面向核辐射屏蔽材料设计开发的新兴智能技术研究进展

于小航; 周舟; 郝慧杰; 赵静宜; 齐凯丽; 张礼楠; 鲁中良

doi:10.19554/j.cnki.1001-3563.2026.13.009

PDF(7989 KB)

包装工程（技术栏目） ›› 2026, Vol. 47 ›› Issue (13) : 64-77. DOI: 10.19554/j.cnki.1001-3563.2026.13.009

复杂辐射场下多场景辐射防护与屏蔽技术

面向核辐射屏蔽材料设计开发的新兴智能技术研究进展

于小航^1,2, 周舟², 郝慧杰², 赵静宜², 齐凯丽², 张礼楠², 鲁中良^1*

作者信息 +

Research Progress on Emerging Intelligent Technologies for the Design and Development of Nuclear Radiation Shielding Materials

YU Xiaohang^1,2, ZHOU Zhou², HAO Huijie², ZHAO Jingyi², QI Kaili², ZHANG Linan², LU Zhongliang^1*

Author information +

文章历史 +

摘要

目的当前,全球核能技术正迎来新一轮快速发展期。核辐射屏蔽材料作为保障核安全的第一道防线,面临着高屏蔽效能、轻量化、耐辐照及成本可控等多重目标的协同优化需求。然而,传统研发方法长期依赖经验试错与单一物理机制模拟,存在研发周期长、效率低、多目标协同困难等突出问题,亟需引入新的研究范式。本文旨在系统梳理人工智能、数字孪生与增材制造等新兴技术在核辐射屏蔽材料领域的研究进展,分析其深度融合所面临的关键问题,以期为该领域智能化设计与制造的实现提供参考。方法通过文献综述方法,系统总结近年来人工智能、数字孪生与增材制造在核辐射屏蔽材料成分设计、结构优化、制造工艺、质量控制及服役监测等方面的研究成果与技术进展。在此基础上,进一步分析上述技术在深度融合与工程应用过程中面临的核心挑战,主要包括：高质量训练数据获取受限所导致的小样本问题;人工智能模型在跨材料、跨工艺条件下的泛化能力不足;数字孪生建模成本高昂且实时同步困难;增材制造工艺适应性差、核级认证标准缺失等关键问题。结论人工智能、数字孪生与增材制造等新兴技术的深度融合已在核辐射屏蔽材料领域展现出巨大潜力,并在部分应用场景中取得了一定成效。然而,要实现从实验室研究向工程化规模应用的跨越,仍需在数据共享机制建设、模型泛化能力提升、高效计算方法与耐辐射传感技术发展、增材制造工艺优化与标准认证等方面重点突破。本文所梳理的智能化技术方法与应用案例,涵盖了核辐射屏蔽材料研发全链条的关键环节,旨在为核辐射屏蔽材料的高效设计与可靠制造提供方法借鉴与实践参考。

Abstract

Global nuclear energy technology is currently entering a new phase of rapid development. As the primary line of defense in ensuring nuclear safety, nuclear radiation shielding materials face an urgent demand for the simultaneous optimization of multiple objectives, including high shielding performance, lightweight design, radiation resistance, and cost control. However, traditional research and development methods have long relied on trial-and-error approaches and simulations based on single physical mechanisms, leading to prolonged development cycles, low efficiency, and difficulties in multi-objective coordination. Therefore, new research paradigms are urgently needed. The work aims to review the research progress on nuclear radiation shielding materials involving emerging technologies such as artificial intelligence (AI), digital twins (DT), and additive manufacturing (AM), analyze the key challenges hindering their deep integration, and provide guidance for the implementation of intelligent design and manufacturing in this field. Through a literature review, recent research findings and technological advancements in AI, DT, and AM in the composition design, structural optimization, manufacturing processes, quality control, and in-service monitoring of nuclear radiation shielding materials were systematically summarized. On this basis, the core challenges faced in the deep integration and engineering application of these technologies were further analyzed, primarily including the small-sample problem caused by limited access to high-quality training data, insufficient generalization capabilities of AI models across different materials and process conditions, high costs associated with digital twin modeling and difficulties in real-time synchronization, as well as key issues such as the poor adaptability of additive manufacturing processes and the lack of nuclear-grade certification standards. The deep integration of emerging technologies such as AI, DT, and AM has demonstrated tremendous potential in the field of nuclear radiation shielding materials and has achieved certain successes in specific application scenarios. However, to bridge the gap between laboratory research and large-scale engineering applications, breakthroughs are still needed in key areas such as establishing data-sharing mechanisms, enhancing model generalization capabilities, developing efficient computational methods and radiation-resistant sensing technologies, and optimizing additive manufacturing processes and standard certification. This work systematically reviews intelligent technology methods and their applications across the key stages of the entire R&D chain for nuclear radiation shielding materials, covering aspects from composition design and structural optimization to manufacturing process control, quality inspection, and in-service monitoring, providing methodological guidance and practical references for the efficient design and reliable manufacturing of nuclear radiation shielding materials.

