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

摘要/Abstract

摘要： 提出了一种天鹰算法(AO)与BP神经网络相结合的方法,以优化X射线屏蔽材料的组分,实现对不同能量区段X射线的屏蔽。通过XCOM程序筛选具有K吸收边互补特性的功能元素,并利用蒙特卡罗方法计算不同质量配比下的透射粒子数,利用此数据集训练BP神经网络,将训练结果与蒙特卡罗模拟结果对比分析,并采用沙普利加和解释(SHAP)量化分析各元素对屏蔽率的贡献程度,再通过AO算法求解最优元素质量配比方案,最后通过蒙特卡罗模拟对优化结果进行屏蔽性能的模拟测试与对比分析。结果表明,当W、Bi、Gd、Sm和SEBS质量配比为0.018 8∶0.261 0∶0.058 1∶0.162 1∶0.500 0时,在100 kV管电压下屏蔽率可达75.51%,此时材料密度为1.600 7 g/cm³。该方法丰富了复合屏蔽材料研发和应用优化计算方法。

关键词: 辐射屏蔽, X射线, AO算法, BP神经网络, 蒙特卡罗, 优化设计

Abstract: The performance optimization of radiation shielding materials remains a central focus in the field of radiation protection. Traditional approaches to shielding material design have relied heavily on extensive experimental data and empirical knowledge, which is not only time-consuming and costly, but also cannot guarantee identification of globally optimal solutions. This study proposes a strategy combining the Aquila Optimizer (AO) with a BP neural network to optimize the composition of X-ray shielding materials and achieve efficient shielding across different X-ray energy segments. Initially, Monte Carlo simulations are employed to establish an X-ray tube model. Functional elements featuring complementary K-absorption edge characteristics are screened via the XCOM program, and Monte Carlo calculations determine the shielding rate for various elemental proportions. Subsequently, a BP neural network is employed to model the non-linear mapping between input parameters (elemental composition) and output parameters (shielding performance). SHAP (SHapley Additive Explanations) interpretability is applied to quantify the contribution of each element to the shielding rate. The AO algorithm is subsequently employed to determine the optimal elemental proportion scheme. Finally, Monte Carlo simulations are utilized for performance testing and comparative analysis of the optimized composition. Results indicate that for the composition W∶Bi∶Gd∶Sm∶SEBS= 0.018 8∶0.261 0∶0.058 1∶0.162 1∶0.500 0, a shielding rate of 75.51% is achieved at 100 kV tube voltage, with a material density of 1.600 7 g/cm³. Additionally, an in-depth investigation of optimal functional element proportions for different energy segments was performed. This method demonstrates significant innovation and effectiveness, thus enriching the computational methods for research, development, and application optimization of composite shielding materials.

Key words: radiation shielding, x-ray, aquila optimizer algorithm, BP neural network, Monte Carlo, optimization design

中图分类号:

王宇桐, 朱伟杰, 魏昊, 李君, 原林, 王博宇, 刘洋. 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 Yutong, ZHU Weijie, WEI Hao, LI Jun, YUAN Lin, WANG Boyu, LIU Yang. 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.

