VULNERABILITY ANALYSIS OF NPP EQUIPMENT BASED ON NEURAL NETWORK
-
摘要: 核电结构的易损性分析是核电厂地震安全评估中至关重要的一环, 但是由于核电结构的复杂性以及考虑土−结相互作用(SSI)时较大的计算规模, 使得计算核电厂设备易损性曲线十分耗时. 为发展高效的核电厂设备易损性分析方法, 本文采用核电结构土−结相互作用分析的分区计算方法, 并利用有限的SSI分析结果建立神经元模型(ANN)代替有限元模型(FEM), 分别基于对数正态假定的回归法和蒙特卡洛法进行了设备易损性分析. ANN数值模拟包括了以下内容: (1)基于半偏相关系数选择最相关的地震动参数作为ANN输入, 并通过交叉检验建立神经元模型; (2)量化研究ANN数值模拟的预测不确定性, 其中包含了由于简化地震动输入引起的随机不确定性和训练样本缺失引起的认知不确定性; (3)基于ANN模型预测结果分别采用蒙特卡洛法和基于对数正态假定的回归法进行设备的易损性分析. 本文探讨了不同的地震强度指标以及土层材料的不确定性对易损性曲线的影响, 同时验证了回归法中对数正态模型假定的基本合理性, 为核电厂设备易损性分析提供了一种可能方向.
-
关键词:
- 易损性分析 /
- 人工神经网络 /
- 蒙特卡洛法 /
- 预测不确定性 /
- 概率土−结构相互作用
Abstract: The vulnerability analysis is a vital part of the seismic probabilistic risk assessment of nuclear power plants. However, due to the complexity of nuclear power structures and the larger calculation scale, the vulnerability analysis of NPP equipment is very time consuming when considering soil-structure interaction (SSI). In order to develop an efficient vulnerability analysis method, this paper adopts a partition calculation method applied to NPP SSI analysis, and establishes an artificial neural network (ANN) using limited SSI analysis results to substitute the FEM process. Based on the regression method with log-normal assumption and Monte Carlo method to analyze the equipment vulnerability. The ANN numerical simulation includes the following contents: (1) Establish the best ANN model through cross-validation to substitute the FEM process, and the most relevant ground motion parameters are selected as the ANN input based on the semi-partial correlation coefficient; (2) Quantification and investigation of the ANN prediction uncertainty. It includes the aleatory uncertainty caused by the simplification of the seismic inputs and the epistemic uncertainty from the limited size of the training data; (3) Computation of fragility curves with Monte Carlo method and the regression method with log-normal assumption based on the prediction data of ANN model. This paper explores the impact on fragility curves induced by different seismic intensity measures and uncertainty of soil material. Meanwhile, the results verify the basic rationality of the lognormal assumption and provide a possible direction for the vulnerability analysis of NPP equipment.-
Key words:
- vulnerability analysis /
- ANN /
- MC method /
- forecast uncertainty /
- probabilistic SSI
-
图 6 Case2工况下ANN训练过程: (a) ANN训练结果; (b) ANN残差分布; (c)认知不确定性
Figure 6. ANN training process under Case2 conditions: (a) ANN training results; (b) ANN residual distribution; (c) epistemic uncertainty
图 9 不考虑土层材料不确定性(Case3)和考虑土层材料不确定性(Case5)的易损性曲线
Figure 9. Fragility curves without considering soil material uncertainty (Case3) and considering soil material uncertainty (Case5)
表 1 核电材料不确定性
Table 1. Uncertainties in material parameters of NPP
Type Distribution E/GPa C.V NAB Log-norm 24.7 0.2 NSB Log-norm 32.9 0.2 SCV Log-norm 210.0 0.2 
下载: 导出CSV
表 2 土层材料不确定性
Table 2. Uncertainties in material parameters of soil
Layer H/m Distribution Vs(m/s2) C.V L1 20 Log-norm 560 0.2 L2 20 Log-norm 673 0.2 L3 20 Log-norm 794 0.2
下载: 导出CSV
表 3 地震动特征值
Table 3. Seismic intensity measures
IMs Definition R Rsp PGA $ \max \left| {a(t)} \right| $ 0.73 0.18 PGV $ \max \left| {v(t)} \right| $ 0.29 −0.13 PGD $ \max \left| {d(t)} \right| $ 0.36 0.07 IA $\dfrac{ {\text{π} } }{ {2 g} }\displaystyle\int_0^{ {t_{ {\text{total} } } }} {a{ {(t)}^2}{\rm{d}}t}$ 0.49 −0.03 CAV $\displaystyle\int_0^{ {t_{ {\text{total} } } }} {\left| {a(t)} \right|{\rm{d}}t}$ 0.38 0.03 PSamax $ \max (PSa(T)) $ 0.58 −0.03 Tp $ \arg \max (PSa(T)) $ −0.26 0.16 ASA $\displaystyle\int_5^{33} {PSa(f){\rm{d}}f}$ 0.85 0.33 注: R为相关系数, RSP为半偏相关系数
下载: 导出CSV
-