导出引用

于小航, 周舟, 郝慧杰, 赵静宜, 齐凯丽, 张礼楠, 鲁中良. 面向核辐射屏蔽材料设计开发的新兴智能技术研究进展[J]. 包装工程. 2026, 47(13): 64-77 https://doi.org/10.19554/j.cnki.1001-3563.2026.13.009

YU Xiaohang, ZHOU Zhou, HAO Huijie, ZHAO Jingyi, QI Kaili, ZHANG Linan, LU Zhongliang. Research Progress on Emerging Intelligent Technologies for the Design and Development of Nuclear Radiation Shielding Materials[J]. Packaging Engineering. 2026, 47(13): 64-77 https://doi.org/10.19554/j.cnki.1001-3563.2026.13.009

中图分类号： TB34

参考文献

[1] 王兰, 李言瑞, 严磊. 从巴黎核能峰会看我国核电发展战略路径与创新方向[J]. 中国核工业, 2026(3): 26-28.
WANG L, LI Y R, YAN L.Strategic Path and Innovation Direction of China’s Nuclear Power Development from Paris Nuclear Energy Summit[J]. China Nuclear Industry, 2026(3): 26-28.
[2] 周令. 碳达峰目标下大亚湾核电站创新生态系统演化路径研究[J]. 中国资源综合利用, 2026, 44(2): 157-160.
ZHOU L.Research on the Evolution Path of the Innovation Ecosystem of Daya Bay Nuclear Power Plant under the Goal of Carbon Peaking[J]. China Resources Comprehensive Utilization, 2026, 44(2): 157-160.
[3] BHOWMIK P K, SUH K Y.Evaluating Thermal- Hydraulic Energy Conversion of Water-Cooled Small Modular Reactors: Supporting Design Changes and Customer Needs[J]. Nuclear Engineering and Design, 2026, 456: 115007.
[4] 任猛, 张荣, 王国辉, 等. 聚合物基复合材料在中子/γ射线防护中的研究进展与挑战[J/OL]. 材料导报, 2026: 1-30[2026-06-01]. https://link.cnki.net/urlid/50.1078.TB.20260325.1353.004.
REN M, ZHANG R, WANG G H, et al. Research Progress and Challenges of Polymer Matrix Composites in Neutron/Gamma Ray Protection[J/OL]. Materials Reports, 2026: 1-30[2026-06-01]. https://link.cnki.net/urlid/50.1078.TB.20260325.1353.004.
[5] WANG Y, CHENG Y, HUANG W, et al.Dynamic Electromagnetic-Thermal Mapping in Motor Digital Twins: A Real-Time Multiphysics Framework[J]. Digital Engineering, 2026, 8: 100082.
[6] 曹志增, 王桂吉, 罗斌强. 基于机器学习的金属材料力学性能智能预测研究现状与展望[J]. 力学进展, 2026, 56(1): 123-168.
CAO Z Z, WANG G J, LUO B Q.Intelligent Prediction of Mechanical Properties in Metallic Materials Based on Machine Learning: A Review & Perspective[J]. Advances in Mechanics, 2026, 56(1): 123-168.
[7] WANG Y, LI Y C, et al.Optimal Placement Method for Monitoring Devices Under Unknown Harmonic Source Information in Distribution Networks[J]. Power System Protection and Control, 2026, 53(19): 162-174.
[8] 花靖, 蒋秀, 于超, 等. 基于多策略改进蜣螂算法和支持向量回归的CO₂输送管道腐蚀预测[J]. 科学技术与工程, 2026, 26(3): 1028-1037.
HUA J, JIANG X, YU C, et al.Corrosion Prediction of CO₂ Transport Pipeline Based on Multi-Strategy Improved Dung Beetle Algorithm and Support Vector Regression[J]. Science Technology and Engineering, 2026, 26(3): 1028-1037.
[9] CHEN H Y, XU T T, DU Y H, et al.CLKA-LPO: A CNN-LSTM-KAN Neural Network for Lightning Potential and Flash Rate Prediction Based on Atmospheric Physical Parameters[J]. Atmospheric and Oceanic Science Letters, 2026, 19(3): 100679.
