模型重要更新参数选择能够在保证预测精度的前提下有效缓解高维贝叶斯模型更新中的“维度灾难”问题。针对基于计算模型的重要更新参数选择方法难以直接反映参数对模型预测误差影响的问题，通过将似然函数作为Sobol全局灵敏度方法的评估函数，实现了输入参数对模型预测误差影响的定量评估，并提出基于似然函数总Sobol指标累积和的重要参数选择方法。进一步基于随机与认知不确定性贡献分离框架，构建了随机和认知不确定性分离条件下的重要更新参数选择与贝叶斯更新方法，该方法能够有效识别对模型预测误差起主导作用且具有可缩减不确定性的重要认知参数并进行更新。通过算例表明，在随机不确定条件下，所提方法在显著减少待更新参数数量的同时，能够获得与多参数更新甚至全参数更新相当的预测精度与不确定性缩减效果；在随机与认知不确定性分离条件下所提方法能够稳定识别影响模型预测误差的重要认知参数，避免对包含随机不确定性的参数的无效或冗余更新。研究结果进一步表明，在模型更新过程中区分随机不与认知不确定性对于降低更新维度以及增强更新结果的物理可解释性具有重要意义。
The selection of important updating parameters can effectively alleviate the “curse of dimensionality” in high-dimensional Bayesian model updating while maintaining prediction accuracy. However, existing methods for se-lecting important updating parameters based on computational models often fail to directly reflect the influence of input parameters on model prediction errors. To address this issue, the likelihood function is introduced as the evaluation function in the Sobol global sensitivity analysis framework, enabling a quantitative assessment of the influence of input parameters on model prediction errors. Based on this framework, an important parameter selec-tion method is proposed using the cumulative sum of total Sobol indices derived from the likelihood function. Fur-thermore, within a framework that separates the contributions of aleatory and epistemic uncertainties, an important updating parameter selection and Bayesian updating method under the separation of aleatory and epistemic un-certainties is developed. This method can effectively identify important epistemic parameters that dominate the model prediction error and possess reducible uncertainty for updating. Numerical examples demonstrate that, un-der aleatory uncertainty conditions, the proposed method can significantly reduce the number of parameters to be updated while achieving prediction accuracy and uncertainty reduction comparable to those obtained from multi-parameter or even full-parameter updating. Under the condition of separating aleatory and epistemic uncertainties, the proposed method can stably identify important epistemic parameters that influence model prediction errors, thereby avoiding ineffective or redundant updating of parameters associated with aleatory uncertainty. The results further indicate that distinguishing between aleatory and epistemic uncertainties during the model updating process is essential for reducing the updating dimensionality and enhancing the physical interpretability of the updating results.
[1]Capiez-Lernout E, Pellissetti M, Pradlwarter H, et al.Data and model uncertainties in complex aerospace engineering systems[J].Journal of Sound and Vibration, 2006, 295(3-5):923-938
[2]Simoen E, De Roeck G, Lombaert G.Dealing with un-certainty in model updating for damage assessment: A re-view[J].Mechanical Systems and Signal Processing, 2015, 56:123-149
[3]Wang Y, Zhao D, Li H.Finite element model updating technique for super High-Rise Building based on response surface method[J].Buildings, 2025, 15(1):126-
[4]Bai Y, Peng Z, Wang Z.A finite element model updating method based on the trust region and adaptive surrogate model[J]. Journal of Sound and Vibration, 2023, 555: 117701.
[5]Zhang E L, Feissel P, Antoni J.A comprehensive Bayesi-an approach for model updating and quantification of modeling errors[J].Probabilistic engineering mechanics, 2011, 26(4):550-560
[6]Bi S, Beer M, Zhang J, et al.Optimization or Bayesian strategy? Performance of the Bhattacharyya distance in different algorithms of stochastic model updating[J].ASCE-ASME Journal of Risk and Uncertainty in Engi-neering Systems, Part B: Mechanical Engineering, 2021, 7(2):020903-
[7]Straub D, Papaioannou I.Bayesian updating with struc-tural reliability methods[J].Journal of Engineering Me-chanics, 2015, 141(3):04014134-
[8]Wan H P, Ren W X.Parameter selection in finite-element-model updating by global sensitivity analysis us-ing Gaussian process metamodel[J].Journal of Structural Engineering, 2015, 141(6):04014164-
[9]Patel D V, Ray D, Oberai A A.Solution of physics-based Bayesian inverse problems with deep generative priors[J]. Computer Methods in Applied Mechanics and Engineer-ing, 2022, 400: 115428.
[10]Mottershead J E, Mares C, Friswell M I, et al.Selection and updating of parameters for an aluminium space-frame model[J].Mechanical Systems and Signal Pro-cessing, 2000, 14(6):923-944
[11]Morris M D.Factorial sampling plans for preliminary computational experiments[J].Technometrics, 1991, 33(2):161-174
[12]McRae G J, Tilden J W, Seinfeld J H.Global sensitivity analysis—a computational implementation of the Fourier amplitude sensitivity test (FAST)[J].Computers & Chemical Engineering, 1982, 6(1):15-25
[13]Sobol I M.Global sensitivity indices for nonlinear math-ematical models and their Monte Carlo estimates[J].Mathematics and computers in simulation, 2001, 55(1-3):271-280
[14]Jafari M, Akbari K.Global sensitivity analysis approach-es applied to parameter selection for numerical model-updating of structures[J].Engineering Computations, 2019, 36(4):1282-1304
[15]Sankararaman S, Mahadevan S.Separating the contribu-tions of variability and parameter uncertainty in probabil-ity distributions[J]. Reliability Engineering & System Safety, 2013, 112: 187-199.
[16]Beck J L, Au S K.Bayesian updating of structural mod-els and reliability using Markov chain Monte Carlo simu-lation[J].Journal of engineering mechanics, 2002, 128(4):380-391
[17]Blei D M, Kucukelbir A, McAuliffe J D.Variational inference: A review for statisticians[J].Journal of the American statistical Association, 2017, 112(518):859-877
[18]张峰, 吕震宙.可靠性灵敏度分析的自适应重要抽样法[J].工程力学, 2008, 25(4):80-84
[19]ZHANG F, LU Z Z.An adaptive importance sampling method for estimation of reliability sensitivity[J].Engi-neering Mechanics, 2008, 25(4):80-84
[20]Borgonovo E.A new uncertainty importance measure[J].Reliability Engineering & System Safety, 2007, 92(6):771-784
[21]Wan H, Xia J, Zhang L, et al.Sensitivity and interaction analysis based on Sobol’method and its application in a distributed flood forecasting model[J].Water, 2015, 7(6):2924-2951
[22]Sobol’ I M, Kucherenko S.Derivative based global sen-sitivity measures and their link with global sensitivity in-dices[J].Mathematics and Computers in Simulation, 2009, 79(10):3009-3017
[23]Wright L F.Information gap decision theory: decisions under severe uncertainty[J].Journal of the Royal Statisti-cal Society Series A: Statistics in Society, 2003, 167(1):185-186
CJA