A novel fractional moments-based maximum entropy method for high-dimensional reliability analysis

High-dimensional reliability analysis is still an open challenge in structural reliability community. To address this problem, a new sampling approach, named the good lattice point method based partially stratified sampling is proposed in the fractional moments-based maximum entropy method. In this approach, the original sample space is first partitioned into several orthogonal low-dimensional sample spaces, say 2 and 1 dimensions. Then, the samples in each low-dimensional sample space are generated by the good lattice point method, which are deterministic points and possess the property of large variance reduction. Finally, the samples in the original space can be obtained by randomly pairing the samples in low-dimensions, which may also significantly reduce the variance in high-dimensional cases. Then, this sampling approach is applied to evaluate the low-order fractional moments in the maximum entropy method with the tradeoff of efficiency and accuracy for high-dimensional reliability problems. In this regard, the probability density function of the performance function involving a large number of random inputs can be derived accordingly, where the reliability can be straightforwardly evaluated by a simple integral over the probability density function. Numerical examples are studied to validate the proposed method, which indicate the proposed method is of accuracy and efficiency for high-dimensional reliability analysis.     

M5 model tree and Monte Carlo simulation for efficient structural reliability analysis

Practically, the performance of many engineering problems can be defined using a complex implicit limit state function. Approximation of the accurate failure probability is very time-consuming and inefficient based on Monte Carlo simulation (MCS) for complex performance functions. M5 model tree (M5Tree) model is robust approach for simulation and prediction phenomena, which provides ability to dealing with complex implicit problems by dividing them into smaller problems. By improving the efficiency of reliability method using accurate approximated failure probability, an efficient reliability method using the MCS and M5Tree is proposed to calibrate the performance function and estimate the failure probability, respectively. The superiorities including simplicity and accuracy of M5Tree meta-model are investigated to evaluate the actual performance function through five nonlinear complex mathematical and structural reliability problems. The proposed reliability method-based MCS and M5Tree improved the computational efforts for evaluating the performance function in reliability analysis. The M5Tree significantly increased the efficiency of reliability analysis with accurate failure probability.     

Gaussian cubature: A practitioner’s guide

Accurate modeling of management and economic processes often requires that researchers accurately approximate the expectations of functions of random variables. While commonly employed, Monte Carlo simulation techniques generally require large sample sizes to insure accuracy. For functions that are computationally burdensome, the Monte Carlo approach may be impractical. We propose a method to generate samples from multivariate distributions that contain far fewer points than reliable Monte Carlo samples, yet retain much of the original distributions’ information. Our method, Gaussian cubatures generated via linear programming, is designed to be feasible for joint, but independent distributions. While heuristic for joint, dependent distributions, this method appears to be very reliable and to accurately approximate expectations of an important class of functions.     

结构可靠性分析的支持向量机方法

针对结构可靠性分析中功能函数不能显式表达的问题,将支持向量机方法引入到结构可靠性分析中．支持向量机是一种实现了结构风险最小化原则的分类技术,它具有出色的小样本学习性能和良好的泛化性能,因此提出了两种基于支持向量机的结构可靠性分析方法．与传统的响应面法和神经网络法相比,支持向量机可靠性分析方法的显著特点是在小样本下高精度地逼近函数,并且可以避免维数灾难．算例结果也充分表明支持向量机方法可以在抽样范围内很好地逼近真实的功能函数,减少隐式功能函数分析（通常是有限元分析）的次数,具有一定的工程实用价值．     

Enriched self-adjusted performance measure approach for reliability-based design optimization of complex engineering problems

For reliability-based design optimization (RBDO) of practical structural/mechanical problems under highly nonlinear constraints, it is an important characteristic of the performance measure approach (PMA) to show robustness and high convergence rate. In this study, self-adjusted mean value is used in the PMA iterative formula to improve the robustness and efficiency of the RBDO-based PMA for nonlinear engineering problems based on dynamic search direction. A novel merit function is applied to adjust the modified search direction in the enriched self-adjusted mean value (ESMV) method, which can control the instability and value of the step size for highly nonlinear probabilistic constraints in RBDO problems. The convergence performance of the enriched self-adjusted PMA is illustrated using four nonlinear engineering problems. In particular, a complex engineering example of aircraft stiffened panel is used to compare the RBDO results of different reliability methods. The results demonstrate that the proposed self-adjusted steepest descent search direction can improve the computational efficiency and robustness of the PMA compared to existing modified reliability methods for nonlinear RBDO problems.     

