基于机器学习算法的高放废物处置库屏障材料膨胀性能演化研究

摘要/Abstract

参考文献

Metrics

摘要： 高放废物处置库服役周期长且地质条件复杂,常规手段无法直接获取膨润土缓冲屏障膨胀性能演化趋势,本文尝试采用机器学习算法展开预测。利用在材料性能预测方面比较成熟的9种算法训练模型,探讨机器学习算法预测膨润土膨胀性能的可行性,通过分析其决定系数和均方根误差,遴选出神经网络算法为最优.引入我国北山候选处置库地球化学条件,预测出高庙子膨润土在高放废物处置库服役期间膨胀力呈“S”型演化;考虑蒙脱石含量、初始含水率、温度以及Na⁺浓度影响,缓冲屏障初始干密度建议值不小于1.58 g/cm³;若进一步考虑铁质储存罐Fe(Ⅱ)释放的影响,缓冲屏障初始干密度应进一步增大。本研究可为我国北山高放废物处置库地下试验室原位试验开展和缓冲屏障性能评价提供理论依据。

关键词: 膨润土, 高放废物处置库, 缓冲屏障, 膨胀性能, 机器学习

Abstract: High-level radioactive waste repository has a long service period and complex geological conditions. It is difficult for general tests to obtain the evolution trend of the swelling performance of bentonite buffer barrier under the working conditions of the repository. This paper attempts to use machine learning algorithms to research it. The model is trained by ten machine learning algorithms which is more mature in material performance prediction, the coefficient of determination and root mean square error of the above algorithms are compared and analyzed. The feasibility of machine learning algorithms in predicting the swelling performance of bentonite is discussed, and the neural network algorithm is selected as the best one. The geochemical condition of Beishan candidate repository in China is introduced. It is predicted that the swelling pressure evolution trend of Gaomiaozi bentonite during the service of high-level radioactive repository is ‘S’ type. The results show that considering the influence of dry density, montmorillonite content, initial moisture content and temperature, the recommended value of initial dry density of buffer barrier is not less than 1.58 g/cm³. If the effect of Fe(II) release from the iron container is further considered, the initial dry density of the buffer barrier should be further increased. This study can provide a theoretical basis for the in-situ experiment and buffer barrier performance evaluation of the underground laboratory of Beishan high-level waste radioactive repository in China.

Key words: bentonite, high-level radioactive waste repository, buffer barrier, swelling performance, machine learning

中图分类号:

TU42

张明, 胡栋科, 谢敬礼, 王赵明, 李小明, 周方亮, 赵留义. 基于机器学习算法的高放废物处置库屏障材料膨胀性能演化研究[J]. 辐射防护, 2025, 45(2): 157-166.

ZHANG Ming, HU Dongke, XIE Jingli, WANG Zhaoming, LI Xiaoming, ZHOU Fangliang, ZHAO Liuyi. Research on evolution of swelling performance of buffer barrier in high-level radioactive waste repository based on machine learning algorithms[J]. RADIATION PROTECTION, 2025, 45(2): 157-166.

