Line Sampling Simulation

Line sampling is an efficient sampling-based simulation approach for reliability analysis of complex engineering structures and systems. It is particularly suitable for estimating the probability of occurrence of rare events for problems involving a large number of uncertain parameters and moderately nonlinear behavior. The basis of line sampling consists of combining random sampling with univariate numerical integration along a so-called important direction. This chapter provides an overview of the line sampling approach, its basic theoretical formulation as well as recent extensions and improvements. In addition, practical applications in reliability sensitivity estimation, coupling with surrogate models, estimation of interval failure probabilities in problems involving aleatoric and epistemic uncertainty, and software implementation are discussed as well. Line sampling is one of the most efficient approaches for reliability analysis, capable of dealing with industry-sized problems, which makes it a reliable and mature approach for simulation.