机械可靠性分析的高精度响应面法

通过对已有可靠性分析中的响应面法的研究,提出了一种高精度的响应面法,该方法通过迭代线性插值的策略,来保证确定响应面的抽样点比经典的响应面法更接近真实的极限状态方程,并且该方法通过序列线性插值的方法来控制抽样点与插值中心点的距离,保证随着插值中心点收敛于真实设计点,抽样点提供更多的关于设计点附近真实极限状态方程的信息,进而保证了收敛的响应面能够在设计点附近更好地拟合真实的极限状态方程,并得到高精度的失效概率计算结果．算例充分说明了所提方法的合理性与适用性．     

Selecting rows and columns for training support vector regression models with large retail datasets

Although support vector regression models are being used successfully in various applications, the size of the business datasets with millions of observations and thousands of variables makes training them difficult, if not impossible to solve. This paper introduces the Row and Column Selection Algorithm (ROCSA) to select a small but informative dataset for training support vector regression models with standard SVM tools. ROCSA uses ε-SVR models with L₁-norm regularization of the dual and primal variables for the row and column selection steps, respectively. The first step involves parallel processing of data chunks and selects a fraction of the original observations that are either representative of the pattern identified in the chunk, or represent those observations that do not fit the identified pattern. The column selection step dramatically reduces the number of variables and the multicolinearity in the dataset, increasing the interpretability of the resulting models and their ease of maintenance. Evaluated on six retail datasets from two countries and a publicly available research dataset, the reduced ROCSA training data improves the predictive accuracy on average by 39% compared with the original dataset when trained with standard SVM tools. Comparison with the ε SSVR method using reduced kernel technique shows similar performance improvement. Training a standard SVM tool with the ROCSA selected observations improves the predictive accuracy on average by 21% compared to the practical approach of random sampling.     

具有强非线性状态方程的机械零部件可靠性灵敏度分析方法

基于可靠性灵敏度设计的随机摄动技术,结合可靠性分析的矩方法、矩阵微分理论和Kronecker代数的相关理论,讨论了实际中存在着高度非线性极限状态方程结构的可靠性灵敏度问题．在已知随机变量前4阶矩的前提下,对基于摄动法的可靠性灵敏度计算方法进行了修正,提出了具有高度非线性结构的可靠性灵敏度计算方法．并结合实例证明了采用此方法大大提高了可靠性灵敏度的计算精度,并为工程实际提供了更加可信的理论依据．     

A hybrid conjugate finite-step length method for robust and efficient reliability analysis

The robustness and efficiency of the first-order reliability method (FORM) are the important issues in the structural reliability analysis. In this paper, a hybrid conjugate search direction with finite-step length is proposed to improve the efficiency and robustness of FORM, namely hybrid conjugate finite-step length (CFSL-H). The conjugate scalar factor in CFSL-H is adaptively updated using two conjugate methods with a dynamic participation factor. The accuracy, efficiency and robustness of the CFSL-H are illustrated through the nonlinear explicit and structural implicit limit state functions with normal and non-normal random variables. The results illustrated that the proposed CFSL-H algorithm is more robust, efficient and accurate than the modified existing FORM algorithms for complex structural problems.     

Rare Event Probability Estimation in the Presence of Epistemic Uncertainty on Input Probability Distribution Parameters