[1] Kennedy RP, Cornell CA, Campbell RD, et al. Probabilistic seismic safety study of an existing nuclear power plant. Nuclear Engineering and Design, 1980, 59(2): 315-338 doi: 10.1016/0029-5493(80)90203-4 [2] Kennedy RP, Ravindra MK. Seismic fragilities for nuclear power plant risk studies. Nuclear Engineering and Design, 1984, 79(1): 47-68 doi: 10.1016/0029-5493(84)90188-2 [3] Vamvatsikos D, Cornell CA. Incremental dynamic analysis. Earthquake Engineering and Structural Dynamics, 2002, 31(3): 491-514 doi: 10.1002/eqe.141 [4] Vamvatsikos D, Cornell CA. Applied incremental dynamic analysis. Earthquake Spectra, 2004, 20(2): 523-553 doi: 10.1193/1.1737737 [5] Shinozuka M, Feng MQ, Lee J, et al. Statistical analysis of fragility curves. Journal of Engineering Mechanics, 2000, 126(12): 1224-1231 doi: 10.1061/(ASCE)0733-9399(2000)126:12(1224) [6] Zentner I. Numerical computation of fragility curves for NPP equipment. Nuclear Engineering and Design, 2010, 240(6): 1614-1621 doi: 10.1016/j.nucengdes.2010.02.030 [7] Cornell CA, Jalayer F, Hamburger RO, et al. Probabilistic basis for 2000 SAC federal emergency management agency steel moment frame guidelines. Journal of Structural Engineering, 2002, 128(4): 526-533 doi: 10.1061/(ASCE)0733-9445(2002)128:4(526) [8] Zentner I, Humbert N, Ravet S, et al. Numerical methods for seismic fragility analysis of structures and components in nuclear industry application to a reactor coolant system. Georisk Assessment and Management of Risk for Engineered Systems and Geohazards, 2011, 5(2): 99-109 doi: 10.1080/17499511003630512 [9] ASCE/SEI 4-16. Seismic analysis of safety-related nuclear structures. American Society of Civil Engineers, 2017 [10] Unnikrishnan VU, Prasad AM, Rao BN. Development of fragility curves using high-dimensional model representation. Earthquake Engineering & Structural Dynamics, 2013, 42: 419-430 [11] Mangalathu S, Jeon JS, Desroches R. Critical uncertainty parameters influencing seismic performance of bridges using lasso regression. Earthquake Engineering & Structural Dynamics, 2018, 47: 784-801 [12] Calabrese A, Lai CG. Fragility functions of blockwork wharves using artificial neural networks. Soil Dynamics and Earthquake Engineering, 2013, 52: 88-102 doi: 10.1016/j.soildyn.2013.05.002 [13] Wang ZY, Zentner I, Zio E. A Bayesian framework for estimating fragility curves based on seismic damage data and numerical simulations by adaptive neural networks. Nuclear Engineering and Design, 2018, 338: 232-246 doi: 10.1016/j.nucengdes.2018.08.016 [14] Wang ZY, Pedroni N, Zentner I, et al. Seismic fragility analysis with artificial neural networks: Application to nuclear power plant equipment. Engineering Structures, 2018, 162: 213-225 doi: 10.1016/j.engstruct.2018.02.024 [15] 谷音, 郑文婷, 卓卫东. 基于LHS-MC方法的矮塔斜拉桥地震风险概率分析. 工程力学, 2013, 30(8): 96-102 + 110 (Gu Yin, Zheng Wenting, Zhuo Weidong. Analysis of seismic risk probability assessment of lower-tower cable-stayed bridge based on LHS-MC method. Engineering Mechanics, 2013, 30(8): 96-102 + 110 (in Chinese) doi: 10.6052/j.issn.1000-4750.2012.04.0256 [16] ASCE/SEI 43-05. Seismic design criteria for structures, systems, and components in nuclear facilities. American Society of Civil Engineers, 2005 [17] Idriss IM, Sun JI. User's manual for shake91- A computer program for conducting equivalent linear seismic response analyses of horizontally layered soil deposits. Center for Geotechnical Modeling, Department of Civil & Environmental Engineering, UC Davis, 1992 [18] 陈少林, 张娇, 郭琪超等. 非水平成层场地上核电结构时域土–结相互作用分析. 岩土工程学报, 2020, 42(2): 308-316 (Chen Shaolin, Zhang Jiao, Guo Qichao, et al. Time-domain soil-structure interaction analysis of nuclear facilities on non-horizontal layered site. Chinese Journal of Geotechnical Engineering, 2020, 42(2): 308-316 (in Chinese) [19] 陈少林, 陆新宇, 赵宇昕. 考虑基础柔性的土-结动力相互作用分区显-隐式分析算法. 