参考文献

[1] Kim Y C, Kim K H, Son D Y, et al. Printable organometallic perovskite enables large-area, low-dose X-ray imaging[J]. Nature, 2017, 550(7674): 87-91.
[2] 王博宇,张栋栋,袁继龙,等.无铅柔性高分子复合材料 X 射线屏蔽性能研究[J]. 辐射防护,2024,44(6): 695-704.
WANG Boyu, ZHANG Dongdong, YUAN Jilong, et al. X-ray shielding properties of lead-free flexible polymer composite materials[J]. Radiation Protection, 2024, 44(6): 695-704.
[3] Yu L, Yap P L, Santos A M C, et al. Lightweight polyester fabric with elastomeric bismuth titanate composite for high-performing lead-free X-ray shielding[J]. Radiation Physics and Chemistry, 2023, 205: 110726.
[4] Tishkevich D I, Grabchikov S S, Lastovskii S B, et al. Effect of the synthesis conditions and microstructure for highly effective electron shields production based on Bi coatings[J]. ACS Applied Energy Materials, 2018, 1(4): 1695-1702.
[5] Martinez L M, Kingston J. Space radiation analysis: radiation effects and particle interaction outside the earth’s magnetosphere using GRAS and GEANT4[J]. Acta Astronautica, 2012, 72: 156-164.
[6] Verdipoor K, Alemi A, Mesbahi A. Photon mass attenuation coefficients of a silicon resin loaded with WO₃, PbO, and Bi₂O₃ Micro and nano-particles for radiation shielding[J]. Radiation Physics and Chemistry, 2018, 147: 85-90.
[7] Nambiar S, Osei E K, Yeow J T W. Polymer nanocomposite-based shielding against diagnostic X-rays[J]. Journal of applied polymer science, 2013, 127(6): 4939-4946.
[8] Li Q X, Wei Q L, Zheng W J, et al. Enhanced radiation shielding with conformal light-weight nanoparticle-polymer composite[J]. ACS applied materials & interfaces, 2018, 10(41): 35510-35515.
[9] McCaffrey J P, Mainegra-Hing E, Shen H. Optimizing non-Pb radiation shielding materials using bilayers[J]. Medical physics, 2009, 36(12): 5586-5594.
[10] 于志翔,邹树梁,徐守龙,等.基于BP神经网络的船用反应堆屏蔽设计快速计算功能研究[J]. 核电子学与探测技术,2016,36(2):209-213.
YU Zhixiang, ZOU Shuliang, XU Shoulong, et al. Fast calculation of shielding design for marine reactor based on BP neural network[J]. Nuclear Electronics & Detection Technology, 2016, 36(2): 209-213.
[11] HU Huasi, WANG Qunshu, QIN Juan, et al. Study on composite material for shielding mixed neutron and γ-rays[J]. IEEE Transactions on Nuclear Science, 2008, 55(4): 2376-2384.
[12] HU Guang, SHI Guang, HU Huasi, et al. Development of gradient composite shielding material for shielding neutrons and gamma rays[J]. Nuclear Engineering and Technology, 2020, 52(10): 2387-2393.
[13] Ashayer S, Askari M, Afarideh H. Optimal per cent by weight of elements in diagnostic quality radiation shielding materials[J]. Radiation protection dosimetry, 2012, 149(3): 268-288.
[14] 廖伶元,邱小平.屏蔽材料组分含量的优化设计[J]. 核电子学与探测技术,2010,30(1):118-120.
LIAO Lingyuan, QIU Xiaoping. Optimized design of component content of shielding material[J]. Nuclear Electronics & Detection Technology, 2010, 30(1): 118-120.
[15] 李晓梦,李志峰,宋英明,等.基于 FCNN-NSGA-Ⅲ 的反应堆辐射屏蔽设计智能优化研究[J]. 原子核物理评论,2023,40(4):572-578.
LI Xiaomeng, LI Zhifeng, SONG Yingming, et al. Research on intelligent optimization of reactor radiation shielding design based on FCNN-NSGA-Ⅲ[J]. Nuclear Physics Review, 2023, 40(4): 572-578.