[10] 可帅, 潘开林, 王波, 等. 基于机器视觉的辐射环境下塑封材料缺陷检测方法及系统: CN202510449009.9[P].2025-07-15.
KE S, PAN K L, WANG B, et al. Method and System for Defect Detection of Plastic Packaging Materials in Radiation Environment Based on Machine Vision: CN202510449009[P].2025-07-15.
[11] 李征, 邓植中, 吴鹏飞, 等. 基于激光散斑图像和卷积神经网络-支持向量回归的表面粗糙度预测[J]. 激光与光电子学进展, 2024, 61(14): 1412006.
LI Z, DENG Z Z, WU P F, et al.Surface Roughness Prediction Based on Laser Speckle Images and Convolutional Neural Network-Support Vector Regression[J]. Laser & Optoelectronics Progress, 2024, 61(14): 1412006.
[12] 程铭, 韦子豪. 基于人工智能技术的数字反应堆加速计算技术研究[J]. 数字通信世界, 2025(8): 34-36.
CHENG M, WEI Z H.Research on Accelerated Computing Technology for Digital Reactors Based on Artificial Intelligence Technology[J]. Digital Communication World, 2025(8): 34-36.
[13] LIAO R X, ZHANG Y M, WANG H, et al.Digital Twin-Assisted Automatic Ship Size Measurement for Ship-Bridge Collision Early Warning Systems[J]. Journal of Zhejiang University: Science A, 2026, 27(1): 277.
[14] WANG L, YAO Y D, LUO X D, et al.A Critical Review on Intelligent Optimization Algorithms and Surrogate Models for Conventional and Unconventional Reservoir Production Optimization[J]. Fuel, 2023, 350: 128826.
[15] 杨欢, 周永霞, 丁昭军, 等. 深度学习重建算法在低剂量冠状动脉CT血管成像中的图像质量与辐射剂量优化: 一项前瞻性随机对照研究[J]. 中国医学装备, 2026, 23(2): 13-17.
YANG H, ZHOU Y X, DING Z J, et al.Optimization of Image Quality and Radiation Dose of Low Dose Coronary CTA by Using Deep Learning Reconstruction Algorithms: A Prospective RCT[J]. China Medical Equipment, 2026, 23(2): 13-17.
[16] 杨佳均, 陈龙淼, 刘太素, 等. 基于组合优化算法的多工况火炮车架轻量化[J/OL]. 火炮发射与控制学报, 2026: 1-8[2026-06-01]. https://doi.org/10.19323/j.issn.1673-6524.202510012.
YANG J J, CHEN L M, LIU T S, et al. Lightweight Design of Multi-Condition Gun Frame Based on Combined Optimization Algorithm[J/OL]. Journal of Gun Launch & Control, 2026: 1-8[2026-06-01]. https://doi.org/10.19323/j.issn.1673-6524.202510012.
[17] MA Q L, SU T, XIE Y C, et al.Multi-Objective Optimization of a Hydrogen-Butanol Rotary Engine Driven by Machine Learning and Intelligent Algorithm[J]. Applied Thermal Engineering, 2026, 300: 131560.
[18] 潘翔, 王宇琛. 基于移动最小二乘拟合曲面的网格去噪算法[J]. 浙江工业大学学报, 2026: 1-10[2026-06-01]. https://link.cnki.net/urlid/33.1193.t.20260519.1050.006.
PAN X, WANG Y C. Mesh Denoising Algorithm Based on Moving Least Squares Fitting Surface[J]. Journal of Zhejiang University of Technology, 2026: 1-10[2026-06-01]. https://link.cnki.net/urlid/33.1193.t.20260519.1050.006.
[19] 陈其鹏, 郭耿君. 基于布谷鸟搜索算法与改进粒子群优化算法的微生物燃料电池最大功率点跟踪[J]. 自动化应用, 2026, 67(9): 196-198.
CHEN Q P, GUO G J.Maximum Power Point Tracking for MFC Based on CS Algorithm and IPSO Algorithm[J]. Automation Application, 2026, 67(9): 196-198.
[20] 陈震, 李锐杰, 李晓克, 等. 融合物理信息神经网络与群智能优化算法的结构损伤识别研究[J]. 振动工程学报, 2026, 1-14.