自然灾害学报, 2020, 29(3): 9-19 (Chen Shaolin, Lu Xinyu, Zhao Yuxin. Explicit-implicit algorithm for analysis of three-dimensional soil-foundation-structure dynamic interaction. Journal of Natural Disasters, 2020, 29(3): 9-19 (in Chinese) [20] 陈少林, 郭琪超, 周国良. 核电结构土-结相互作用分析分区混合计算方法. 力学学报, 2020, 52(1): 258-282 (Chen Shaolin, Guo QiChao, Zhou Guoliang. Partitioned hybrid method for soil-structure interaction analysis of nuclear power structure. Chinese Journal of Theoretical and Applied Mechanics, 2020, 52(1): 258-282 (in Chinese) doi: 10.6052/0459-1879-19-271 [21] 陈少林, 宗娟. 平面波任意角度入射时波动散射问题输入的一种实现方法. 固体力学学报, 2018, 39(1): 80-89 (Chen Shaolin, Zong Juan. Wave input method for three-dimensional wave scattering simulation of an incident wave in an arbitrary direction. Chinese Journal of Solid Mechanics, 2018, 39(1): 80-89 (in Chinese) [22] 周开利. 神经网络模型及其MATLAB仿真程序设计. 北京: 清华大学出版社, 2005: 69-90Zhou Kaili. Neural Network Model and MATLAB Simulation Program Design. Beijing: Tsinghua University Press, 2005: 69-90 (in Chinese) [23] 姚俊. 半偏相关系数的计算公式及其应用. 统计与决策, 2011(5): 4-7 (Yao Jun. Calculation formula of semi-partial correlation coefficient and its application. Statistics and Decision, 2011(5): 4-7 (in Chinese) [24] Zio E. A study of the bootstrap method for estimating the accuracy of artificial neural networks in predicting nuclear transient processes. IEEE Transactions on Nuclear Science, 2006, 53(3): 1460-1478 doi: 10.1109/TNS.2006.871662 [25] Chryssolouris G, Lee M, Ramsey A. Confidence interval prediction for neural network models. IEEE Transactions on Neural Networks, 1996, 7(1): 229-232 doi: 10.1109/72.478409 [26] 周国良, 唐晖, 魏超等. 新型压水堆核电厂核岛厂房结构地震反应分析. 第22届全国结构工程学术会议论文集第Ⅲ册, 2013Zhou Guoliang, Tang Hui, Wei Chao, et al. Seismic response analysis of advanced power nuclear island buildings. Proceedings of the 22 nd National Structural Engineering Conference Volume III, 2013(in Chinese) [27] Liel AB, Haselton CB, Deierlein GG, et al. Incorporating modeling uncertainties in the assessment of seismic collapse risk of buildings. Structural Safety, 2009, 31(2): 197-211 doi: 10.1016/j.strusafe.2008.06.002 [28] Mangalathu S, Jeon JS, Desroches R. Critical uncertainty parameters influencing seismic performance of bridges using lasso regression. Earthquake Engineering & Structural Dynamics, 2018 [29] 尚昆. 考虑SSI效应的核电厂安全壳及内部结构抗震能力评估[硕士论文]. 哈尔滨工业大学, 2014: 15-17Shang Kun. Seismic assessment of nuclear power plants containment and internal structure considering SSI [Master’s Thesis]. Harbin Institute of Technology, 2014: 15-17 (in Chinese) [30] 王晓磊. 基于场地危险性和目标谱的核电安全壳概率地震风险分析[博士论文]. 哈尔滨工业大学, 2018: 18-38Wang Xiaolei. Seismic probabilistic risk analysis for nuclear power plant containments based on site-specific hazard and target spectra [PhD Thesis]. Harbin Institute of Technology, 2018: 18-38 (in Chinese) [31] 纪春玲, 董博. 山东某场地概率地震危险性分析. 地震地磁观测与研究, 2017, 38(4): 53-64 (Ji Chunlin, Dong Bo. Probabilistic seismic hazard analysis of a site in Shandong Province. Seismological and Geomagnetic Observation and Research, 2017, 38(4): 53-64 (in Chinese) doi: 10.3969/j.issn.1003-3246.2017.04.010 [32] 俞言祥, 汪素云. 中国东部和西部地区水平向基岩加速度反应谱衰减关系. 震灾防御技术, 2006, 1(3): 206-217 (Yu Yanxiang, Wang Suyun. Attenuation relations for horizontal peak ground acceleration and response spectrum in eastern and western china. Earthquake Disaster Prevention Technology, 2006, 1(3): 206-217 (in Chinese) doi: 10.3969/j.issn.1673-5722.2006.03.005 [33] 李小军, 侯春林, 戴志军等. 核岛结构设计地基场地及计算基底效应研究. 岩土力学, 2015, 36(8): 8 (Li Xiaojun, Hou Chunlin, Dai Zhijun, et al. Research on the effects of soil layers and bedrock on designing the foundation of nuclear island structure. Geotechnical Mechanics, 2015, 36(8): 8 (in Chinese) -
下载:
点击查看大图
图(9) / 表(3)
计量
- 文章访问数: 11
- HTML全文浏览量: 4
- PDF下载量: 3
- 被引次数: 0
