Evaluating small failure probabilities of multiple limit states by parallel subset simulation

A novel subset simulation algorithm, called the parallel subset simulation, is proposed to estimate small failure probabilities of multiple limit states with only a single subset simulation analysis. As well known, crude Monte Carlo simulation is inefficient in estimating small probabilities but is applicable to multiple limit states, while the ordinary subset simulation is efficient in estimating small probabilities but can only handle a single limit state. The proposed novel stochastic simulation approach combines the advantages of the two simulation methods: it is not only efficient in estimating small probabilities but also applicable to multiple limit states. The key idea is to introduce a “principal variable” which is correlated with all performance functions. The failure probabilities of all limit states therefore could be evaluated simultaneously when subset simulation algorithm generates the principal variable samples. The statistical properties of the failure probability estimators are also derived. Two examples are presented to demonstrate the effectiveness of the new approach and to compare with crude Monte Carlo and ordinary subset simulation methods.     

Modified Metropolis-Hastings algorithm with delayed rejection

The development of an efficient MCMC strategy for sampling from complex distributions is a difficult task that needs to be solved for calculating the small failure probabilities encountered in the high-dimensional reliability analysis of engineering systems. Usually different variations of the Metropolis-Hastings algorithm (MH) are used. However, the standard MH algorithm does not generally work in high dimensions, since it leads to very frequent repeated samples. In order to overcome this deficiency one can use the Modified Metropolis-Hastings algorithm (MMH) proposed in Au and Beck (2001) [1]. Another variation of the MH algorithm, called the Metropolis-Hastings algorithm with delayed rejection (MHDR) has been proposed by Tierney and Mira (1999) [7]. The key idea behind the MHDR algorithm is to reduce the correlation between states of the Markov chain. In this paper we combine the ideas of MMH and MHDR and propose a novel modification of the MH algorithm, called the Modified Metropolis-Hastings algorithm with delayed rejection (MMHDR). The efficiency of the new algorithm is demonstrated with a numerical example where MMHDR is used together with Subset simulation for computing small failure probabilities in high dimensions.     

Hybrid Subset Simulation method for reliability estimation of dynamical systems subject to stochastic excitation

A hybrid Subset Simulation approach is proposed for reliability estimation for general dynamical systems subject to stochastic excitation. This new stochastic simulation approach combines the advantages of the two previously proposed Subset Simulation methods, Subset Simulation with Markov Chain Monte Carlo (MCMC) algorithm and Subset Simulation with splitting. The new method employs the MCMC algorithm before reaching an intermediate failure level and splitting after reaching the level to exploit the causality of dynamical systems. The statistical properties of the failure probability estimators are derived. Two examples are presented to demonstrate the effectiveness of the new approach and to compare with the previous two Subset Simulation methods. The results show that the new method is robust to the choice of proposal distribution for the MCMC algorithm and to the intermediate failure events selected for Subset Simulation.     

Local estimation of failure probability function by weighted approach

In the reliability-based design of engineering systems, it is often required to evaluate the failure probability for different values of distribution parameters involved in the specification of design configuration. The failure probability as a function of the distribution parameters is referred as the ‘failure probability function (FPF)’ in this work. From first principles, this problem requires repeated reliability analyses to estimate the failure probability for different distribution parameter values, which is a computationally expensive task. A “weighted approach” is proposed in this work to locally evaluate the FPF efficiently by means of a single simulation. The basic idea is to rewrite the failure probability estimate for a given set of random samples in simulation as a function of the distribution parameters. It is shown that the FPF can be written as a weighted sum of sample values. The latter must be evaluated by system analysis (the most time-consuming task) but they do not depend on the distribution. Direct Monte Carlo simulation, importance sampling and Subset Simulation are incorporated under the proposed approach. Examples are given to illustrate their application.     

MCMC algorithms for Subset Simulation

Subset Simulation is an adaptive simulation method that efficiently solves structural reliability problems with many random variables. The method requires sampling from conditional distributions, which is achieved through Markov Chain Monte Carlo (MCMC) algorithms. This paper discusses different MCMC algorithms proposed for Subset Simulation and introduces a novel approach for MCMC sampling in the standard normal space. Two variants of the algorithm are proposed: a basic variant, which is simpler than existing algorithms with equal accuracy and efficiency, and a more efficient variant with adaptive scaling. It is demonstrated that the proposed algorithm improves the accuracy of Subset Simulation, without the need for additional model evaluations.     