CHEN Z, LI R J, LI X K, et al.Structural Damage Identification Based on Physics-Informed Neural Network and Swarm Intelligence Optimization Algorithm[J]. Journal of Vibration Engineering, 2026,1-14.
[21] NIU L, DENG J X, HU R, et al.A Novel Extreme Gradient Boosting Based Adaptive Genetic Algorithm Method for Electro-Thermal Performance Optimization of Power Integrated Circuits[J]. Engineering Applications of Artificial Intelligence, 2026, 180: 115235.
[22] XIE W B, SUN Y H, PENG C, et al.Multi-Objective Optimization of Solid Oxide Fuel Cells Based on Multi-Physics Simulation and Hybrid Intelligent Algorithms[J]. International Journal of Hydrogen Energy, 2026, 241: 155565.
[23] 侯艳龙. 利用智能优化算法的形变模型参数反演分析[D]. 徐州: 中国矿业大学, 2025.
HOU Y L.Inversion Analysis of Deformation Model Parameters Using Intelligent Optimization Algorithms[D]. Xuzhou: China University of Mining and Technology, 2025.
[24] QI Y, WANG J C, BAI R H.Exploring the Construction of Digital Workshops within the TOE Analysis Framework[J]. Sustainable Development, 2026, 16(2): 21-25.
[25] JI L Y, ZHANG R, YANG X J, et al.Design and Implementation of a ROS-Based Multi-UAV Cooperative Virtual-Physical Integrated System[J]. Computer Science and Application, 2026, 16(1): 142-153.
[26] 陶飞, 刘蔚然, 张萌, 等. 数字孪生五维模型及十大领域应用[J]. 计算机集成制造系统, 2019, 25(1): 1-18.
TAO F, LIU W R, ZHANG M, et al.Five-Dimension Digital Twin Model and Its Ten Applications[J]. Computer Integrated Manufacturing Systems, 2019, 25(1): 1-18.
[27] 陶飞, 张萌, 程江峰, 等. 数字孪生车间——一种未来车间运行新模式[J]. 计算机集成制造系统, 2017, 23(1): 1-9.
TAO F, ZHANG M, CHENG J F, et al.Digital Twin Workshop: A New Paradigm for Future Workshop[J]. Computer Integrated Manufacturing Systems, 2017, 23(1): 1-9.
[28] KOBAYASHI K, ALAM S B. Explainable, Interpretable,Trustworthy AI for an Intelligent Digital Twin: A Case Study on Remaining Useful Life[J]. Engineering Applications of Artificial Intelligence, 2024, 129: 107620.
[29] ABADI B N R, HATTEL J H, SARHADI A. Machine Learning-Driven Digital Twin for Real-Time Temperature Prediction and Adaptive Process Control in Large-Scale Additive Manufacturing[J]. Journal of Manufacturing Systems, 2026, 87: 62-77.
[30] ZHUMABEKOVA A, YANKIN A, PERVEEN A, et al.A Review on Additive Manufacturing of Ti-Containing High-Entropy Alloys: Processing, Microstructure, and Mechanical Behavior[J]. Advances in Materials Science and Engineering, 2026, 2026(1): 5588584.
[31] ABDELMOULA M, MUSINSKI W D.Laser Beam Shaping in Powder Bed Fusion Additive Manufacturing: A Review of Melt Pool Morphology and Microstructure Effects[J]. The International Journal of Advanced Manufacturing Technology, 2026, 144(9): 6083-6109.
[32] WANG Y J.A Review on Spray-Formed High-Speed Steels: Process Modeling, Microstructure Evolution, and Mechanical Properties[J]. The International Journal of Advanced Manufacturing Technology, 2026, 143(3): 1253-1279.