The accurate estimation of rare event probabilities is a crucial problem in engineering to characterize the reliability of complex systems. Several methods such as Importance Sampling or Importance Splitting have been proposed to perform the estimation of such events more accurately (i.e., with a lower variance) than crude Monte Carlo method. However, these methods assume that the probability distributions of the input variables are exactly defined (e.g., mean and covariance matrix perfectly known if the input variables are defined through Gaussian laws) and are not able to determine the impact of a change in the input distribution parameters on the probability of interest. The problem considered in this paper is the propagation of the input distribution parameter uncertainty defined by intervals to the rare event probability. This problem induces intricate optimization and numerous probability estimations in order to determine the upper and lower bounds of the probability estimate. The calculation of these bounds is often numerically intractable for rare event probability (say 10^?5), due to the high computational cost required. A new methodology is proposed to solve this problem with a reduced simulation budget, using the adaptive Importance Sampling. To this end, a method for estimating the Importance Sampling optimal auxiliary distribution is proposed, based on preceding Importance Sampling estimations. Furthermore, a Kriging-based adaptive Importance Sampling is used in order to minimize the number of evaluations of the computationally expensive simulation code. To determine the bounds of the probability estimate, an evolutionary algorithm is employed. This algorithm has been selected to deal with noisy problems since the Importance Sampling probability estimate is a random variable. The efficiency of the proposed approach, in terms of accuracy of the found results and computational cost, is assessed on academic and engineering test cases.     

Artificial neural network based inverse reliability analysis

An inverse reliability analysis is the problem to find design parameters corresponding to specified reliability levels expressed by reliability index or by theoretical failure probability. Design parameters can be deterministic or they can be associated to random variables described by statistical moments. The aim is to solve generally not only the single design parameter case but also the multiple parameter problems with given multiple reliability constraints. A new general approach of inverse reliability analysis is proposed. The inverse analysis is based on the coupling of a stochastic simulation of Monte Carlo type and an artificial neural network. A novelty of the approach is the utilization of the efficient small-sample simulation method Latin Hypercube Sampling used for the stochastic preparation of the training set. (© 2010 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim)     

Structural reliability analysis with imprecise random and interval fields

This paper investigates the issue of reliability assessment for engineering structures involving mixture of stochastic and non-stochastic uncertain parameters through the Finite Element Method (FEM). Non-deterministic system inputs modelled by both imprecise random and interval fields have been incorporated, so the applicability of the structural reliability analysis scheme can be further promoted to satisfy the intricate demand of modern engineering application. The concept of robust structural reliability profile for systems involving hybrid uncertainties is discussed, and then a new computational scheme, namely the unified interval stochastic reliability sampling (UISRS) approach, is proposed for assessing the safety of engineering structures. The proposed method provides a robust semi-sampling scheme for assessing the safety of engineering structures involving multiple imprecise random fields with various distribution types and interval fields simultaneously. Various aspects of structural reliability analysis with multiple imprecise random and interval fields are explored, and some theoretically instructive remarks are also reported herein.     

A new method for reliability analysis of structures with mixed random and convex variables

This paper proposes a method combining projection-outline-based active learning strategy with Kriging metamodel for reliability analysis of structures with mixed random and convex variables. In this method, it is determined that the approximation accuracy of projection outlines on the limit-state surface is crucial for estimation of failure probability instead of the whole limit-state surface. To efficiently improve the approximation accuracy of projection outlines, a new projection-outline-based active learning strategy is developed to sequentially obtain update points located around the projection outlines. Taking into account the influence of metamodel uncertainty on the estimation of failure probability, a quantification function of metamodel uncertainty is developed and introduced in the stopping condition of Kriging metamodel update. Finally, Monte Carlo simulation is employed to calculate the failure probability based on the refined Kriging metamodel. Four examples including the Burro Creek Bridge and a piezoelectric energy harvester are tested to validate the performance of the proposed method. Results indicate that the proposed method is accurate and efficient for reliability analysis of structures with mixed random and convex variables.     

An efficient third-moment saddlepoint approximation for probabilistic uncertainty analysis and reliability evaluation of structures

This paper presents an efficient third-moment saddlepoint approximation approach for probabilistic uncertainty analysis and reliability evaluation of random structures. By constructing a concise cumulant generating function (CGF) for the state variable according to its first three statistical moments, approximate probability density function and cumulative distribution function of the state variable, which may possess any types of distribution, are obtained analytically by using saddlepoint approximation technique. A convenient generalized procedure for structural reliability analysis is then presented. In the procedure, the simplicity of general moment matching method and the accuracy of saddlepoint approximation technique are integrated effectively. The main difference of the presented method from existing moment methods is that the presented method may provide more detailed information about the distribution of the state variable. The main difference of the presented method from existing saddlepoint approximation techniques is that it does not strictly require the existence of the CGFs of input random variables. With the advantages, the presented method is more convenient and can be used for reliability evaluation of uncertain structures where the concrete probability distributions of input random variables are known or unknown. It is illustrated and examined by five representative examples that the presented method is effective and feasible.     