[16] Abualigah L, Yousri D, Abd Elaziz M, et al.Aquila optimizer: a novel meta-heuristic optimization algorithm[J]. Computers & Industrial Engineering,2021,157: 107250.
[17] 钟鹏,刘超卓,王殿生,等.Cu-Zr-Al-Sm非晶合金的γ射线屏蔽性能研究[J]. 核技术,2015,38(1): 29-33.
ZHONG Peng, LIU Chaozhuo, WANG Diansheng, et al. γ-ray shielding properties of Cu-Zr-Al-Sm bulk metallic glasses[J]. Nuclear Techniques, 2015, 38(1): 29-33.
[18] 张璇, 李德红, 张晓乐, 等. 少铅/无铅材料对X射线屏蔽性能的检测方法研究进展[J]. 辐射防护, 2023, 43(5): 412-421.
ZHANG Xuan, LI Dehong, ZHANG Xiaole, et al. Research progress of testing methods for X-ray shielding performance of low-lead/lead-free materials[J]. Radiation Protection, 2023, 43(5): 412-421.
[19] 孔燕, 卓维海, 陈波, 等. 医用诊断X射线能谱的MCNP模拟[J]. 核技术, 2019, 42(11): 38-42.
KONG Yan, ZHUO Weihai, CHEN Bo, et al. MCNP simulations of medical diagnostic X-ray spectra[J]. Nuclear Techniques, 2019, 42(11): 38-42.
[20] WANG Boyu, GUO Xiaolin, YUAN Lin, et al. Micro Gadolinium oxide dispersed flexible composites developed for the shielding of thermal neutron/gamma rays[J]. Nuclear Engineering and Technology, 2023, 55(5): 1763-1774.
[21] 仇天祎, 张国青, 王敏娟, 等. 环保型柔性医用X射线防护材料研制及其防护性能分析与优化[J]. 中华放射医学与防护杂志, 2023, 43(12): 1016-1021.
QIU Tianyi, ZHANG Guoqing, WANG Minjuan, et al. Development of environmentally friendly flexible medical X-ray shielding materials and analysis and optimization of their protective performance[J]. Chinese Journal of Radiological Medicine and Protection, 2023, 43(12): 1016-1021.
[22] 国家药品监督管理局. 医用诊断X射线辐射防护器具第1部分: 材料衰减性能的测定: YY/T 0292.1—2020/IEC 61331-1:2014[S]. 北京: 中国标准出版社, 2020.
[23] Berger M J, Hubbell J H. XCOM: photon cross sections on a personal computer: NBSIR 87-3597[R]. Gaithersburg: National Bureau of Standards, 1987.
[24] LV Yaqiong, ZHOU Qianwen, LI Yifan, et al. A predictive maintenance system for multi-granularity faults based on AdaBelief-BP neural network and fuzzy decision making[J]. Advanced Engineering Informatics, 2021, 49: 101318.
[25] LU Lu, MENG Xuhui, MAO Zhiping, et al. DeepXDE: a deep learning library for solving differential equations[J]. SIAM Review, 2021, 63(1): 208-228.
[26] Vardhan L A, Vasan A. Evaluation of penalty function methods for constrained optimization using particle swarm optimization[C]//2013 IEEE Second International Conference on Image Information Processing (ICIIP-2013). Shimla: IEEE, 2013: 487-492.
[27] Bell J. Machine learning:hands-on for developers and technical professionals[M]. 2nd ed. Hoboken: John Wiley & Sons, 2020.
[28] Géron A. Hands-on machine learning with scikit-learn, keras, and TENSORFLOW: concepts, tools, and techniques to build intelligent systems[M]. Sevastopol: O’Reilly Media, Inc., 2022.
[29] Baptista M L, Goebel K, Henriques E M P. Relation between prognostics predictor evaluation metrics and local interpretability SHAP values[J]. Artificial Intelligence, 2022, 306: 103667.
[30] Mirjalili S, Mirjalili S M, Lewis A. Grey wolf optimizer[J]. Advances in Engineering Software, 2014, 69: 46-61.
[31] Marini F, Walczak B. Particle swarm optimization (PSO). A tutorial[J]. Chemometrics and Intelligent Laboratory Systems, 2015, 149(Part B): 153-165.
[32] Mirjalili S, Mirjalili S. Genetic algorithm[J]. Evolutionary Algorithms and Neural Networks:Theory and Applications, 2019: 43-55.