Inverse reliability task: Artificial neural networks and reliability-based optimization approaches

Abstract

The paper presents two alternative approaches to solve inverse reliability task - to determine the design parameters to achieve desired target reliabilities. The first approach is based on utilization of artificial neural networks and small-sample simulation Latin hypercube sampling. The second approach considers inverse reliability task as reliability-based optimization task using double-loop method and also small-sample simulation. Efficiency of both approaches is presented in numerical example, advantages and disadvantages are discussed.