Modified Metropolis-Hastings algorithm with reduced chain correlation for efficient subset simulation

Simulation of Markov chain samples using the Metropolis-Hastings algorithm is useful for reliability estimation. Subset simulation is an example of the reliability estimation method utilizing this algorithm. The efficiency of the simulation is governed by the correlation between the simulated Markov chain samples. The objective of this study is to propose a modified Metropolis-Hastings algorithm with reduced chain correlation. The modified algorithm differs from the original in terms of the transition probability. It has been verified that the modified algorithm satisfies the reversibility condition and therefore the simulated samples follow the target distribution for the correct theoretical reasons. When applied to subset simulation, the modified algorithm produces a more accurate estimate of failure probability as indicated by a lower coefficient of variation and a lower mean square error. The advantage is more significant for small failure probability. Examples of soil slope with spatially variable properties were presented to demonstrate the applicability of the proposed modification to reliability estimation of engineering problems. It was found that the modified algorithm produces a more accurate estimator over the range of random dimensions studied.     

Analyzing maintenance strategies by agent-based simulations: A feasibility study

Thoroughly planned and implemented maintenance strategies save time and cost. However, the integration of maintenance work into reliability analysis is difficult as common modeling techniques are often not applicable due to state explosion which calls for restrictive model assumptions and oversimplification. From authors’ point of view, agent-based modeling (ABM) of technical and organizational systems is a promising approach to overcome such problems. But since ABM is not well established in reliability analysis its feasibility in this area still has to be demonstrated. For this purpose ABM is compared with Markov chains, namely by analyzing the reliability of a maintained n-unit system with dependent repair events, applying both modeling approaches. Although ABM and Markov chains lead to the same numerical results, the former points out the potentiality of an improved system state handling. This is demonstrated by extending the ABM with operators as additional “agents” featuring their location (x;y) availability (0;1) and different maintenance strategies. This extension highlights the capability of ABM to analyze complex emergent system behavior and allows a systematic refinement and optimization of the maintenance strategies.     

Subset simulation for structural reliability sensitivity analysis

Based on two procedures for efficiently generating conditional samples, i.e. Markov chain Monte Carlo (MCMC) simulation and importance sampling (IS), two reliability sensitivity (RS) algorithms are presented. On the basis of reliability analysis of Subset simulation (Subsim), the RS of the failure probability with respect to the distribution parameter of the basic variable is transformed as a set of RS of conditional failure probabilities with respect to the distribution parameter of the basic variable. By use of the conditional samples generated by MCMC simulation and IS, procedures are established to estimate the RS of the conditional failure probabilities. The formulae of the RS estimator, its variance and its coefficient of variation are derived in detail. The results of the illustrations show high efficiency and high precision of the presented algorithms, and it is suitable for highly nonlinear limit state equation and structural system with single and multiple failure modes.     

General network reliability problem and its efficient solution by Subset Simulation

Complex technological networks designed for distribution of some resource or commodity are a pervasive feature of modern society. Moreover, the dependence of our society on modern technological networks constantly grows. As a result, there is an increasing demand for these networks to be highly reliable in delivering their service. As a consequence, there is a pressing need for efficient computational methods that can quantitatively assess the reliability of technological networks to enhance their design and operation in the presence of uncertainty in their future demand, supply and capacity. In this paper, we propose a stochastic framework for quantitative assessment of the reliability of network service, formulate a general network reliability problem within this framework, and then show how to calculate the service reliability using Subset Simulation, an efficient Markov chain Monte Carlo method that was originally developed for estimating small failure probabilities of complex dynamic systems. The efficiency of the method is demonstrated with an illustrative example where two small-world network generation models are compared in terms of the maximum-flow reliability of the networks that they produce.     

