Structural reliability analysis of multiple limit state functions using multi-input multi-output support vector machine

Abstract

Selecting and using an appropriate structural reliability method is critical for the success of structural reliability analysis and reliability-based design optimization. However, most of existing structural reliability methods are developed and designed for a single limit state function and few methods can be used to simultaneously handle multiple limit state functions in a structural system when the failure probability of each limit state function is of interest, for example, in a reliability-based design optimization loop. This article presents a new method for structural reliability analysis with multiple limit state functions using support vector machine technique. A sole support vector machine surrogate model for all limit state functions is constructed by a multi-input multi-output support vector machine algorithm. Furthermore, this multi-input multi-output support vector machine surrogate model for all limit state functions is only trained from one data set with one calculation process, instead of constructing a series of standard support vector machine models which has one output only. Combining the multi-input multi-output support vector machine surrogate model with direct Monte Carlo simulation, the failure probability of the structural system as well as the failure probability of each limit state function corresponding to a failure mode in the structural system can be estimated. Two examples are used to demonstrate the accuracy and efficiency of the presented method.

Support vector machine in structural reliability analysis: A review

“…Various DOE schemes have been developed for efficient reliability estimation by SVR-based metamodeling approach. Li et al [73] adopted the median Latin hypercube (LH) sampling to obtain the training samples for the multi-input multi-output SVR model which was used for SRA of problems involving multiple LSFs. Further, Li et al [68] proposed a hybrid approach combining uniform design and SVR-based metamodel for reliability analysis of tunnel structures.…”

A new surrogate modeling method combining polynomial chaos expansion and Gaussian kernel in a sparse Bayesian learning framework

“…Kernel‐based surrogate modeling methods typically make use of local information related to each training data point and combine this information to define the overall surrogate model. Support vector regression, neural network, and Kriging (also known as Gaussian process modeling) are popular kernel‐based surrogate modeling techniques. Recently, Schöbi et al and Kersaudy et al have developed a new surrogate modeling technique called PC‐Kriging.…”

Combination of line sampling and important sampling for reliability assessment of buried pipelines

“…The methods mentioned above are all available in the literature. [9][10][11][12][13][14][15] Corrosion of underground pipeline is associated with high degree of variability and has been a major contributing factor for the pipe failure as a result of large spatial and temporary variabilities. 16 Due to the spatial and temporary variabilities of the corrosion parameters, the need to develop a more efficient and reliable quantification approach for estimating pipe failure becomes very imperative due to the need to have robust engineering structures.…”