摘要
随着新一代信息技术与制造技术的深度融合，人工智能（Artificial Intelligence, AI）已成为推动机械制造系统向智能化、数字化和网络化方向变革的核心驱动力。本文系统综述了2019—2024年人工智能在机械制造系统中的应用研究进展。首先，阐述了人工智能赋能智能制造的时代背景与战略意义，分析了大数据、深度学习及工业物联网等关键技术对制造系统转型升级的支撑作用。其次，重点综述了人工智能在生产调度优化、刀具状态监测与预测、表面质量检测与缺陷识别等机械制造核心环节的应用现状，深入分析了深度学习、强化学习、迁移学习等AI算法在制造系统性能提升中的具体实现路径。进一步，探讨了人工智能在制造系统层面的人机协同、预测性维护及智能化决策等前沿发展方向。最后，总结了当前研究中面临的数据质量、模型可解释性、实时性及安全性等挑战，并展望了人工智能与数字孪生、边缘计算及大模型技术融合的发展趋势。本文旨在为人工智能在机械制造系统中的深入应用研究提供理论参考和技术借鉴。
关键词： 人工智能；机械制造系统；智能制造；生产调度；刀具监测；缺陷检测；深度学习
Abstract
With the deep integration of new-generation information technology and manufacturing technology, artificial intelligence (AI) has become a core driving force for the transformation of mechanical manufacturing systems towards intelligence, digitalization, and networking. This paper systematically reviews the research progress on the application of AI in mechanical manufacturing systems from 2019 to 2024. First, it elucidates the historical context and strategic significance of AI empowering intelligent manufacturing, and analyzes the supporting role of key technologies such as big data, deep learning, and the Industrial Internet of Things in the transformation and upgrading of manufacturing systems. Second, it focuses on reviewing the current application status of AI in core mechanical manufacturing processes such as production scheduling optimization, tool condition monitoring and prediction, and surface quality inspection and defect identification, and deeply analyzes the specific implementation paths of AI algorithms such as deep learning, reinforcement learning, and transfer learning in improving the performance of manufacturing systems. Furthermore, it explores the cutting-edge development directions of AI at the manufacturing system level, such as human-machine collaboration, predictive maintenance, and intelligent decision-making. Finally, it summarizes the challenges faced in current research, including data quality, model interpretability, real-time performance, and security, and looks forward to the development trend of the integration of AI with digital twins, edge computing, and large-scale model technologies. This paper aims to provide theoretical reference and technical guidance for the in-depth application research of artificial intelligence in mechanical manufacturing systems.
Key words： Artificial intelligence; Mechanical manufacturing system; Intelligent manufacturing; Production scheduling; Tool monitoring; Defect detection; Deep learning
参考文献 References
[1] 王柏村, 薛塬, 延建林, 等. 以人为本的智能制造：理念、技术与应用[J]. 中国工程科学, 2020, 22(4): 58-67.
[2] 袁烨, 张永, 丁汉. 工业人工智能的关键技术及其在预测性维护中的应用现状[J]. 自动化学报, 2020, 46(10): 2001-2014.
[3] 张洁, 汪俊亮, 吕佑龙, 等. 大数据驱动的智能制造[J]. 中国机械工程, 2019, 30(2): 127-133.
[4] 王柏村, 易兵, 刘振宇, 等. CPS视角下智能制造的发展与研究[J]. 计算机集成制造系统, 2021, 27(1): 1-16.
[5] 汪俊亮, 高鹏捷, 张洁, 等. 制造大数据分析综述：内涵、方法、应用和趋势[J]. 机械工程学报, 2023, 59(12): 1-16.
[6] 吴秀丽, 孙琳. 智能制造系统基于数据驱动的车间实时调度[J]. 控制与决策, 2020, 35(3): 523-535.
[7] 陈剑, 孙明月, 马文静, 等. 基于VCG拍卖的智能车间主动调度机制研究[J]. 工业工程与管理, 2024, 29(1): 1-11.
[8] 周亚勤, 汪俊亮, 吕志军, 等. 密集仓储环境下多AGV/RGV调度方法研究[J]. 机械工程学报, 2021, 57(10): 245-256.
[9] 周亚勤, 吕佑龙, 郑鹏, 等. 考虑动态资源和工件批量约束的柔性车间生产调度方法[J]. 计算机集成制造系统, 2020, 26(5): 1258-1267.
[10] 周亚勤, 汪俊亮, 鲍劲松, 等. 针织生产智能管控的通用数据模型研究[J]. 中国机械工程, 2019, 30(2): 143-148.
[11] 刘献礼, 李雪冰, 丁明娜, 等. 面向智能制造的刀具全生命周期智能管控技术[J]. 机械工程学报, 2021, 57(10): 196-219.
[12] 李亚, 黄亦翔, 赵路杰, 等. 基于t分布邻域嵌入与XGBoost的刀具多工况磨损评估[J]. 机械工程学报, 2020, 56(1): 132-140.
[13] 戴稳, 张超勇, 孟磊磊, 等. 采用深度学习的铣刀磨损状态预测模型[J]. 中国机械工程, 2020, 31(17): 2071-2078.
[14] 刘会永, 张松, 李剑峰, 等. 采用改进CNN-BiLSTM模型的刀具磨损状态监测[J]. 中国机械工程, 2022, 33(16): 1940-1947.
[15] 刘辉, 张超勇, 戴稳. 基于堆叠稀疏去噪自动编码网络与多隐层反向传播神经网络的铣刀磨损预测模型[J]. 计算机集成制造系统, 2021, 27(10): 2801-2812.
[16] 伍麟, 郝鸿宇, 宋友. 基于计算机视觉的工业金属表面缺陷检测综述[J]. 自动化学报, 2024, 50(7): 1261-1283.
[17] 李宗祐, 高春艳, 吕晓玲, 等. 基于深度学习的金属材料表面缺陷检测综述[J]. 制造技术与机床, 2023(6): 61-67.
[18] 张宇梁, 钟占荣, 曹洁, 等. “人工智能赋能激光”——智能化激光制造装备及工艺研究进展[J]. 中国激光, 2023, 50(11): 1101005.
[19] 高艺平, 王浩, 李新宇, 等. 基于深度智能视觉的表面缺陷检测研究进展[J]. 工业工程, 2024, 27(2): 27-36.
[20] 王柏村, 黄思翰, 易兵, 等. 面向智能制造的人因工程研究与发展[J]. 机械工程学报, 2020, 56(16): 1-12.
[21] CHRYSSOLOURIS G, ALEXOPOULOS K, ARKOULI Z. Artificial intelligence in manufacturing systems[M]//A perspective on artificial intelligence. Cham: Springer, 2023: 85-118.
[22] PERES R S, JESUS A D, JONKER J, et al. Industrial artificial intelligence in industry 4.0—systematic review, challenges and outlook[J]. IEEE Access, 2020, 8: 220121-220139.
[23] WANG J, XU C, ZHANG J, et al. Big data analytics for intelligent manufacturing systems: a review[J]. Journal of Manufacturing Systems, 2021, 62: 738-752.
[24] AMERI R, HSU C C, BAND S S. A systematic review of deep learning approaches for surface defect detection in industrial applications[J]. Engineering Applications of Artificial Intelligence, 2024, 130: 107717.
[25] ARINEZ J F, CHANG Q, GAO R X, et al. Artificial intelligence in advanced manufacturing: Current status and future outlook[J]. Journal of Manufacturing Science and Engineering, 2020, 142(11): 110804.