随机和区间变量共存条件下的模型确认指标

doi:10.13700/j.bh.1001-5965.2017.0345

北京航空航天大学学报 ›› 2018, Vol. 44 ›› Issue (5): 967-974.doi: 10.13700/j.bh.1001-5965.2017.0345

随机和区间变量共存条件下的模型确认指标

赵录峰¹, 吕震宙¹, 阚丽娟²

1. 西北工业大学航空学院, 西安 71007;
2. 空军工程大学装备管理与安全工程学院, 西安 710051

收稿日期:2017-05-22 出版日期:2018-05-20 发布日期:2017-09-18
通讯作者: 吕震宙 E-mail:zhenzhoulu@nwpu.edu.cn
作者简介:赵录峰,男,博士研究生。主要研究方向:可靠性工程、模型确认;吕震宙,女,教授,博士生导师。主要研究方向:可靠性工程、灵敏度分析、模型确认和多学科优化;阚丽娟,女,博士研究生。主要研究方向:安全性工程。
基金资助:
国家自然科学基金（51475370）；中央高校基本科研业务费专项资金（3102015BJ（Ⅱ）CG009）

A validation metric for model with mixture of random and interval variables

ZHAO Lufeng¹, LYU Zhenzhou¹, KAN Lijuan²

1. School of Aeronautics, Northwestern Polytechnical University, Xi'an 71007;
2. Equipment Management and Safety Engineering College, Air Force Engineering University, Xi'an 710051, China

Received:2017-05-22 Online:2018-05-20 Published:2017-09-18

摘要/Abstract

摘要： 现有的不确定性模型确认方法建立在概率理论基础之上，仅仅适用于随机不确定性因素影响下的模型确认，而不适合随机和区间变量共存条件下的模型确认问题。针对这一问题，研究了随机和区间变量共存条件下的模型确认方法。首先，分析了随机和区间变量共存条件下数学模型的特点；然后，运用概率方法和区间理论，提出了一种新的模型确认指标，通过模型响应量的上下界分布函数（CDF）与实验响应量的上下界经验CDF之间差异，来度量随机和区间输入变量共存条件下模型预测与实际物理实验结果之间的不一致性；讨论了所提指标的数学性质，给出了指标的计算方法和步骤；最后，采用一个数字算例和一个工程算例验证了所提指标在随机和区间输入变量共存条件下进行模型确认的可行性和有效性。

关键词: 模型确认, 指标, 随机变量, 区间变量, 混合模型

Abstract: The existing model validation methods under uncertainty based on theory of probability are only applicable to validate model with random variables, but inapplicable to validate model with the mixture of random and interval variables. To address this issue, the validation method for model with the mixture of random and interval variables is studied in this paper. First, the characteristics of the mathematical model with the mixture of random and interval variables are analyzed. Second, a new validation metric is proposed by using interval theory and probability method. This metric provides a comparison between the cumulative distribution functions (CDFs) of the upper and the lower bounds of the model responses and the empirical CDFs of the upper and the lower bounds of the experimental responses to show the disagreement between the quantitative predictions from a model and the physical observations. The mathematical properties of the new metric are discussed, and its estimation method and procedures are presented. Finally, the feasibility and effectiveness of the proposed validation metric are illustrated by a numerical test case and an engineering application with mixture of random and interval variables.

Key words: model validation, metric, random variables, interval variables, mixed model

中图分类号:

赵录峰, 吕震宙, 阚丽娟. 随机和区间变量共存条件下的模型确认指标[J]. 北京航空航天大学学报, 2018, 44(5): 967-974.

ZHAO Lufeng, LYU Zhenzhou, KAN Lijuan. A validation metric for model with mixture of random and interval variables[J]. JOURNAL OF BEIJING UNIVERSITY OF AERONAUTICS AND A, 2018, 44(5): 967-974.