[1] 刘月妙, 徐国庆, 刘淑芬. 高放废物地质处置库缓冲/回填材料性能测定[J]. 辐射防护, 1998,18(4): 52-57.
LIU Yuemiao, XU Guoqing, LIU Shufen. A study on buffer/backfill materials for hlw geological repository[J]. Radiation Protection, 1998,18(4): 52-57.
[2] ZHANG Chunliang, Kröhn K P. Sealing behaviour of crushed claystone-bentonite mixtures[J]. Geomechanics for Energy and the Environment, 2019, 17: 90-105.
[3] 刘月妙, 蔡美峰, 王驹. 高放废物处置库缓冲材料导热性能研究[J]. 岩石力学与工程学报, 2007(S2): 3891-3896.
LIU Yuemiao, CAI Meifeng, WANG Ju. Thermal properties of buffer material for high-level radioactive waste disposal[J]. Chinese Journal of Rock Mechanics and Engineering, 2007(S2): 3891-3896.
[4] 叶为民, Schanz T, 钱丽鑫, 等. 高压实高庙子膨润土GMZ01的膨胀力特征[J]. 岩石力学与工程学报, 2007(S2): 3861-3865.
YE Weimin, Schanz T, QIAN Lixin, et al. Characteristics of swelling pressure of densely compacted gaomiaozi bentonite GMZ01[J]. Chinese Journal of Rock Mechanics and Engineering, 2007(S2): 3861-3865.
[5] 刘月妙, 徐国庆, 刘淑芬, 等. 我国高放废物处置库缓冲/回填材料压实膨胀特性研究[J]. 铀矿地质, 2001, 17(1): 44-47.
LIU Yuemiao, XU Guoqing, LIU Shufen, et al. Study on compactibility and swelling property of buffer/backfili material for HLW pepository[J]. Uranium Geology, 2001, 17(1): 44-47.
[6] Tanaka Y, Watanabe Y. Modelling the effects of test conditions on the measured swelling pressure of compacted bentonite[J]. Soils and Foundations, 2019, 59(1): 136-150.
[7] RUAN Kunlin, WANG Hailong, Komine H, et al. Experimental study for temperature effect on swelling pressures during saturation of bentonites[J]. Soils and Foundations, 2022, 62(6): 101245.
[8] Mokni N, Cabrera J, Deleruyelle F. On the installation of an in situ large-scale vertical SEALing (VSEAL) experiment on bentonite pellet-powder mixture[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2023, 15(9): 2388-2401.
[9] Samper J, Mon A, Montenegro L. A revisited thermal, hydrodynamic, chemical and mechanical model of compacted bentonite for the entire duration of the FEBEX in situ test[J]. Applied Clay Science, 2018, 160: 58-70.
[10] ZHENG Liange, Samper J, Montenegro L. A coupled THC model of the FEBEX in situ test with bentonite swelling and chemical and thermal osmosis[J]. Journal of Contaminant Hydrology, 2011, 126(1/2): 45-60.
[11] DA Tianxing, CHEN Tao, HE Wenke, et al. Applying machine learning methods to estimate the thermal conductivity of bentonite for a high-level radioactive waste repository[J]. Nuclear Engineering and Design, 2022, 392: 111765.
[12] HU Guang, Pfingsten W. Data-driven machine learning for disposal of high-level nuclear waste: A review[J]. Annals of Nuclear Energy, 2023, 180: 109452.
[13] Bishnoi S, Singh S, Ravinder R, et al. Predicting young’s modulus of oxide glasses with sparse datasets using machine learning[J]. Journal of Non-crystalline Solids, 2019, 524: 119643.
[14] Bang H T, Yoon S, Jeon H. Application of machine learning methods to predict a thermal conductivity model for compacted bentonite[J]. Annals of Nuclear Energy, 2020, 142: 107395.
[15] FENG Zhengye, GAO Zepeng, WANG Yongjia, et al. Application of machine learning to study the effective diffusion coefficient of Re(Ⅶ) in compacted bentonite[J]. Applied Clay Science, 2023, 243: 107076.
[16] Ebiwonjumi B, Cherezov A, Dzianisau S, et al. Machine learning of LWR spent nuclear fuel assembly decay heat measurements[J]. Nuclear Engineering and Technology, 2021, 53(11): 3563-3579.
[17] 崔素丽, 张虎元, 刘吉胜, 等. 混合型缓冲回填材料膨胀变形试验研究[J]. 岩土力学, 2011, 32(3): 684-691+696.
CUI Suli, ZHANG Huyuan, LIU Jisheng, et al. Experimental study of swelling deformation for compacted bentonite-sand mixture as buffer material[J]. Rock and Soil Mechanics, 2011, 32(3): 684-691+696.
[18] 孙德安, 张龙. 盐溶液饱和高庙子膨润土膨胀特性及预测[J]. 岩土力学, 2013(10): 2790-2795.
