Recent advances in reliability-based structural optimization under earthquake loading

In this paper a robust and efficient methodology is presented for treating large-scale reliability-based, structural optimization problems under seismic loads using the pushover analysis method. The optimization problem is solved with the Evolution Strategies method, while the reliability analysis is carried out with the Monte Carlo simulation method. In order to reduce the excessive computational cost of the reliability-based optimization process the repeated structural analyses that are required during the Monte Carlo simulations are replaced by an efficient artificial neural network approximation scheme. 2. Keywords: structural optimization, reliability analysis, Monte Carlo, evolutionary computation, artificial neural networks. Reliability analysis methods have been developed significantly over the last decades and have stimulated the interest for the probabilistic optimum design of structures. Despite the theoretical advancements and the improvements in the efficiency of the reliability analysis techniques, they still require disproportionate computational effort for treating practical reliability problems. On the other hand, structural optimization is the only rational procedure to assess whether the design adopted meets the require