征、机理-数据融合建模、虚实同步与数字线程、工业部署与可信闭环、系统集成架构5类智能磨削共性支撑能力。进一步，从开放数据与统一评测、小样本与跨工况泛化、安全可信与人在环协同、平台化运维与能力建设四方面展望了智能磨削的发展机遇。最后，归纳了AI与DT赋能智能磨削由单源感知、局部建模与离线优化，向覆盖4类场景、贯通3阶段、依托5类支撑的系统化闭环智能方向发展的研究趋势，为复杂工况下磨削过程的智能感知、稳定预测、闭环调控和持续演化研究提供参考。

Traditional grinding is affected by random abrasive cutting, time-varying contact, abrasive tool wear, and force–thermal coupling, leading to bottlenecks in process-state perception, abnormal-risk identification, quality-result prediction, and closed-loop parameter regulation. As a result, it is difficult to meet the requirements of high-quality and high-efficiency intelligent manufacturing characterized by process self-generation, state self-perception, parameter self-decision-making, and process self-adaptation. Focusing on four typical task-dominant scenarios, namely difficult-to-machine materials, complex surfaces, low-rigidity structures, and high-consistency manufacturing, this paper systematically reviews the research progress of intelligent grinding enabled by Artificial Intelligence (AI) methods and Digital Twin (DT) technology across the full task chain of pre-grinding planning, in-process execution, and post-grinding feedback. Five common supporting capabilities for intelligent grinding are discussed, including multi-source data foundation and unified state representation, mechanism–data fusion modeling, virtual–physical synchronization and digital thread, industrial deployment and trustworthy closed-loop operation, and system integration architecture. Future opportunities for intelligent grinding are further discussed from four aspects: open data and unified evaluation, small-sample learning and cross-condition generalization, safety and trustworthiness with human-in-the-loop collaboration, and platform-based operation and maintenance and capability development. This review provides a reference for intelligent perception, stable prediction, closed-loop regulation, and continuous evolution of grinding processes under complex working conditions.