离散变量的分级优化方法及其应用

在工程优化设计中,绝大多数实际问题的设计变量往往限定取离散值,为了求得问题的真正最优解,就必须采用离散变量的优化方法进行求解.本文根据离散变量数学规划的特性,提出了一种分级优化搜索算法.这种方法的基本思想是在约束集合内,寻求一可行的离散初始点,然后在该点的邻域内,进行分级寻优搜索,以求得一个改进的新离散点,随之,以该点作为初始点,重复执行分级寻优搜索过程,直至求得问题的最优解.通过对工程实例的计算,证明本文所提出的新方法具有快速、简便的特点,能有效地应用各种工程优化设计问题.     

Markov decision processes for infinite horizon problems solved with the cosine simplex method

This article presents a new method of linear programming (LP) for solving Markov decision processes (MDPs) based on the simplex method (SM). SM has shown to be the most efficient method in many practical problems; unfortunately, classical SM has an exponential complexity. Therefore, new SMs have emerged for obtaining optimal solutions in the most efficient way. The cosine simplex method (CSM) is one of them. CSM is based on the Karush Kuhn Tucker conditions, and is able to efficiently solve general LP problems. This work presents a new method named the Markov Cosine Simplex Method (MCSM) for solving MDP problems, which is an extension of CSM. In this article, the efficiency of MCSM is compared to the traditional revised simplex method (RSM); experimental results show that MCSM is far more efficient than RSM.     

On computing distributions of products of non-negative independent random variables

We introduce a new functional representation of probability density functions (PDFs) of non-negative random variables via a product of a monomial factor and linear combinations of decaying exponentials with complex exponents. This approximate representation of PDFs is obtained for any finite, user-selected accuracy. Using a fast algorithm involving Hankel matrices, we develop a general numerical method for computing the PDF of the sums, products, or quotients of any number of non-negative independent random variables yielding the result in the same type of functional representation. We present several examples to demonstrate the accuracy of the approach.     

A response-surface-based structural reliability analysis method by using non-probability convex model

Due to its weak dependence on the amount of the uncertainty information, the non-probability convex model approach can be used to deal with the problems without sufficient information. In this paper, by integrating the response surface (RS) technique with the convex model approach, a new structural reliability analysis method is developed for many complex engineering problems with black-box limit-state functions. Using the newly developed correlation analysis technique for non-probability convex model, the multi-dimensional ellipsoid is efficiently constructed to characterize the uncertain parameters. A quadratic polynomial without cross terms is adopted to parameterize the black-box limit-state function, based on which the functional values as well as the first-order gradients can be explicitly calculated. At each iteration, the created RS is combined with the iHL-RF algorithm to obtain an approximate reliability index. A sequential procedure is subsequently formulated to update the RS and hence improve the precision of the reliability analysis. Four numerical examples and one engineering application are investigated to demonstrate the effectiveness of the presented method.     

基于支持向量机委员会机器的个人信用评估模型

为了充分利用SVM在个人信用评估方面的优点、克服其不足,提出了基于支持向量机委员会机器的个人信用评估模型.将模型与基于属性效用函数估计构造新学习样本方法结合起来进行个人信用评估;经实证分析及与SVM方法对比发现,模型具有更好、更快、更多适应性的预测分类能力.     

A practical non-parametric copula algorithm for system reliability with correlations

System reliability analysis involving correlated random variables is challenging because the failure probability cannot be uniquely determined under the given probability information. This paper proposes a system reliability evaluation method based on non-parametric copulas. The approximated joint probability distribution satisfying the constraints specified by correlations has the maximal relative entropy with respect to the joint probability distribution of independent random variables. Thus the reliability evaluation is unbiased from the perspective of information theory. The estimation of the non-parametric copula parameters from Pearson linear correlation, Spearman rank correlation, and Kendall rank correlation are provided, respectively. The approximated maximum entropy distribution is then integrated with the first and second order system reliability method. Four examples are adopted to illustrate the accuracy and efficiency of the proposed method. It is found that traditional system reliability method encodes excessive dependence information for correlated random variables and the estimated failure probability can be significantly biased.