[33] 杨凯, 王磊, 汤永凯, 等. 面向高端装备的金属激光增材制造技术发展与应用[J]. 中国机械工程, 2025, 36(9): 2068-2080.
YANG K, WANG L, TANG Y K, et al.Development and Application of Metal Laser Additive Manufacturing Technology for High-End Equipment[J]. China Mechanical Engineering, 2025, 36(9): 2068-2080.
[34] ABUSHAHLA K H, ARSLAN H.Prediction of Mass Attenuation Coefficients in Mixed Alkali and Borosilicate Glasses Using Machine Learning Approaches[J]. Radiation Physics and Chemistry, 2025, 229: 112471.
[35] RASOULI F S, YAHYAEE A, MASOUDI S F.Using ANN for Thermal Neutron Shield Designing for BNCT Treatment Room[J]. Scientific Reports, 2024, 14: 14805.
[36] AHMAD S, CHANG B, LIAN C, et al.Design and Development Study of Gradient Composite Shielding Material for Nuclear Radiation[J]. Nuclear Engineering and Design, 2023, 414: 112517.
[37] 蔡垚, 胡华四, 潘紫姮, 等. 针对车载D-D加速器中子源的紧凑、轻量化屏蔽材料优化设计研究[J]. 原子能科学技术, 2018, 52(4): 715-721.
CAI Y, HU H S, PAN Z H, et al.Study on Optimization Design of Compact and Lightweight Radiation Shielding Material for Vehicle-Mounted Accelerator-Driven D-D Neutron Source[J]. Atomic Energy Science and Technology, 2018, 52(4): 715-721.
[38] MA W J, ZHENG M X, WANG R C, et al.Machine Learning-Assisted Rapid Development of High Performance Flexible Lead-Free Radiation Shielding Gels[J]. Science China Materials, 2026: 1-11.
[39] 王宇桐, 朱伟杰, 魏昊, 等. 基于天鹰算法与BP神经网络混合模型的X射线柔性材料屏蔽性能优化[J]. 辐射防护, 2026, 46(2): 106-115.
WANG Y T, ZHU W J, WEI H, et al.Performance Optimization of X-Ray Flexible Shielding Materials Based on a Hybrid AO-BP Neural Network Model[J]. Radiation Protection, 2026, 46(2): 106-115.
[40] 付昊成, 吴少伟, 姜潮. 基于蒙特卡罗减方差方法的图像传感器辐射屏蔽结构多目标优化设计[J]. 中国机械工程, 2026, 37(5): 1045-1053.
FU H C, WU S W, JIANG C.Radiation Shielding Structure Multi-Objective Optimization of Imagine Sensors Based on Monte-Carlo Variance Reduction Method[J]. China Mechanical Engineering, 2026, 37(5): 1045-1053.
[41] 姬俊杰, 刘宇辰, 韩毅, 等. 基于智能算法与MCNP模型的个体辐射防护装备屏蔽结构优化设计研究[J]. 核电子学与探测技术, 2026, 46(5): 665-673.
JI J J, LIU Y C, HAN Y, et al.Optimization Design of Shielding Structure for Individual Radiation Protection Equipment Based on Intelligent Algorithm and MCNP Model[J]. Nuclear Electronics & Detection Technology, 2026, 46(5): 665-673.
[42] 王建昭, 马继楠, 张庆祥, 等. 木星系探测中多层材料的辐射屏蔽优化设计方法[J]. 航天器环境工程, 2019, 36(6): 601-606.
WANG J Z, MA J N, ZHANG Q X, et al.Optimization Design of Radioprotection by Multilayer Materials in Jovian System Exploration Missions[J]. Spacecraft Environment Engineering, 2019, 36(6): 601-606.
[43] LIU B B, GU Y Z, GUO R Q, et al.Multilayer Design and Multi-Objective Optimization of Neutron Shielding Composites by Means of MCNP Simulation and Machine Learning[J]. Composites Science and Technology, 2026, 274: 111451.