A study using Monte Carlo Simulation for failure probability calculation in Reliability-Based Optimization

In this study, a Reliability-Based Optimization (RBO) methodology that uses Monte Carlo Simulation techniques, is presented. Typically, the First Order Reliability Method (FORM) is used in RBO for failure probability calculation and this is accurate enough for most practical cases. However, for highly nonlinear problems it can provide extremely inaccurate results and may lead to unreliable designs. Monte Carlo Simulation (MCS) is usually more accurate than FORM but very computationally intensive. In the RBO methodology presented in this paper, limit state approximations are used in conjunction with MCS techniques in an approximate MCS-based RBO that facilitates the efficient calculation of the probabilities of failure. A FORM-based RBO is first performed to obtain the initial limit state approximations. A Symmetric Rank-1 (SR1) variable metric algorithm is used to construct and update the quadratic limit state approximations. The approximate MCS-based RBO uses a conditional-expectation-based MCS, that was chosen over indicator-based MCS because of the smoothness of the probability of failure estimates and the availability of analytic sensitivities. The RBO methodology was implemented for an analytic test problem and a higher-dimensional, control-augmented-structure test problem. The results indicate that the SR1 algorithm provides accurate limit state approximations (and therefore accurate estimates of the probabilities of failure) for these test problems. It was also observed that the RBO methodology required two orders of magnitude fewer analysis calls than an approach that used exact limit state evaluations for both test problems.     

Reliability of structures in high dimensions. Part II. Theoretical validation

This paper provides proofs to the claims made [Probab. Eng. Mech. (submitted)] concerning the convergence rates of the estimators used.     

Relative importance of uncertain structural parameters. Part I: algorithm

A novel procedure for estimating the relative importance of uncertain parameters of complex FE model is presented. The method is specifically directed toward problems involving high-dimensional input parameter spaces, as they are encountered during uncertainty analysis of large scale, refined FE models. In these cases one is commonly faced with thousands of uncertain parameters and traditional techniques, e.g. finite difference or direct differentiation methods become expensive. In contrast, the presented method quickly filters out the most influential variables. Hence, the main objective is not to compute the sensitivity but to identify those parameters whose random variations have the biggest influence on the response. This is achieved by generating a set of samples with direct Monte Carlo simulation, which are closely scattered around the point at which the relative importance measures are sought. From these samples, estimators of the relative importance are synthesized and the most important ones are refined with a method of choice. In this paper, the underlying theory as well as the resulting algorithm is presented.     

A fully Bayesian approach for combining multilevel failure information in fault tree quantification and optimal follow-on resource allocation

This paper presents a fully Bayesian approach that simultaneously combines non-overlapping (in time) basic event and higher-level event failure data in fault tree quantification. Such higher-level data often correspond to train, subsystem or system failure events. The fully Bayesian approach also automatically propagates the highest-level data to lower levels in the fault tree. A simple example illustrates our approach. The optimal allocation of resources for collecting additional data from a choice of different level events is also presented. The optimization is achieved using a genetic algorithm.     

A fully Bayesian approach for combining multi-level information in multi-state fault tree quantification

This paper presents a fully Bayesian approach that simultaneously combines non-overlapping (in time) basic event and higher-level event failure data in fault tree quantification with multi-state events. Such higher-level data often correspond to train, subsystem or system failure events. The fully Bayesian approach also automatically propagates the highest-level data to lower levels in the fault tree. A simple example illustrates our approach.     

Geometric insight into the challenges of solving high-dimensional reliability problems

In this paper we adopt a geometric perspective to highlight the challenges associated with solving high-dimensional reliability problems. Adopting a geometric point of view we highlight and explain a range of results concerning the performance of several well-known reliability methods.

We start by investigating geometric properties of the N-dimensional Gaussian space and the distribution of samples in such a space or in a subspace corresponding to a failure domain. Next, we discuss Importance Sampling (IS) in high dimensions. We provide a geometric understanding as to why IS generally does not work in high dimensions [Au SK, Beck JL. Importance sampling in high dimensions. Structural Safety 2003;25(2):139–63]. We furthermore challenge the significance of “design point” when dealing with strongly nonlinear problems. We conclude by showing that for the general high-dimensional nonlinear reliability problems the selection of an appropriate fixed IS density is practically impossible.

Next, we discuss the simulation of samples using Markov Chain Monte Carlo (MCMC) methods. Firstly, we provide a geometric explanation as to why the standard Metropolis–Hastings (MH) algorithm does “not work” in high-dimensions. We then explain why the modified Metropolis–Hastings (MMH) algorithm introduced by Au and Beck [Au SK, Beck JL. Estimation of small failure probabilities in high dimensions by subset simulation. Probabilistic Engineering Mechanics 2001;16(4):263–77] overcomes this problem. A study of the correlation of samples obtained using MMH as a function of different parameters follows. Such study leads to recommendations for fine-tuning the MMH algorithm. Finally, the MMH algorithm is compared with the MCMC algorithm proposed by Katafygiotis and Cheung [Katafygiotis LS, Cheung SH. Application of spherical subset simulation method and auxiliary domain method on a benchmark reliability study, Structural Safety 2006 (in print)] in terms of the correlation of samples they generate.     