SUN Dean, ZHANG Long. Swelling characteristics of Gaomiaozi bentonite saturated by salt solution and their prediction[J]. Rock and Soil Mechanics, 2013(10): 2790-2795.
[19] 陈永贵, 刘聪, 马婧, 等. 盐碱演化环境下高压实GMZ膨润土膨胀变形特性[J]. 岩土工程学报, 2023, 45(4): 690-698.
CHEN Yonggui, LIU Cong, MA Jing, et al. Swelling characteristics of compacted GMZ bentonite with saline-alkali evolution solutions[J]. Chinese Journal of Geotechnical Engineering, 2023, 45(4): 690-698.
[20] Miettinen H, Bomberg M, Bes R, et al. Transformation of inherent microorganisms in Wyoming-type bentonite and their effects on structural iron[J]. Applied Clay Science, 2022, 221: 106465.
[21] Navarro V, Asensio L, Gharbieh H, et al. A triple porosity hydro-mechanical model for MX-80 bentonite pellet mixtures[J]. Engineering Geology, 2020, 265: 105311.
[22] 鲁文玥, 刘月妙, 谢敬礼, 等. 高庙子钠基膨润土的膨胀性能研究[J]. 中国矿业, 2020, 29(3): 177-182.
LU Wenyue, LIU Yuemiao, XIE Jingli, et al. Swelling of different Gaomiaozi sodium-based bentonites[J]. China Mining Magazine, 2020, 29(3): 177-182.
[23] CHEN Yonggui, LIU Lina, YE Weimin, et al. Deterioration of swelling pressure of compacted Gaomiaozi bentonite induced by heat combined with hyperalkaline conditions[J]. Soils and Foundations, 2019, 59(6): 2254-2264.
[24] XU Hongzhang, HE Hongjie, ZHANG Ying, et al. A comparative study of loss functions for road segmentation in remotely sensed road datasets[J]. International Journal of Applied Earth Observation and Geoinformation, 2023, 116: 103159.
[25] Topuz B, Çakici Alp N. Machine learning in architecture[J]. Automation in Construction, 2023, 154: 105012.
[26] 刘晓燕, 刘路路, 蔡国军, 等. 温度和盐/碱作用下膨润土-砂-石墨缓冲材料膨胀力性能演化[J]. 岩土工程学报, 2023, 45(12): 2463-2471.
LIU Xiaoyan, LIU Lulu, CAI Guojun, et al. Evolution of swelling pressure properties of bentonite-sand-graphite buffer materials under action of temperature and salt/alkali[J]. Chinese Journal of Geotechnical Engineering, 2023, 45(12): 2463-2471.
[27] ZHANG Qichao, ZHENG Min, HUANG Yanliang, et al. Long term corrosion estimation of carbon steel, titanium and its alloy in backfill material of compacted bentonite for nuclear waste repository[J]. Scientific Reports, 2019, 9(1): 3195.
[28] 张虎元, 张明, 崔素丽, 等. 混合型缓冲回填材料土水特征曲线测试与修正[J]. 岩石力学与工程学报, 2011, 30(2): 382-390.
ZHANG Huyuan, ZHANG Ming, CUI Suli, et al. Determination and modification of soil-water characteristic curves of bentonite-sand mixtures as high-level waste backfill/buffer material[J]. Chinese Journal of Rock Mechanics and Engineering, 2011, 30(2): 382-390.
[29] 陈永贵, 蒯琪, 叶为民, 等. 高压实膨润土膨胀力预测研究[J]. 同济大学学报(自然科学版), 2018, 46(12): 1628-1636.
CHEN Yonggui, KUAI Qi, YE Weimin, et al. Prediction of swelling pressure for compacted bentonite[J]. Journal of Tongji University(Natural Science), 2018, 46(12): 1628-1636.
[30] 王建威. 高放废物处置库缓冲/回填材料膨胀性能研究[D]. 绵阳: 西南科技大学, 2015.
[31] 项国圣, 方圆, 徐永福. 阳离子交换对高庙子钠基膨润土膨胀性能的影响[J]. 浙江大学学报版(工学版), 2017, 51(5): 931-936.
XIANG Guosheng, FANG Yuan, XU Yongfu. Swelling characteristics of GMZ01 bentonite affected by cation exchange reaction[J]. Journal of Zhejiang University(Engineering Science), 2017, 51(5): 931-936.
[32] 张虎元, 梁健, 刘吉胜, 等. 混合型缓冲回填材料压实性能研究[J]. 岩石力学与工程学报, 2009, 28(12): 2585-2592.
ZHANG Huyuan, LIANG Jian, LIU Jisheng, et al. Compaction properties of bentonite-sand mixture as buffer material for hlw disposal[J]. Chinese Journal of Rock Mechanics and Engineering, 2009, 28(12): 2585-2592.

Just accepted

Online first

Just accepted

Online first

Viewed

Full text

	From	local

	Times	1
	Rate	100%

Abstract

Just accepted	Online first	Issue

0	0	12

	From	Others

	Times	12
	Rate	100%

Cited

Web of Science	Crossref	ScienceDirect	Search for Citations in Google Scholar >>


This page requires you have already subscribed to WoS.

Shared