[44] XU D, KOROLOVYCH V, et al.Warpage-Resistant, Under-Extrusion-Free, High-Surface-Quality Additive Manufacturing Process for Polyethylene-Based Composite Radiation Shielding Material[J]. ACS Applied Polymer Materials, 2025, 7(18): 12304-12320.
[45] ZEKRAOUI S, LESCOT T, AKBARI TAEMEH M, et al.Radiopaque Filaments for Fused Filament Fabrication (FFF) 3D Printing[J]. Additive Manufacturing, 2025, 110: 104914.
[46] DHARMADHIKARI S, MENON N, BASAK A.A Reinforcement Learning Approach for Process Parameter Optimization in Additive Manufacturing[J]. Additive Manufacturing, 2023, 71: 103556.
[47] RUI Z M, LIU J, SHI Y, et al.Additive Manufacturing Method of Lattice Structure Based on Material Manufacturing Performance Driven: Using Machine Learning to Optimize Manufacturing Process[J]. Additive Manufacturing Frontiers, 2026, 5(1): 200258.
[48] 曾瑞圳, 韦辉亮, 杜川鹏, 等. 人工智能驱动的激光粉末床熔融缺陷在线监测与控制方法[J]. 中国激光, 2026, 53(4): 95-119.
ZENG R Z, WEI H L, DU C P, et al.Artificial Intelligence Driven in Situ Monitoring and Control Methods for Laser Powder Bed Fusion Processes(Invited)[J]. Chinese Journal of Lasers, 2026, 53(4): 95-119.
[49] ZHENG Z W, QIU S Y, YUE X Z, et al.Detecting Irradiation Defects in Materials: A Machine Learning Approach to Analyze Helium Bubble Images[J]. Journal of Nuclear Materials, 2024, 596: 155117.
[50] ZIABARI A, RAHMAN O, VENKATAKRISHNAN S, et al.Advancing Additive Manufacturing through Artificial Intelligence-Powered, High-Throughput, Nondestructive Characterization and Process Optimization:[R]. Oak Ridge, TN: Oak Ridge National Laboratory, 2024
[51] MALIKOV A K U, FLORES CUENCA M F, KIM B, et al. Ultrasonic Tomography Imaging Enhancement Approach Based on Deep Convolutional Neural Networks[J]. Journal of Visualization, 2023, 26(5): 1067-1083.
[52] PANAHI R, JAFARI H, AZIZI M, et al.An Innovative Approach for Predicting Concrete Moisture Content Based on Gamma Ray Attenuation and Artificial Neural Networks[J]. Journal of Nuclear Research and Applications, 2024, 4(4): 34-44.
[53] HOSSAIN R, AHMED F, KOBAYASHI K, et al.Virtual Sensing-Enabled Digital Twin Framework for Real-Time Monitoring of Nuclear Systems Leveraging Deep Neural Operators[J]. npj Materials Degradation, 2025, 9: 21.
[54] ABUALASAL A, TAMUS Z Á.Non-Destructive Assessment of Gamma Radiation Aging in Nuclear Cables via New Dielectric Spectroscopy Markers and Machine Learning Algorithm[J]. Polymers, 2026, 18(4): 500.
[55] SHI J Q, LV Z, WANG J, et al.A Finite Element Study on the Irradiation-Induced Mechanical Behaviors of Aluminum-Matrix Radiation-Shielding Composites[J]. Journal of Nuclear Materials, 2025, 603: 155440.
[56] NASIRI P, FIFIELD L S, NOURI H, et al. Data-Driven Model for Elastomers under Simultaneous Thermal and Radiation Exposure[PP/OL]. arXiv (2025-11-25). https://doi.org/10.48550/arXiv.2512.05978.