Fast Monte Carlo reliability evaluation using support vector machine

This paper deals with the feasibility of using support vector machine (SVM) to build empirical models for use in reliability evaluation. The approach takes advantage of the speed of SVM in the numerous model calculations typically required to perform a Monte Carlo reliability evaluation. The main idea is to develop an estimation algorithm, by training a model on a restricted data set, and replace system performance evaluation by a simpler calculation, which provides reasonably accurate model outputs. The proposed approach is illustrated by several examples. Excellent system reliability results are obtained by training a SVM with a small amount of information.     

First excursion probabilities for linear systems by very efficient importance sampling

An analytical study of the failure region of the first excursion reliability problem for linear dynamical systems subjected to Gaussian white noise excitation is carried out with a view to constructing a suitable importance sampling density for computing the first excursion failure probability. Central to the study are ‘elementary failure regions’, which are defined as the failure region in the load space corresponding to the failure of a particular output response at a particular instant. Each elementary failure region is completely characterized by its design point, which can be computed readily using impulse response functions of the system. It is noted that the complexity of the first excursion problem stems from the structure of the union of the elementary failure regions. One important consequence of this union structure is that, in addition to the global design point, a large number of neighboring design points are important in accounting for the failure probability. Using information from the analytical study, an importance sampling density is proposed. Numerical examples are presented, which demonstrate that the efficiency of using the proposed importance sampling density to calculate system reliability is remarkable.     

蒙特卡洛仿真在工程项目进度管理中的应用

对于工序时间具有随机性的复杂工程项目,在Excel中运用蒙特卡洛仿真获得项目的完成时间分布并找出关键工序。在一新产品研制项目的仿真模型中,运用Excel中的“公式”表示项目完成时间的算法,用蒙特卡洛法处理工序时间的不确定性。仿真运行后,获得了项目完成时间的频数图和相关统计量,通过灵敏度分析确定各工序对项目完成时间变动的影响程度。     

Local estimation of failure probability function and its confidence interval with maximum entropy principle

An approach is developed to locally estimate the failure probability of a system under various design values. Although it seems to require numerous reliability analysis runs to locally estimate the failure probability function, which is a function of the design variables, the approach only requires a single reliability analysis run. The approach can be regarded as an extension of that proposed by Au [Au SK. Reliability-based design sensitivity by efficient simulation. Computers and Structures 2005;83(14):1048–61], but it proposes a better framework in estimating the failure probability function. The key idea is to implement the maximum entropy principle in estimating the failure probability function. The resulting local failure probability function estimate is more robust; moreover, it is possible to find the confidence interval of the failure probability function as well as estimate the gradient of the logarithm of that function with respect to the design variables. The use of the new approach is demonstrated with several simulated examples. The results show that the new approach can effectively locally estimate the failure probability function and the confidence interval with one single Subset Simulation run. Moreover, the new approach is applicable when the dimension of the uncertainties is high and when the system is highly nonlinear. The approach should be valuable for reliability-based optimization and reliability sensitivity analysis.     

Coherence region of the Priority‐AND gate: Analytical and numerical examples

In recent years, the need for a more accurate dependability modelling (encompassing reliability, availability, maintenance, and safety) has favoured the emergence of novel dynamic dependability techniques able to account for temporal and stochastic dependencies of a system. One of the most successful and widely used methods is Dynamic Fault Tree that, with the introduction of the dynamic gates, enables the analysis of dynamic failure logic systems such as fault‐tolerant or reconfigurable systems. Among the dynamic gates, Priority‐AND (PAND) is one of the most frequently used gates for the specification and analysis of event sequences. Despite the numerous modelling contributions addressing the resolution of the PAND gate, its failure logic and the consequences for the coherence behaviour of the system need to be examined to understand its effects for engineering decision‐making scenarios including design optimization and sensitivity analysis. Accordingly, the aim of this short communication is to analyse the coherence region of the PAND gate so as to determine the coherence bounds and improve the efficacy of the dynamic dependability modelling process.