参考文献

[1] OBERKAMPF W L,ROY C J.Verification and validation in scientific computing[M].New York:Cambridge University Press,2010:21-25.
[2] OBERKAMPF W L,BARONE M F.Measures of agreement between computation and experiment:Validation metrics[J].Journal of Computational Physics,2006,217:5-36.
[3] OBERKAMPF W L,SINDIR M,CONLISK A.Guide for the verification and validation of computational fluid dynamics simulations[M].Reston:AIAA,1998:2-4.
[4] XIONG Y,CHEN W,TSUI K L,et al.A better understanding of model updating strategies in validating engineering models[J].Compute Methods in Applied Mechanics and Engineering,2009,189(15-16):1327-1337.
[5] MESSER M,PANCHAL J H,KRISHNAMURTHY V,et al.Model selection under limited information using a value of information based indicator[J].Journal of Mechanical Design,2010,132(12):121008.
[6] KENNEDY M C,O'HAGAN A.Bayesian calibration of computer models[J].Journal of the Royal Statistical Society,2001,63(3):425-464.
[7] BAYARRI M J,BERGER J O,PAULO R,et al.A framework for validation of computer models[J].Technometrics,2007,49(2):138-154.
[8] ARENDT P D,APLEY D W,CHEN W,et al.Improving identifiability in model calibration using multiple responses[J].Journal of Mechanical Design,2012,134(10):100909.
[9] ARENDT P D,APLEY D W,CHEN W.Quantification of model uncertainty:Calibration,model discrepancy,and identifiability[J].Journal of Mechanical Design,2012,134(10):100908.
[10] LIU Y,CHEN W,ARENDT P,et al.Toward a better understanding of model validation metrics[J].Journal of Mechanical Design,2011,133(7):071005.
[11] REBBA R,MAHADEVAN S.Validation of models with multivariate output[J].Reliability Engineering and System Safety,2006,91(8):861-871.
[12] FERSON S,OBERKAMPF W L.Validation of imprecise probability models[J].International Journal of Reliability and Safety,2009,3:3-22.
[13] FERSON S,OBERKAMPF W L,GINZBURG L.Model validation and predictive capability for the thermal challenge problem[J].Computer Methods in Applied Mechanics and Engineering,2008,197(29-32):2408-2430.
[14] 赵录峰,吕震宙,张磊刚,等.多输出模型确认中的混合矩指标[J].国防科技大学学报,2015,37(6):61-68.ZHAO L F,LYU Z Z,ZHANG L G,et al.Mixed moment validation metric for models with multivariate output[J].Journal of National University of Defense Technology,2015,37(6):61-68(in Chinese).
[15] LI W,CHEN W,JIANG Z,et al.New validation metrics for models with multiple correlated responses[J].Reliability Engineering and System Safety,2014,127:1-11.
[16] ZHAO L F,LU Z Z,YUN W Y,et al.Validation metric based on Mahalanobis distance for models with multiple correlated responses[J].Reliability Engineering and System Safety,2017,159:80-89.
[17] 胡嘉蕊,吕震宙.基于核主成分分析的多输出模型确认方法[J].北京航空航天大学学报,2017,43(7):1470-1480.HU J R,LYU Z Z.Model validation model with multivariate output based on kernel principal component analysis[J].Journal of Beijing University of Aeronautics and Astronautics,2017,43(7):1470-1480(in Chinese).

随机和区间变量共存条件下的模型确认指标

A validation metric for model with mixture of random and interval variables

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	刘朝霞, 孙宇锋, 轩杰, 许智宏, 赵广燕. 考虑多因素的可修系统任务可靠性分配方法[J]. 北京航空航天大学学报, 2019, 45(4): 834-840.
[2]	程蕾, 张磊刚, 雷豹, 梁祖典, 刘鹏. 一种平均矩独立重要性指标及其拒绝抽样方法[J]. 北京航空航天大学学报, 2019, 45(1): 66-73.
[3]	宋飞, 杨扬, 杨昆, 张愫, 毕东升. 基于双特征的丘陵山区耕地低空遥感图像配准算法[J]. 北京航空航天大学学报, 2018, 44(9): 1952-1963.
[4]	张佳乐, 钱红燕, 成翔, 陈兵. 一种软件定义卫星网络的多波束切换机制[J]. 北京航空航天大学学报, 2018, 44(12): 2503-2509.
[5]	成凯, 吕震宙, 石岩. 基于可能性矩的混合不确定性全局灵敏度分析[J]. 北京航空航天大学学报, 2017, 43(8): 1705-1712.
[6]	胡嘉蕊, 吕震宙. 基于核主成分分析的多输出模型确认方法[J]. 北京航空航天大学学报, 2017, 43(7): 1470-1480.
[7]	员婉莹, 吕震宙, 蒋献, 杨彩琼. 可靠性全局灵敏度指标的空间分割高效方法[J]. 北京航空航天大学学报, 2017, 43(6): 1199-1207.
[8]	唐伟财, 陈善广, 肖毅, 姜国华, 田志强. 空间立体信息缺失对机械臂遥操作任务的影响[J]. 北京航空航天大学学报, 2017, 43(2): 335-343.
[9]	李琪, 高占宝, 李善营, 李宝安. 变工况条件下基于相似性的剩余使用寿命预测方法[J]. 北京航空航天大学学报, 2016, 42(6): 1236-1243.
[10]	张耀天, 张旭成, 贾明顺, 薛向上. 基于层次分析法的自适应决策评价方法[J]. 北京航空航天大学学报, 2016, 42(5): 1065-1070.
[11]	员婉莹, 吕震宙, 牟珊珊. 一种高效计算各类基于方差灵敏度指标的方法[J]. 北京航空航天大学学报, 2016, 42(4): 796-805.
[12]	张修远, 常欣, 李想, 杨放青. 基于改进ELECTRE法的舰船气流场方案评估方法[J]. 北京航空航天大学学报, 2016, 42(11): 2507-2515.
[13]	许俊飞, 邢昌风, 吴玲. 基于解析规则的舰艇区域防空作战能力需求生成[J]. 北京航空航天大学学报, 2016, 42(1): 193-200.
[14]	钟睿. 基于动力学递推算法的绳系卫星系统刚柔耦合多体模型[J]. 北京航空航天大学学报, 2015, 41(7): 1188-1195.
[15]	李强, 王中宇, 王卓然, 燕虎. 压力传感器激波管校准条件下的动态参数估计[J]. 北京航空航天大学学报, 2015, 41(7): 1223-1230.